Ping O.
Mister Hat
Peter Ding
+jackyzy823
+George Brighton
+Remita Amine
-i, --ignore-errors Continue on download errors, for example to skip unavailable videos in a playlist
--abort-on-error Abort downloading of further videos (in the playlist or the command line) if an error occurs
--dump-user-agent Display the current browser identification
- --list-extractors List all supported extractors and the URLs they would handle
+ --list-extractors List all supported extractors
--extractor-descriptions Output descriptions of all supported extractors
+ --force-generic-extractor Force extraction to use the generic extractor
--default-search PREFIX Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for youtube-dl "large apple".
Use the value "auto" to let youtube-dl guess ("auto_warning" to emit a warning when guessing). "error" just throws an error. The
default value "fixup_error" repairs broken URLs, but emits an error if this is not possible instead of searching.
--playlist-reverse Download playlist videos in reverse order
--xattr-set-filesize Set file xattribute ytdl.filesize with expected filesize (experimental)
--hls-prefer-native Use the native HLS downloader instead of ffmpeg (experimental)
- --external-downloader COMMAND Use the specified external downloader. Currently supports aria2c,curl,wget
+ --external-downloader COMMAND Use the specified external downloader. Currently supports aria2c,curl,httpie,wget
--external-downloader-args ARGS Give these arguments to the external downloader
## Filesystem Options:
--all-formats Download all available video formats
--prefer-free-formats Prefer free video formats unless a specific one is requested
-F, --list-formats List all available formats
- --youtube-skip-dash-manifest Do not download the DASH manifest on YouTube videos
- --merge-output-format FORMAT If a merge is required (e.g. bestvideo+bestaudio), output to given container format. One of mkv, mp4, ogg, webm, flv.Ignored if no
+ --youtube-skip-dash-manifest Do not download the DASH manifests and related data on YouTube videos
+ --merge-output-format FORMAT If a merge is required (e.g. bestvideo+bestaudio), output to given container format. One of mkv, mp4, ogg, webm, flv. Ignored if no
merge is required
## Subtitle Options:
parameters replace existing values. Additional templates: %(album)s, %(artist)s. Example: --metadata-from-title "%(artist)s -
%(title)s" matches a title like "Coldplay - Paradise"
--xattrs Write metadata to the video file's xattrs (using dublin core and xdg standards)
- --fixup POLICY Automatically correct known faults of the file. One of never (do nothing), warn (only emit a warning), detect_or_warn(the default;
+ --fixup POLICY Automatically correct known faults of the file. One of never (do nothing), warn (only emit a warning), detect_or_warn (the default;
fix file if we can, warn otherwise)
--prefer-avconv Prefer avconv over ffmpeg for running the postprocessors (default)
--prefer-ffmpeg Prefer ffmpeg over avconv for running the postprocessors
### HTTP Error 429: Too Many Requests or 402: Payment Required
-These two error codes indicate that the service is blocking your IP address because of overuse. Contact the service and ask them to unblock your IP address, or - if you have acquired a whitelisted IP address already - use the [`--proxy` or `--network-address` options](#network-options) to select another IP address.
+These two error codes indicate that the service is blocking your IP address because of overuse. Contact the service and ask them to unblock your IP address, or - if you have acquired a whitelisted IP address already - use the [`--proxy` or `--source-address` options](#network-options) to select another IP address.
### SyntaxError: Non-ASCII character ###
- **AcademicEarth:Course**
- **AddAnime**
- **AdobeTV**
+ - **AdobeTVVideo**
- **AdultSwim**
- **Aftenposten**
- **Aftonbladet**
- **dailymotion**
- **dailymotion:playlist**
- **dailymotion:user**
+ - **DailymotionCloud**
- **daum.net**
- **DBTV**
- **DctpTv**
- **divxstage**: DivxStage
- **Dotsub**
- **DouyuTV**
+ - **dramafever**
+ - **dramafever:series**
- **DRBonanza**
- **Dropbox**
- **DrTuber**
- **fernsehkritik.tv**
- **fernsehkritik.tv:postecke**
- **Firstpost**
+ - **FiveTV**
- **Flickr**
- **Folketinget**: Folketinget (ft.dk; Danish parliament)
- **FootyRoom**
- **instagram:user**: Instagram user profile
- **InternetVideoArchive**
- **IPrima**
+ - **iqiyi**
- **ivi**: ivi.ru
- **ivi:compilation**: ivi.ru compilations
- **Izlesene**
- **Motherless**
- **Motorsport**: motorsport.com
- **MovieClips**
+ - **MovieFap**
- **Moviezine**
- **movshare**: MovShare
- **MPORA**
- **Odnoklassniki**
- **OktoberfestTV**
- **on.aol.com**
+ - **OnionStudios**
- **Ooyala**
- **OoyalaExternal**
- **OpenFilm**
- **PhilharmonieDeParis**: Philharmonie de Paris
- **Phoenix**
- **Photobucket**
+ - **Pinkbike**
- **Pladform**
- **PlanetaPlay**
- **play.fm**
- **Pyvideo**
- **qqmusic**
- **qqmusic:album**
+ - **qqmusic:playlist**
- **qqmusic:singer**
- **qqmusic:toplist**
- **QuickVid**
- **rutube:movie**: Rutube movies
- **rutube:person**: Rutube person videos
- **RUTV**: RUTV.RU
+ - **Ruutu**
- **safari**: safaribooksonline.com online video
- **safari:course**: safaribooksonline.com online courses
- **Sandia**: Sandia National Laboratories
- **smotri:broadcast**: Smotri.com broadcasts
- **smotri:community**: Smotri.com community videos
- **smotri:user**: Smotri.com user videos
+ - **SnagFilms**
+ - **SnagFilmsEmbed**
- **Snotr**
- **Sohu**
- **soompi**
- **TheOnion**
- **ThePlatform**
- **TheSixtyOne**
+ - **ThisAmericanLife**
- **ThisAV**
- **THVideo**
- **THVideoPlaylist**
- **TV2**
- **TV2Article**
- **TV4**: tv4.se and tv4play.se
+ - **TVC**
+ - **TVCArticle**
- **tvigle**: Интернет-телевидение Tvigle.ru
- **tvp.pl**
- **tvp.pl:Series**
- **twitch:stream**
- **twitch:video**
- **twitch:vod**
+ - **TwitterCard**
- **Ubu**
- **udemy**
- **udemy:course**
- **XBef**
- **XboxClips**
- **XHamster**
+ - **XHamsterEmbed**
- **XMinus**
- **XNXX**
- **Xstream**
- **YesJapan**
- **Ynet**
- **YouJizz**
- - **Youku**
+ - **youku**
- **YouPorn**
- **YourUpload**
- **youtube**: YouTube.com
username: Username for authentication purposes.
password: Password for authentication purposes.
- videopassword: Password for acces a video.
+ videopassword: Password for accessing a video.
usenetrc: Use netrc for authentication instead.
verbose: Print additional info to stdout.
quiet: Do not print messages to stdout.
outtmpl: Template for output names.
restrictfilenames: Do not allow "&" and spaces in file names
ignoreerrors: Do not stop on download errors.
+ force_generic_extractor: Force downloader to use the generic extractor
nooverwrites: Prevent overwriting files.
playliststart: Playlist item to start at.
playlistend: Playlist item to end at.
info_dict.setdefault(key, value)
def extract_info(self, url, download=True, ie_key=None, extra_info={},
- process=True):
+ process=True, force_generic_extractor=False):
'''
Returns a list with a dictionary for each video we find.
If 'download', also downloads the videos.
extra_info is a dict containing the extra values to add to each result
'''
+ if not ie_key and force_generic_extractor:
+ ie_key = 'Generic'
+
if ie_key:
ies = [self.get_info_extractor(ie_key)]
else:
t.get('preference'), t.get('width'), t.get('height'),
t.get('id'), t.get('url')))
for i, t in enumerate(thumbnails):
- if 'width' in t and 'height' in t:
+ if t.get('width') and t.get('height'):
t['resolution'] = '%dx%d' % (t['width'], t['height'])
if t.get('id') is None:
t['id'] = '%d' % i
info_dict['id'], info_dict.get('subtitles'),
info_dict.get('automatic_captions'))
- # This extractors handle format selection themselves
- if info_dict['extractor'] in ['Youku']:
- if download:
- self.process_info(info_dict)
- return info_dict
-
# We now pick which formats have to be downloaded
if info_dict.get('formats') is None:
# There's only one format available
for url in url_list:
try:
# It also downloads the videos
- res = self.extract_info(url)
+ res = self.extract_info(
+ url, force_generic_extractor=self.params.get('force_generic_extractor', False))
except UnavailableVideoError:
self.report_error('unable to download video')
except MaxDownloadsReached:
'autonumber_size': opts.autonumber_size,
'restrictfilenames': opts.restrictfilenames,
'ignoreerrors': opts.ignoreerrors,
+ 'force_generic_extractor': opts.force_generic_extractor,
'ratelimit': opts.ratelimit,
'nooverwrites': opts.nooverwrites,
'retries': opts_retries,
import socket
import subprocess
import sys
+import itertools
try:
pass
return _terminal_size(columns, lines)
+try:
+ itertools.count(start=0, step=1)
+ compat_itertools_count = itertools.count
+except TypeError: # Python 2.6
+ def compat_itertools_count(start=0, step=1):
+ n = start
+ while True:
+ yield n
+ n += step
__all__ = [
'compat_HTTPError',
'compat_html_entities',
'compat_http_client',
'compat_http_server',
+ 'compat_itertools_count',
'compat_kwargs',
'compat_ord',
'compat_parse_qs',
cmd += ['--', info_dict['url']]
return cmd
+
+class HttpieFD(ExternalFD):
+ def _make_cmd(self, tmpfilename, info_dict):
+ cmd = ['http', '--download', '--output', tmpfilename, info_dict['url']]
+ for key, val in info_dict['http_headers'].items():
+ cmd += ['%s:%s' % (key, val)]
+ return cmd
+
_BY_NAME = dict(
(klass.get_basename(), klass)
for name, klass in globals().items()
def get_external_downloader(external_downloader):
""" Given the name of the executable, see whether we support the given
downloader . """
- bn = os.path.basename(external_downloader)
+ # Drop .exe extension on Windows
+ bn = os.path.splitext(os.path.basename(external_downloader))[0]
return _BY_NAME[bn]
from .abc7news import Abc7NewsIE
from .academicearth import AcademicEarthCourseIE
from .addanime import AddAnimeIE
-from .adobetv import AdobeTVIE
+from .adobetv import (
+ AdobeTVIE,
+ AdobeTVVideoIE,
+)
from .adultswim import AdultSwimIE
from .aftenposten import AftenpostenIE
from .aftonbladet import AftonbladetIE
DailymotionIE,
DailymotionPlaylistIE,
DailymotionUserIE,
+ DailymotionCloudIE,
)
from .daum import DaumIE
from .dbtv import DBTVIE
from .dhm import DHMIE
from .dotsub import DotsubIE
from .douyutv import DouyuTVIE
+from .dramafever import (
+ DramaFeverIE,
+ DramaFeverSeriesIE,
+)
from .dreisat import DreiSatIE
from .drbonanza import DRBonanzaIE
from .drtuber import DrTuberIE
)
from .elpais import ElPaisIE
from .embedly import EmbedlyIE
-from .empflix import EMPFlixIE
from .engadget import EngadgetIE
from .eporner import EpornerIE
from .eroprofile import EroProfileIE
from .firstpost import FirstpostIE
from .firsttv import FirstTVIE
from .fivemin import FiveMinIE
+from .fivetv import FiveTVIE
from .fktv import (
FKTVIE,
FKTVPosteckeIE,
from .kontrtube import KontrTubeIE
from .krasview import KrasViewIE
from .ku6 import Ku6IE
+from .kuwo import (
+ KuwoIE,
+ KuwoAlbumIE,
+ KuwoChartIE,
+ KuwoSingerIE,
+ KuwoCategoryIE,
+ KuwoMvIE,
+)
from .la7 import LA7IE
from .laola1tv import Laola1TvIE
from .letv import (
from .muzu import MuzuTVIE
from .myspace import MySpaceIE, MySpaceAlbumIE
from .myspass import MySpassIE
+from .myvi import MyviIE
from .myvideo import MyVideoIE
from .myvidster import MyVidsterIE
from .nationalgeographic import NationalGeographicIE
from .netzkino import NetzkinoIE
from .nerdcubed import NerdCubedFeedIE
from .nerdist import NerdistIE
+from .neteasemusic import (
+ NetEaseMusicIE,
+ NetEaseMusicAlbumIE,
+ NetEaseMusicSingerIE,
+ NetEaseMusicListIE,
+ NetEaseMusicMvIE,
+ NetEaseMusicProgramIE,
+ NetEaseMusicDjRadioIE,
+)
from .newgrounds import NewgroundsIE
from .newstube import NewstubeIE
from .nextmedia import (
from .nuvid import NuvidIE
from .odnoklassniki import OdnoklassnikiIE
from .oktoberfesttv import OktoberfestTVIE
+from .onionstudios import OnionStudiosIE
from .ooyala import (
OoyalaIE,
OoyalaExternalIE,
from .philharmoniedeparis import PhilharmonieDeParisIE
from .phoenix import PhoenixIE
from .photobucket import PhotobucketIE
+from .pinkbike import PinkbikeIE
from .planetaplay import PlanetaPlayIE
from .pladform import PladformIE
from .played import PlayedIE
QQMusicSingerIE,
QQMusicAlbumIE,
QQMusicToplistIE,
+ QQMusicPlaylistIE,
)
from .quickvid import QuickVidIE
from .r7 import R7IE
SmotriUserIE,
SmotriBroadcastIE,
)
+from .snagfilms import (
+ SnagFilmsIE,
+ SnagFilmsEmbedIE,
+)
from .snotr import SnotrIE
from .sohu import SohuIE
from .soompi import (
from .theonion import TheOnionIE
from .theplatform import ThePlatformIE
from .thesixtyone import TheSixtyOneIE
+from .thisamericanlife import ThisAmericanLifeIE
from .thisav import ThisAVIE
from .tinypic import TinyPicIE
from .tlc import TlcIE, TlcDeIE
TMZIE,
TMZArticleIE,
)
-from .tnaflix import TNAFlixIE
+from .tnaflix import (
+ TNAFlixIE,
+ EMPFlixIE,
+ MovieFapIE,
+)
from .thvideo import (
THVideoIE,
THVideoPlaylistIE
TV2ArticleIE,
)
from .tv4 import TV4IE
+from .tvc import (
+ TVCIE,
+ TVCArticleIE,
+)
from .tvigle import TvigleIE
from .tvp import TvpIE, TvpSeriesIE
from .tvplay import TVPlayIE
TwitchBookmarksIE,
TwitchStreamIE,
)
+from .twitter import TwitterCardIE
from .ubu import UbuIE
from .udemy import (
UdemyIE,
WDRMobileIE,
WDRMausIE,
)
-from .webofstories import WebOfStoriesIE
+from .webofstories import (
+ WebOfStoriesIE,
+ WebOfStoriesPlaylistIE,
+)
from .weibo import WeiboIE
from .wimp import WimpIE
from .wistia import WistiaIE
from .wsj import WSJIE
from .xbef import XBefIE
from .xboxclips import XboxClipsIE
-from .xhamster import XHamsterIE
+from .xhamster import (
+ XHamsterIE,
+ XHamsterEmbedIE,
+)
from .xminus import XMinusIE
from .xnxx import XNXXIE
from .xstream import XstreamIE
YandexMusicPlaylistIE,
)
from .yesjapan import YesJapanIE
+from .yinyuetai import YinYueTaiIE
from .ynet import YnetIE
from .youjizz import YouJizzIE
from .youku import YoukuIE
parse_duration,
unified_strdate,
str_to_int,
+ float_or_none,
+ ISO639Utils,
)
'view_count': view_count,
'formats': formats,
}
+
+
+class AdobeTVVideoIE(InfoExtractor):
+ _VALID_URL = r'https?://video\.tv\.adobe\.com/v/(?P<id>\d+)'
+
+ _TEST = {
+ # From https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners
+ 'url': 'https://video.tv.adobe.com/v/2456/',
+ 'md5': '43662b577c018ad707a63766462b1e87',
+ 'info_dict': {
+ 'id': '2456',
+ 'ext': 'mp4',
+ 'title': 'New experience with Acrobat DC',
+ 'description': 'New experience with Acrobat DC',
+ 'duration': 248.667,
+ },
+ }
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, video_id)
+
+ player_params = self._parse_json(self._search_regex(
+ r'var\s+bridge\s*=\s*([^;]+);', webpage, 'player parameters'),
+ video_id)
+
+ formats = [{
+ 'url': source['src'],
+ 'width': source.get('width'),
+ 'height': source.get('height'),
+ 'tbr': source.get('bitrate'),
+ } for source in player_params['sources']]
+
+ # For both metadata and downloaded files the duration varies among
+ # formats. I just pick the max one
+ duration = max(filter(None, [
+ float_or_none(source.get('duration'), scale=1000)
+ for source in player_params['sources']]))
+
+ subtitles = {}
+ for translation in player_params.get('translations', []):
+ lang_id = translation.get('language_w3c') or ISO639Utils.long2short(translation['language_medium'])
+ if lang_id not in subtitles:
+ subtitles[lang_id] = []
+ subtitles[lang_id].append({
+ 'url': translation['vttPath'],
+ 'ext': 'vtt',
+ })
+
+ return {
+ 'id': video_id,
+ 'formats': formats,
+ 'title': player_params['title'],
+ 'description': self._og_search_description(webpage),
+ 'duration': duration,
+ 'subtitles': subtitles,
+ }
class BaiduVideoIE(InfoExtractor):
+ IE_DESC = '百度视频'
_VALID_URL = r'http://v\.baidu\.com/(?P<type>[a-z]+)/(?P<id>\d+)\.htm'
_TESTS = [{
'url': 'http://v.baidu.com/comic/1069.htm?frp=bdbrand&q=%E4%B8%AD%E5%8D%8E%E5%B0%8F%E5%BD%93%E5%AE%B6',
'skip_download': True,
},
'skip': 'geolocation',
+ }, {
+ 'url': 'http://www.bbc.co.uk/iplayer/episode/b05zmgwn/royal-academy-summer-exhibition',
+ 'info_dict': {
+ 'id': 'b05zmgw1',
+ 'ext': 'flv',
+ 'description': 'Kirsty Wark and Morgan Quaintance visit the Royal Academy as it prepares for its annual artistic extravaganza, meeting people who have come together to make the show unique.',
+ 'title': 'Royal Academy Summer Exhibition',
+ 'duration': 3540,
+ },
+ 'params': {
+ # rtmp download
+ 'skip_download': True,
+ },
+ 'skip': 'geolocation',
}, {
'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4',
'only_matching': True,
for connection in self._extract_connections(media):
captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions')
lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en')
- ps = captions.findall('./{0}body/{0}div/{0}p'.format('{http://www.w3.org/2006/10/ttaf1}'))
- srt = ''
-
- def _extract_text(p):
- if p.text is not None:
- stripped_text = p.text.strip()
- if stripped_text:
- return stripped_text
- return ' '.join(span.text.strip() for span in p.findall('{http://www.w3.org/2006/10/ttaf1}span'))
- for pos, p in enumerate(ps):
- srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (str(pos), p.get('begin'), p.get('end'), _extract_text(p))
subtitles[lang] = [
{
'url': connection.get('href'),
'ext': 'ttml',
},
- {
- 'data': srt,
- 'ext': 'srt',
- },
]
return subtitles
programme_id, 'Downloading media selection XML')
except ExtractorError as ee:
if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
- media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().encode('utf-8'))
+ media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().decode('utf-8'))
else:
raise
formats, subtitles = self._download_media_selector(programme_id)
title = self._og_search_title(webpage)
description = self._search_regex(
- r'<p class="medium-description">([^<]+)</p>',
+ r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>',
webpage, 'description', fatal=False)
else:
programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id)
'filesize': int_or_none(
lq_durl.find('./size'), get_attr='text'),
}]
- if hq_durl:
+ if hq_durl is not None:
formats.append({
'format_id': 'hq',
'quality': 2,
compat_urllib_parse_urlparse,
compat_urllib_request,
compat_urlparse,
+ compat_xml_parse_error,
)
from ..utils import (
determine_ext,
try:
object_doc = xml.etree.ElementTree.fromstring(object_str.encode('utf-8'))
- except xml.etree.ElementTree.ParseError:
+ except compat_xml_parse_error:
return
fv_el = find_xpath_attr(object_doc, './param', 'name', 'flashVars')
linkBase = find_param('linkBaseURL')
if linkBase is not None:
params['linkBaseURL'] = linkBase
+ return cls._make_brightcove_url(params)
+
+ @classmethod
+ def _build_brighcove_url_from_js(cls, object_js):
+ # The layout of JS is as follows:
+ # customBC.createVideo = function (width, height, playerID, playerKey, videoPlayer, VideoRandomID) {
+ # // build Brightcove <object /> XML
+ # }
+ m = re.search(
+ r'''(?x)customBC.\createVideo\(
+ .*? # skipping width and height
+ ["\'](?P<playerID>\d+)["\']\s*,\s* # playerID
+ ["\'](?P<playerKey>AQ[^"\']{48})[^"\']*["\']\s*,\s* # playerKey begins with AQ and is 50 characters
+ # in length, however it's appended to itself
+ # in places, so truncate
+ ["\'](?P<videoID>\d+)["\'] # @videoPlayer
+ ''', object_js)
+ if m:
+ return cls._make_brightcove_url(m.groupdict())
+
+ @classmethod
+ def _make_brightcove_url(cls, params):
data = compat_urllib_parse.urlencode(params)
return cls._FEDERATED_URL_TEMPLATE % data
[^>]*?>\s*<param\s+name="movie"\s+value="https?://[^/]*brightcove\.com/
).+?>\s*</object>''',
webpage)
- return list(filter(None, [cls._build_brighcove_url(m) for m in matches]))
+ if matches:
+ return list(filter(None, [cls._build_brighcove_url(m) for m in matches]))
+
+ return list(filter(None, [
+ cls._build_brighcove_url_from_js(custom_bc)
+ for custom_bc in re.findall(r'(customBC\.createVideo\(.+?\);)', webpage)]))
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
from ..utils import (
find_xpath_attr,
class ClipsyndicateIE(InfoExtractor):
- _VALID_URL = r'http://www\.clipsyndicate\.com/video/play(list/\d+)?/(?P<id>\d+)'
+ _VALID_URL = r'http://(?:chic|www)\.clipsyndicate\.com/video/play(list/\d+)?/(?P<id>\d+)'
- _TEST = {
+ _TESTS = [{
'url': 'http://www.clipsyndicate.com/video/play/4629301/brick_briscoe',
'md5': '4d7d549451bad625e0ff3d7bd56d776c',
'info_dict': {
'duration': 612,
'thumbnail': 're:^https?://.+\.jpg',
},
- }
+ }, {
+ 'url': 'http://chic.clipsyndicate.com/video/play/5844117/shark_attack',
+ 'only_matching': True,
+ }]
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
+ video_id = self._match_id(url)
js_player = self._download_webpage(
'http://eplayer.clipsyndicate.com/embed/player.js?va_id=%s' % video_id,
video_id, 'Downlaoding player')
compat_str,
)
from ..utils import (
+ NO_DEFAULT,
age_restricted,
bug_reports_message,
clean_html,
sanitize_filename,
unescapeHTML,
)
-_NO_DEFAULT = object()
class InfoExtractor(object):
video_info['description'] = playlist_description
return video_info
- def _search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None):
+ def _search_regex(self, pattern, string, name, default=NO_DEFAULT, fatal=True, flags=0, group=None):
"""
Perform a regex search on the given string, using a single or a list of
patterns returning the first matching group.
return next(g for g in mobj.groups() if g is not None)
else:
return mobj.group(group)
- elif default is not _NO_DEFAULT:
+ elif default is not NO_DEFAULT:
return default
elif fatal:
raise RegexNotFoundError('Unable to extract %s' % _name)
self._downloader.report_warning('unable to extract %s' % _name + bug_reports_message())
return None
- def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None):
+ def _html_search_regex(self, pattern, string, name, default=NO_DEFAULT, fatal=True, flags=0, group=None):
"""
Like _search_regex, but strips HTML tags and unescapes entities.
"""
return self._html_search_meta('twitter:player', html,
'twitter card player')
+ @staticmethod
+ def _form_hidden_inputs(html):
+ return dict(re.findall(
+ r'<input\s+type="hidden"\s+name="([^"]+)"\s+(?:id="[^"]+"\s+)?value="([^"]*)"',
+ html))
+
def _sort_formats(self, formats, field_preference=None):
if not formats:
raise ExtractorError('No video formats found')
def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None,
entry_protocol='m3u8', preference=None,
- m3u8_id=None, note=None, errnote=None):
+ m3u8_id=None, note=None, errnote=None,
+ fatal=True):
formats = [{
'format_id': '-'.join(filter(None, [m3u8_id, 'meta'])),
m3u8_doc = self._download_webpage(
m3u8_url, video_id,
note=note or 'Downloading m3u8 information',
- errnote=errnote or 'Failed to download m3u8 information')
+ errnote=errnote or 'Failed to download m3u8 information',
+ fatal=fatal)
+ if m3u8_doc is False:
+ return m3u8_doc
last_info = None
last_media = None
kv_rex = re.compile(
class CrunchyrollIE(InfoExtractor):
- _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)'
+ _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)'
_NETRC_MACHINE = 'crunchyroll'
_TESTS = [{
'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
# rtmp
'skip_download': True,
},
+ }, {
+ 'url': 'http://www.crunchyroll.com/media-589804/culture-japan-1',
+ 'info_dict': {
+ 'id': '589804',
+ 'ext': 'flv',
+ 'title': 'Culture Japan Episode 1 – Rebuilding Japan after the 3.11',
+ 'description': 'md5:fe2743efedb49d279552926d0bd0cd9e',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'uploader': 'Danny Choo Network',
+ 'upload_date': '20120213',
+ },
+ 'params': {
+ # rtmp
+ 'skip_download': True,
+ },
+
}, {
'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
'only_matching': True,
for fmt in re.findall(r'showmedia\.([0-9]{3,4})p', webpage):
stream_quality, stream_format = self._FORMAT_IDS[fmt]
video_format = fmt + 'p'
- streamdata_req = compat_urllib_request.Request('http://www.crunchyroll.com/xml/')
- # urlencode doesn't work!
- streamdata_req.data = 'req=RpcApiVideoEncode%5FGetStreamInfo&video%5Fencode%5Fquality=' + stream_quality + '&media%5Fid=' + stream_id + '&video%5Fformat=' + stream_format
+ streamdata_req = compat_urllib_request.Request(
+ 'http://www.crunchyroll.com/xml/?req=RpcApiVideoPlayer_GetStandardConfig&media_id=%s&video_format=%s&video_quality=%s'
+ % (stream_id, stream_format, stream_quality),
+ compat_urllib_parse.urlencode({'current_page': url}).encode('utf-8'))
streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
- streamdata_req.add_header('Content-Length', str(len(streamdata_req.data)))
streamdata = self._download_xml(
streamdata_req, video_id,
note='Downloading media info for %s' % video_format)
- video_url = streamdata.find('./host').text
- video_play_path = streamdata.find('./file').text
+ stream_info = streamdata.find('./{default}preload/stream_info')
+ video_url = stream_info.find('./host').text
+ video_play_path = stream_info.find('./file').text
formats.append({
'url': video_url,
'play_path': video_play_path,
class CtsNewsIE(InfoExtractor):
+ IE_DESC = '華視新聞'
# https connection failed (Connection reset)
_VALID_URL = r'http://news\.cts\.com\.tw/[a-z]+/[a-z]+/\d+/(?P<id>\d+)\.html'
_TESTS = [{
'title': full_user,
'entries': self._extract_entries(user),
}
+
+
+class DailymotionCloudIE(DailymotionBaseInfoExtractor):
+ _VALID_URL_PREFIX = r'http://api\.dmcloud\.net/(?:player/)?embed/'
+ _VALID_URL = r'%s[^/]+/(?P<id>[^/?]+)' % _VALID_URL_PREFIX
+ _VALID_EMBED_URL = r'%s[^/]+/[^\'"]+' % _VALID_URL_PREFIX
+
+ _TESTS = [{
+ # From http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html
+ # Tested at FranceTvInfo_2
+ 'url': 'http://api.dmcloud.net/embed/4e7343f894a6f677b10006b4/556e03339473995ee145930c?auth=1464865870-0-jyhsm84b-ead4c701fb750cf9367bf4447167a3db&autoplay=1',
+ 'only_matching': True,
+ }, {
+ # http://www.francetvinfo.fr/societe/larguez-les-amarres-le-cobaturage-se-developpe_980101.html
+ 'url': 'http://api.dmcloud.net/player/embed/4e7343f894a6f677b10006b4/559545469473996d31429f06?auth=1467430263-0-90tglw2l-a3a4b64ed41efe48d7fccad85b8b8fda&autoplay=1',
+ 'only_matching': True,
+ }]
+
+ @classmethod
+ def _extract_dmcloud_url(self, webpage):
+ mobj = re.search(r'<iframe[^>]+src=[\'"](%s)[\'"]' % self._VALID_EMBED_URL, webpage)
+ if mobj:
+ return mobj.group(1)
+
+ mobj = re.search(
+ r'<input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=[\'"](%s)[\'"]' % self._VALID_EMBED_URL,
+ webpage)
+ if mobj:
+ return mobj.group(1)
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ request = self._build_request(url)
+ webpage = self._download_webpage(request, video_id)
+
+ title = self._html_search_regex(r'<title>([^>]+)</title>', webpage, 'title')
+
+ video_info = self._parse_json(self._search_regex(
+ r'var\s+info\s*=\s*([^;]+);', webpage, 'video info'), video_id)
+
+ # TODO: parse ios_url, which is in fact a manifest
+ video_url = video_info['mp4_url']
+
+ return {
+ 'id': video_id,
+ 'url': video_url,
+ 'title': title,
+ 'thumbnail': video_info.get('thumbnail_url'),
+ }
class DouyuTVIE(InfoExtractor):
+ IE_DESC = '斗鱼'
_VALID_URL = r'http://(?:www\.)?douyutv\.com/(?P<id>[A-Za-z0-9]+)'
_TESTS = [{
'url': 'http://www.douyutv.com/iseven',
--- /dev/null
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import itertools
+
+from .common import InfoExtractor
+from ..compat import (
+ compat_HTTPError,
+ compat_urllib_parse,
+ compat_urllib_request,
+ compat_urlparse,
+)
+from ..utils import (
+ ExtractorError,
+ clean_html,
+ determine_ext,
+ int_or_none,
+ parse_iso8601,
+)
+
+
+class DramaFeverBaseIE(InfoExtractor):
+ _LOGIN_URL = 'https://www.dramafever.com/accounts/login/'
+ _NETRC_MACHINE = 'dramafever'
+
+ def _real_initialize(self):
+ self._login()
+
+ def _login(self):
+ (username, password) = self._get_login_info()
+ if username is None:
+ return
+
+ login_form = {
+ 'username': username,
+ 'password': password,
+ }
+
+ request = compat_urllib_request.Request(
+ self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
+ response = self._download_webpage(
+ request, None, 'Logging in as %s' % username)
+
+ if all(logout_pattern not in response
+ for logout_pattern in ['href="/accounts/logout/"', '>Log out<']):
+ error = self._html_search_regex(
+ r'(?s)class="hidden-xs prompt"[^>]*>(.+?)<',
+ response, 'error message', default=None)
+ if error:
+ raise ExtractorError('Unable to login: %s' % error, expected=True)
+ raise ExtractorError('Unable to log in')
+
+
+class DramaFeverIE(DramaFeverBaseIE):
+ IE_NAME = 'dramafever'
+ _VALID_URL = r'https?://(?:www\.)?dramafever\.com/drama/(?P<id>[0-9]+/[0-9]+)(?:/|$)'
+ _TEST = {
+ 'url': 'http://www.dramafever.com/drama/4512/1/Cooking_with_Shin/',
+ 'info_dict': {
+ 'id': '4512.1',
+ 'ext': 'flv',
+ 'title': 'Cooking with Shin 4512.1',
+ 'description': 'md5:a8eec7942e1664a6896fcd5e1287bfd0',
+ 'thumbnail': 're:^https?://.*\.jpg',
+ 'timestamp': 1404336058,
+ 'upload_date': '20140702',
+ 'duration': 343,
+ }
+ }
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url).replace('/', '.')
+
+ try:
+ feed = self._download_json(
+ 'http://www.dramafever.com/amp/episode/feed.json?guid=%s' % video_id,
+ video_id, 'Downloading episode JSON')['channel']['item']
+ except ExtractorError as e:
+ if isinstance(e.cause, compat_HTTPError):
+ raise ExtractorError(
+ 'Currently unavailable in your country.', expected=True)
+ raise
+
+ media_group = feed.get('media-group', {})
+
+ formats = []
+ for media_content in media_group['media-content']:
+ src = media_content.get('@attributes', {}).get('url')
+ if not src:
+ continue
+ ext = determine_ext(src)
+ if ext == 'f4m':
+ formats.extend(self._extract_f4m_formats(
+ src, video_id, f4m_id='hds'))
+ elif ext == 'm3u8':
+ formats.extend(self._extract_m3u8_formats(
+ src, video_id, 'mp4', m3u8_id='hls'))
+ else:
+ formats.append({
+ 'url': src,
+ })
+ self._sort_formats(formats)
+
+ title = media_group.get('media-title')
+ description = media_group.get('media-description')
+ duration = int_or_none(media_group['media-content'][0].get('@attributes', {}).get('duration'))
+ thumbnail = self._proto_relative_url(
+ media_group.get('media-thumbnail', {}).get('@attributes', {}).get('url'))
+ timestamp = parse_iso8601(feed.get('pubDate'), ' ')
+
+ subtitles = {}
+ for media_subtitle in media_group.get('media-subTitle', []):
+ lang = media_subtitle.get('@attributes', {}).get('lang')
+ href = media_subtitle.get('@attributes', {}).get('href')
+ if not lang or not href:
+ continue
+ subtitles[lang] = [{
+ 'ext': 'ttml',
+ 'url': href,
+ }]
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'timestamp': timestamp,
+ 'duration': duration,
+ 'formats': formats,
+ 'subtitles': subtitles,
+ }
+
+
+class DramaFeverSeriesIE(DramaFeverBaseIE):
+ IE_NAME = 'dramafever:series'
+ _VALID_URL = r'https?://(?:www\.)?dramafever\.com/drama/(?P<id>[0-9]+)(?:/(?:(?!\d+(?:/|$)).+)?)?$'
+ _TESTS = [{
+ 'url': 'http://www.dramafever.com/drama/4512/Cooking_with_Shin/',
+ 'info_dict': {
+ 'id': '4512',
+ 'title': 'Cooking with Shin',
+ 'description': 'md5:84a3f26e3cdc3fb7f500211b3593b5c1',
+ },
+ 'playlist_count': 4,
+ }, {
+ 'url': 'http://www.dramafever.com/drama/124/IRIS/',
+ 'info_dict': {
+ 'id': '124',
+ 'title': 'IRIS',
+ 'description': 'md5:b3a30e587cf20c59bd1c01ec0ee1b862',
+ },
+ 'playlist_count': 20,
+ }]
+
+ _CONSUMER_SECRET = 'DA59dtVXYLxajktV'
+ _PAGE_SIZE = 60 # max is 60 (see http://api.drama9.com/#get--api-4-episode-series-)
+
+ def _get_consumer_secret(self, video_id):
+ mainjs = self._download_webpage(
+ 'http://www.dramafever.com/static/51afe95/df2014/scripts/main.js',
+ video_id, 'Downloading main.js', fatal=False)
+ if not mainjs:
+ return self._CONSUMER_SECRET
+ return self._search_regex(
+ r"var\s+cs\s*=\s*'([^']+)'", mainjs,
+ 'consumer secret', default=self._CONSUMER_SECRET)
+
+ def _real_extract(self, url):
+ series_id = self._match_id(url)
+
+ consumer_secret = self._get_consumer_secret(series_id)
+
+ series = self._download_json(
+ 'http://www.dramafever.com/api/4/series/query/?cs=%s&series_id=%s'
+ % (consumer_secret, series_id),
+ series_id, 'Downloading series JSON')['series'][series_id]
+
+ title = clean_html(series['name'])
+ description = clean_html(series.get('description') or series.get('description_short'))
+
+ entries = []
+ for page_num in itertools.count(1):
+ episodes = self._download_json(
+ 'http://www.dramafever.com/api/4/episode/series/?cs=%s&series_id=%s&page_size=%d&page_number=%d'
+ % (consumer_secret, series_id, self._PAGE_SIZE, page_num),
+ series_id, 'Downloading episodes JSON page #%d' % page_num)
+ for episode in episodes.get('value', []):
+ episode_url = episode.get('episode_url')
+ if not episode_url:
+ continue
+ entries.append(self.url_result(
+ compat_urlparse.urljoin(url, episode_url),
+ 'DramaFever', episode.get('guid')))
+ if page_num == episodes['num_pages']:
+ break
+
+ return self.playlist_result(entries, series_id, title, description)
_TESTS = [{
'url': 'http://www.dr.dk/bonanza/serie/portraetter/Talkshowet.htm?assetId=65517',
- 'md5': 'fe330252ddea607635cf2eb2c99a0af3',
'info_dict': {
'id': '65517',
'ext': 'mp4',
'upload_date': '20110120',
'duration': 3664,
},
+ 'params': {
+ 'skip_download': True, # requires rtmp
+ },
}, {
'url': 'http://www.dr.dk/bonanza/radio/serie/sport/fodbold.htm?assetId=59410',
'md5': '6dfe039417e76795fb783c52da3de11d',
'format_id': file['Type'].replace('Video', ''),
'preference': preferencemap.get(file['Type'], -10),
})
+ if format['url'].startswith('rtmp'):
+ rtmp_url = format['url']
+ format['rtmp_live'] = True # --resume does not work
+ if '/bonanza/' in rtmp_url:
+ format['play_path'] = rtmp_url.split('/bonanza/')[1]
formats.append(format)
elif file['Type'] == "Thumb":
thumbnail = file['Location']
description = '%s\n%s\n%s\n' % (
info['Description'], info['Actors'], info['Colophon'])
- for f in formats:
- f['url'] = f['url'].replace('rtmp://vod-bonanza.gss.dr.dk/bonanza/', 'http://vodfiles.dr.dk/')
- f['url'] = f['url'].replace('mp4:bonanza', 'bonanza')
self._sort_formats(formats)
display_id = re.sub(r'[^\w\d-]', '', re.sub(r' ', '-', title.lower())) + '-' + asset_id
r'<source src="([^"]+)"', webpage, 'video URL')
title = self._html_search_regex(
- [r'class="hd_title" style="[^"]+">([^<]+)</h1>', r'<title>([^<]+) - \d+'],
+ [r'<p[^>]+class="title_substrate">([^<]+)</p>', r'<title>([^<]+) - \d+'],
webpage, 'title')
thumbnail = self._html_search_regex(
r'poster="([^"]+)"',
webpage, 'thumbnail', fatal=False)
- like_count = str_to_int(self._html_search_regex(
- r'<span id="rate_likes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>',
- webpage, 'like count', fatal=False))
- dislike_count = str_to_int(self._html_search_regex(
- r'<span id="rate_dislikes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>',
- webpage, 'like count', fatal=False))
- comment_count = str_to_int(self._html_search_regex(
- r'<span class="comments_count">([\d,\.]+)</span>',
- webpage, 'comment count', fatal=False))
+ def extract_count(id_, name):
+ return str_to_int(self._html_search_regex(
+ r'<span[^>]+(?:class|id)="%s"[^>]*>([\d,\.]+)</span>' % id_,
+ webpage, '%s count' % name, fatal=False))
+
+ like_count = extract_count('rate_likes', 'like')
+ dislike_count = extract_count('rate_dislikes', 'dislike')
+ comment_count = extract_count('comments_count', 'comment')
cats_str = self._search_regex(
- r'<span>Categories:</span><div>(.+?)</div>', webpage, 'categories', fatal=False)
+ r'<div[^>]+class="categories_list">(.+?)</div>', webpage, 'categories', fatal=False)
categories = [] if not cats_str else re.findall(r'<a title="([^"]+)"', cats_str)
return {
+++ /dev/null
-from __future__ import unicode_literals
-
-from .tnaflix import TNAFlixIE
-
-
-class EMPFlixIE(TNAFlixIE):
- _VALID_URL = r'https?://(?:www\.)?empflix\.com/videos/(?P<display_id>.+?)-(?P<id>[0-9]+)\.html'
-
- _TITLE_REGEX = r'name="title" value="(?P<title>[^"]*)"'
- _DESCRIPTION_REGEX = r'name="description" value="([^"]*)"'
- _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"'
-
- _TESTS = [
- {
- 'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
- 'md5': 'b1bc15b6412d33902d6e5952035fcabc',
- 'info_dict': {
- 'id': '33051',
- 'display_id': 'Amateur-Finger-Fuck',
- 'ext': 'mp4',
- 'title': 'Amateur Finger Fuck',
- 'description': 'Amateur solo finger fucking.',
- 'thumbnail': 're:https?://.*\.jpg$',
- 'age_limit': 18,
- }
- },
- {
- 'url': 'http://www.empflix.com/videos/[AROMA][ARMD-718]-Aoi-Yoshino-Sawa-25826.html',
- 'only_matching': True,
- }
- ]
class FazIE(InfoExtractor):
IE_NAME = 'faz.net'
- _VALID_URL = r'https?://www\.faz\.net/multimedia/videos/.*?-(?P<id>\d+)\.html'
+ _VALID_URL = r'https?://(?:www\.)?faz\.net/(?:[^/]+/)*.*?-(?P<id>\d+)\.html'
- _TEST = {
+ _TESTS = [{
'url': 'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html',
'info_dict': {
'id': '12610585',
'title': 'Stockholm: Chemie-Nobelpreis für drei amerikanische Forscher',
'description': 'md5:1453fbf9a0d041d985a47306192ea253',
},
- }
+ }, {
+ 'url': 'http://www.faz.net/aktuell/politik/berlin-gabriel-besteht-zerreissprobe-ueber-datenspeicherung-13659345.html',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://www.faz.net/berlin-gabriel-besteht-zerreissprobe-ueber-datenspeicherung-13659345.html',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://www.faz.net/-13659345.html',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://www.faz.net/aktuell/politik/-13659345.html',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://www.faz.net/foobarblafasel-13659345.html',
+ 'only_matching': True,
+ }]
def _real_extract(self, url):
video_id = self._match_id(url)
--- /dev/null
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class FiveTVIE(InfoExtractor):
+ _VALID_URL = r'''(?x)
+ http://
+ (?:www\.)?5-tv\.ru/
+ (?:
+ (?:[^/]+/)+(?P<id>\d+)|
+ (?P<path>[^/?#]+)(?:[/?#])?
+ )
+ '''
+
+ _TESTS = [{
+ 'url': 'http://5-tv.ru/news/96814/',
+ 'md5': 'bbff554ad415ecf5416a2f48c22d9283',
+ 'info_dict': {
+ 'id': '96814',
+ 'ext': 'mp4',
+ 'title': 'Россияне выбрали имя для общенациональной платежной системы',
+ 'description': 'md5:a8aa13e2b7ad36789e9f77a74b6de660',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 180,
+ },
+ }, {
+ 'url': 'http://5-tv.ru/video/1021729/',
+ 'info_dict': {
+ 'id': '1021729',
+ 'ext': 'mp4',
+ 'title': '3D принтер',
+ 'description': 'md5:d76c736d29ef7ec5c0cf7d7c65ffcb41',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 180,
+ },
+ }, {
+ 'url': 'http://www.5-tv.ru/glavnoe/#itemDetails',
+ 'info_dict': {
+ 'id': 'glavnoe',
+ 'ext': 'mp4',
+ 'title': 'Итоги недели с 8 по 14 июня 2015 года',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ },
+ }, {
+ 'url': 'http://www.5-tv.ru/glavnoe/broadcasts/508645/',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://5-tv.ru/films/1507502/',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://5-tv.ru/programs/broadcast/508713/',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://5-tv.ru/angel/',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://www.5-tv.ru/schedule/?iframe=true&width=900&height=450',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id') or mobj.group('path')
+
+ webpage = self._download_webpage(url, video_id)
+
+ video_url = self._search_regex(
+ r'<a[^>]+?href="([^"]+)"[^>]+?class="videoplayer"',
+ webpage, 'video url')
+
+ title = self._og_search_title(webpage, default=None) or self._search_regex(
+ r'<title>([^<]+)</title>', webpage, 'title')
+ duration = int_or_none(self._og_search_property(
+ 'video:duration', webpage, 'duration', default=None))
+
+ return {
+ 'id': video_id,
+ 'url': video_url,
+ 'title': title,
+ 'description': self._og_search_description(webpage, default=None),
+ 'thumbnail': self._og_search_thumbnail(webpage, default=None),
+ 'duration': duration,
+ }
parse_duration,
determine_ext,
)
+from .dailymotion import DailymotionCloudIE
class FranceTVBaseInfoExtractor(InfoExtractor):
continue
video_url_parsed = compat_urllib_parse_urlparse(video_url)
f4m_url = self._download_webpage(
- 'http://hdfauth.francetv.fr/esi/urltokengen2.html?url=%s' % video_url_parsed.path,
+ 'http://hdfauth.francetv.fr/esi/TA?url=%s' % video_url_parsed.path,
video_id, 'Downloading f4m manifest token', fatal=False)
if f4m_url:
formats.extend(self._extract_f4m_formats(f4m_url, video_id, 1, format_id))
'skip_download': 'HLS (reqires ffmpeg)'
},
'skip': 'Ce direct est terminé et sera disponible en rattrapage dans quelques minutes.',
+ }, {
+ 'url': 'http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html',
+ 'md5': 'f485bda6e185e7d15dbc69b72bae993e',
+ 'info_dict': {
+ 'id': '556e03339473995ee145930c',
+ 'ext': 'mp4',
+ 'title': 'Les entreprises familiales : le secret de la réussite',
+ 'thumbnail': 're:^https?://.*\.jpe?g$',
+ }
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
page_title = mobj.group('title')
webpage = self._download_webpage(url, page_title)
+
+ dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
+ if dmcloud_url:
+ return self.url_result(dmcloud_url, 'DailymotionCloud')
+
video_id, catalogue = self._search_regex(
r'id-video=([^@]+@[^"]+)', webpage, 'video id').split('@')
return self._extract_video(video_id, catalogue)
from .nbc import NBCSportsVPlayerIE
from .ooyala import OoyalaIE
from .rutv import RUTVIE
+from .tvc import TVCIE
from .sportbox import SportBoxEmbedIE
from .smotri import SmotriIE
+from .myvi import MyviIE
from .condenast import CondeNastIE
from .udn import UDNEmbedIE
from .senateisvp import SenateISVPIE
from .bliptv import BlipTVIE
from .svt import SVTIE
+from .pornhub import PornHubIE
+from .xhamster import XHamsterEmbedIE
+from .vimeo import VimeoIE
+from .dailymotion import DailymotionCloudIE
+from .onionstudios import OnionStudiosIE
+from .snagfilms import SnagFilmsEmbedIE
class GenericIE(InfoExtractor):
'skip_download': True,
},
},
+ # TVC embed
+ {
+ 'url': 'http://sch1298sz.mskobr.ru/dou_edu/karamel_ki/filial_galleries/video/iframe_src_http_tvc_ru_video_iframe_id_55304_isplay_false_acc_video_id_channel_brand_id_11_show_episodes_episode_id_32307_frameb/',
+ 'info_dict': {
+ 'id': '55304',
+ 'ext': 'mp4',
+ 'title': 'Дошкольное воспитание',
+ },
+ },
# SportBox embed
{
'url': 'http://www.vestifinance.ru/articles/25753',
'skip_download': True,
},
},
+ # Myvi.ru embed
+ {
+ 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
+ 'info_dict': {
+ 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
+ 'ext': 'mp4',
+ 'title': 'Ужастики, русский трейлер (2015)',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 153,
+ }
+ },
+ # XHamster embed
+ {
+ 'url': 'http://www.numisc.com/forum/showthread.php?11696-FM15-which-pumiscer-was-this-%28-vid-%29-%28-alfa-as-fuck-srx-%29&s=711f5db534502e22260dec8c5e2d66d8',
+ 'info_dict': {
+ 'id': 'showthread',
+ 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
+ },
+ 'playlist_mincount': 7,
+ },
# Embedded TED video
{
'url': 'http://en.support.wordpress.com/videos/ted-talks/',
'title': 'John Carlson Postgame 2/25/15',
},
},
+ # Kaltura embed (different embed code)
+ {
+ 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
+ 'info_dict': {
+ 'id': '1_a52wc67y',
+ 'ext': 'flv',
+ 'upload_date': '20150127',
+ 'uploader_id': 'PremierMedia',
+ 'timestamp': int,
+ 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
+ },
+ },
# Eagle.Platform embed (generic URL)
{
'url': 'http://lenta.ru/news/2015/03/06/navalny/',
'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
'uploader': 'Rogers Sportsnet',
},
+ },
+ # Dailymotion Cloud video
+ {
+ 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
+ 'md5': '49444254273501a64675a7e68c502681',
+ 'info_dict': {
+ 'id': '5585de919473990de4bee11b',
+ 'ext': 'mp4',
+ 'title': 'Le débat',
+ 'thumbnail': 're:^https?://.*\.jpe?g$',
+ }
+ },
+ # OnionStudios embed
+ {
+ 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
+ 'info_dict': {
+ 'id': '2855',
+ 'ext': 'mp4',
+ 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
+ 'thumbnail': 're:^https?://.*\.jpe?g$',
+ 'uploader': 'ClickHole',
+ 'uploader_id': 'clickhole',
+ }
+ },
+ # SnagFilms embed
+ {
+ 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
+ 'info_dict': {
+ 'id': '74849a00-85a9-11e1-9660-123139220831',
+ 'ext': 'mp4',
+ 'title': '#whilewewatch',
+ }
+ },
+ # AdobeTVVideo embed
+ {
+ 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
+ 'md5': '43662b577c018ad707a63766462b1e87',
+ 'info_dict': {
+ 'id': '2456',
+ 'ext': 'mp4',
+ 'title': 'New experience with Acrobat DC',
+ 'description': 'New experience with Acrobat DC',
+ 'duration': 248.667,
+ },
}
]
}
if not self._downloader.params.get('test', False) and not is_intentional:
- self._downloader.report_warning('Falling back on generic information extractor.')
+ force = self._downloader.params.get('force_generic_extractor', False)
+ self._downloader.report_warning(
+ '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
if not full_response:
request = compat_urllib_request.Request(url)
# Look for embedded rtl.nl player
matches = re.findall(
- r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+video_embed[^"]+)"',
+ r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
webpage)
if matches:
return _playlist_from_matches(matches, ie='RtlNl')
- # Look for embedded (iframe) Vimeo player
- mobj = re.search(
- r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
- if mobj:
- player_url = unescapeHTML(mobj.group('url'))
- surl = smuggle_url(player_url, {'Referer': url})
- return self.url_result(surl)
- # Look for embedded (swf embed) Vimeo player
- mobj = re.search(
- r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
- if mobj:
- return self.url_result(mobj.group(1))
+ vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
+ if vimeo_url is not None:
+ return self.url_result(vimeo_url)
# Look for embedded YouTube player
matches = re.findall(r'''(?x)
if rutv_url:
return self.url_result(rutv_url, 'RUTV')
+ # Look for embedded TVC player
+ tvc_url = TVCIE._extract_url(webpage)
+ if tvc_url:
+ return self.url_result(tvc_url, 'TVC')
+
# Look for embedded SportBox player
sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
if sportbox_urls:
return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
+ # Look for embedded PornHub player
+ pornhub_url = PornHubIE._extract_url(webpage)
+ if pornhub_url:
+ return self.url_result(pornhub_url, 'PornHub')
+
+ # Look for embedded XHamster player
+ xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
+ if xhamster_urls:
+ return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
+
+ # Look for embedded Tvigle player
+ mobj = re.search(
+ r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'), 'Tvigle')
+
# Look for embedded TED player
mobj = re.search(
r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
if smotri_url:
return self.url_result(smotri_url, 'Smotri')
+ # Look for embedded Myvi.ru player
+ myvi_url = MyviIE._extract_url(webpage)
+ if myvi_url:
+ return self.url_result(myvi_url)
+
# Look for embeded soundcloud player
mobj = re.search(
r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
return self.url_result(mobj.group('url'), 'Zapiks')
# Look for Kaltura embeds
- mobj = re.search(
- r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage)
+ mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage) or
+ re.search(r'(?s)(["\'])(?:https?:)?//cdnapisec\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?\1.*?entry_id\s*:\s*(["\'])(?P<id>[^\2]+?)\2', webpage))
if mobj is not None:
return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
if senate_isvp_url:
return self.url_result(senate_isvp_url, 'SenateISVP')
+ # Look for Dailymotion Cloud videos
+ dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
+ if dmcloud_url:
+ return self.url_result(dmcloud_url, 'DailymotionCloud')
+
+ # Look for OnionStudios embeds
+ onionstudios_url = OnionStudiosIE._extract_url(webpage)
+ if onionstudios_url:
+ return self.url_result(onionstudios_url)
+
+ # Look for SnagFilms embeds
+ snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
+ if snagfilms_url:
+ return self.url_result(snagfilms_url)
+
+ # Look for AdobeTVVideo embeds
+ mobj = re.search(
+ r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
+ webpage)
+ if mobj is not None:
+ return self.url_result(
+ self._proto_relative_url(unescapeHTML(mobj.group(1))),
+ 'AdobeTVVideo')
+
def check_video(vurl):
if YoutubeIE.suitable(vurl):
return True
int_or_none,
float_or_none,
qualities,
+ ExtractorError,
)
class GfycatIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?gfycat\.com/(?P<id>[^/?#]+)'
- _TEST = {
+ _VALID_URL = r'https?://(?:www\.)?gfycat\.com/(?:ifr/)?(?P<id>[^/?#]+)'
+ _TESTS = [{
'url': 'http://gfycat.com/DeadlyDecisiveGermanpinscher',
'info_dict': {
'id': 'DeadlyDecisiveGermanpinscher',
'categories': list,
'age_limit': 0,
}
- }
+ }, {
+ 'url': 'http://gfycat.com/ifr/JauntyTimelyAmazontreeboa',
+ 'info_dict': {
+ 'id': 'JauntyTimelyAmazontreeboa',
+ 'ext': 'mp4',
+ 'title': 'JauntyTimelyAmazontreeboa',
+ 'timestamp': 1411720126,
+ 'upload_date': '20140926',
+ 'uploader': 'anonymous',
+ 'duration': 3.52,
+ 'view_count': int,
+ 'like_count': int,
+ 'dislike_count': int,
+ 'categories': list,
+ 'age_limit': 0,
+ }
+ }]
def _real_extract(self, url):
video_id = self._match_id(url)
gfy = self._download_json(
'http://gfycat.com/cajax/get/%s' % video_id,
- video_id, 'Downloading video info')['gfyItem']
+ video_id, 'Downloading video info')
+ if 'error' in gfy:
+ raise ExtractorError('Gfycat said: ' + gfy['error'], expected=True)
+ gfy = gfy['gfyItem']
title = gfy.get('title') or gfy['gfyName']
description = gfy.get('description')
if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None:
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
- fields = dict(re.findall(r'''(?x)<input\s+
- type="hidden"\s+
- name="([^"]+)"\s+
- (?:id="[^"]+"\s+)?
- value="([^"]*)"
- ''', webpage))
+ fields = self._form_hidden_inputs(webpage)
if fields['op'] == 'download1':
countdown = int_or_none(self._search_regex(
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(
- r'<h2 class="posttitle"><a[^>]*>([^<]+)</a>',
+ r'<h2[^>]+class="posttitle"[^>]*><a[^>]*>([^<]+)</a>',
webpage, 'title')
wrap_url = self._html_search_regex(
- r'<iframe src="([^"]+mp4)"', webpage, 'wrapper url')
+ r'<iframe[^>]+src="([^"]+mp4)"', webpage, 'wrapper url')
wrap_webpage = self._download_webpage(wrap_url, video_id)
video_url = self._html_search_regex(
- r'clip:\s*{\s*url: "([^"]*)"', wrap_webpage, 'video url')
+ r'file\s*:\s*"([^"]+)"', wrap_webpage, 'video url')
return {
'id': video_id,
r'<img src="([^"]+)".+?class="pic"',
webpage, 'thumbnail', fatal=False)
- fields = dict(re.findall(r'''(?x)<input\s+
- type="hidden"\s+
- name="([^"]+)"\s+
- value="([^"]*)"
- ''', webpage))
+ fields = self._form_hidden_inputs(webpage)
request = compat_urllib_request.Request(url, urlencode_postdata(fields))
request.add_header('Content-type', 'application/x-www-form-urlencoded')
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
+from ..utils import parse_iso8601
class HowcastIE(InfoExtractor):
'info_dict': {
'id': '390161',
'ext': 'mp4',
- 'description': 'The square knot, also known as the reef knot, is one of the oldest, most basic knots to tie, and can be used in many different ways. Here\'s the proper way to tie a square knot.',
'title': 'How to Tie a Square Knot Properly',
- }
+ 'description': 'md5:dbe792e5f6f1489027027bf2eba188a3',
+ 'timestamp': 1276081287,
+ 'upload_date': '20100609',
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
+ video_id = self._match_id(url)
- video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
- self.report_extraction(video_id)
-
- video_url = self._search_regex(r'\'?file\'?: "(http://mobile-media\.howcast\.com/[0-9]+\.mp4)',
- webpage, 'video URL')
-
- video_description = self._html_search_regex(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') name=\'description\'',
- webpage, 'description', fatal=False)
+ embed_code = self._search_regex(
+ r'<iframe[^>]+src="[^"]+\bembed_code=([^\b]+)\b',
+ webpage, 'ooyala embed code')
return {
+ '_type': 'url_transparent',
+ 'ie_key': 'Ooyala',
+ 'url': 'ooyala:%s' % embed_code,
'id': video_id,
- 'url': video_url,
- 'title': self._og_search_title(webpage),
- 'description': video_description,
- 'thumbnail': self._og_search_thumbnail(webpage),
+ 'timestamp': parse_iso8601(self._html_search_meta(
+ 'article:published_time', webpage, 'timestamp')),
}
format_info = info['videoPlayerObject']['video']
formats.append({
'format_id': f_id,
- 'url': format_info['url'],
+ 'url': format_info['videoInfoList'][0]['videoUrl'],
})
return {
class InaIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?ina\.fr/video/(?P<id>I?[A-Z0-9]+)'
+ _VALID_URL = r'https?://(?:www\.)?ina\.fr/video/(?P<id>I?[A-Z0-9]+)'
_TEST = {
'url': 'http://www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html',
'md5': 'a667021bf2b41f8dc6049479d9bb38a3',
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
+ compat_urlparse,
)
class InfoQIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?infoq\.com/[^/]+/(?P<id>[^/]+)$'
+ _VALID_URL = r'https?://(?:www\.)?infoq\.com/(?:[^/]+/)+(?P<id>[^/]+)'
- _TEST = {
+ _TESTS = [{
'url': 'http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things',
'md5': 'b5ca0e0a8c1fed93b0e65e48e462f9a2',
'info_dict': {
'description': 'Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.',
'title': 'A Few of My Favorite [Python] Things',
},
- }
+ }, {
+ 'url': 'http://www.infoq.com/fr/presentations/changez-avis-sur-javascript',
+ 'only_matching': True,
+ }]
def _real_extract(self, url):
video_id = self._match_id(url)
video_id, extension = video_filename.split('.')
http_base = self._search_regex(
- r'EXPRESSINSTALL_SWF\s*=\s*"(https?://[^/"]+/)', webpage,
+ r'EXPRESSINSTALL_SWF\s*=\s*[^"]*"((?:https?:)?//[^/"]+/)', webpage,
'HTTP base URL')
formats = [{
'play_path': playpath,
}, {
'format_id': 'http',
- 'url': http_base + real_id,
+ 'url': compat_urlparse.urljoin(url, http_base) + real_id,
}]
self._sort_formats(formats)
class IqiyiIE(InfoExtractor):
IE_NAME = 'iqiyi'
+ IE_DESC = '爱奇艺'
_VALID_URL = r'http://(?:www\.)iqiyi.com/v_.+?\.html'
--- /dev/null
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+import itertools
+
+from .common import InfoExtractor
+from ..utils import (
+ get_element_by_id,
+ clean_html,
+ ExtractorError,
+ remove_start,
+)
+
+
+class KuwoBaseIE(InfoExtractor):
+ _FORMATS = [
+ {'format': 'ape', 'ext': 'ape', 'preference': 100},
+ {'format': 'mp3-320', 'ext': 'mp3', 'br': '320kmp3', 'abr': 320, 'preference': 80},
+ {'format': 'mp3-192', 'ext': 'mp3', 'br': '192kmp3', 'abr': 192, 'preference': 70},
+ {'format': 'mp3-128', 'ext': 'mp3', 'br': '128kmp3', 'abr': 128, 'preference': 60},
+ {'format': 'wma', 'ext': 'wma', 'preference': 20},
+ {'format': 'aac', 'ext': 'aac', 'abr': 48, 'preference': 10}
+ ]
+
+ def _get_formats(self, song_id):
+ formats = []
+ for file_format in self._FORMATS:
+ song_url = self._download_webpage(
+ 'http://antiserver.kuwo.cn/anti.s?format=%s&br=%s&rid=MUSIC_%s&type=convert_url&response=url' %
+ (file_format['ext'], file_format.get('br', ''), song_id),
+ song_id, note='Download %s url info' % file_format['format'],
+ )
+ if song_url.startswith('http://') or song_url.startswith('https://'):
+ formats.append({
+ 'url': song_url,
+ 'format_id': file_format['format'],
+ 'format': file_format['format'],
+ 'preference': file_format['preference'],
+ 'abr': file_format.get('abr'),
+ })
+ self._sort_formats(formats)
+ return formats
+
+
+class KuwoIE(KuwoBaseIE):
+ IE_NAME = 'kuwo:song'
+ IE_DESC = '酷我音乐'
+ _VALID_URL = r'http://www\.kuwo\.cn/yinyue/(?P<id>\d+?)/'
+ _TESTS = [{
+ 'url': 'http://www.kuwo.cn/yinyue/635632/',
+ 'info_dict': {
+ 'id': '635632',
+ 'ext': 'ape',
+ 'title': '爱我别走',
+ 'creator': '张震岳',
+ 'upload_date': '20080122',
+ 'description': 'md5:ed13f58e3c3bf3f7fd9fbc4e5a7aa75c'
+ },
+ }, {
+ 'url': 'http://www.kuwo.cn/yinyue/6446136/',
+ 'info_dict': {
+ 'id': '6446136',
+ 'ext': 'mp3',
+ 'title': '心',
+ 'creator': 'IU',
+ 'upload_date': '20150518',
+ },
+ 'params': {
+ 'format': 'mp3-320'
+ },
+ }]
+
+ def _real_extract(self, url):
+ song_id = self._match_id(url)
+ webpage = self._download_webpage(
+ url, song_id, note='Download song detail info',
+ errnote='Unable to get song detail info')
+
+ song_name = self._html_search_regex(
+ r'<h1[^>]+title="([^"]+)">', webpage, 'song name')
+ singer_name = self._html_search_regex(
+ r'<div[^>]+class="s_img">\s*<a[^>]+title="([^>]+)"',
+ webpage, 'singer name', fatal=False)
+ lrc_content = clean_html(get_element_by_id('lrcContent', webpage))
+ if lrc_content == '暂无': # indicates no lyrics
+ lrc_content = None
+
+ formats = self._get_formats(song_id)
+
+ album_id = self._html_search_regex(
+ r'<p[^>]+class="album"[^<]+<a[^>]+href="http://www\.kuwo\.cn/album/(\d+)/"',
+ webpage, 'album id', fatal=False)
+
+ publish_time = None
+ if album_id is not None:
+ album_info_page = self._download_webpage(
+ 'http://www.kuwo.cn/album/%s/' % album_id, song_id,
+ note='Download album detail info',
+ errnote='Unable to get album detail info')
+
+ publish_time = self._html_search_regex(
+ r'发行时间:(\d{4}-\d{2}-\d{2})', album_info_page,
+ 'publish time', fatal=False)
+ if publish_time:
+ publish_time = publish_time.replace('-', '')
+
+ return {
+ 'id': song_id,
+ 'title': song_name,
+ 'creator': singer_name,
+ 'upload_date': publish_time,
+ 'description': lrc_content,
+ 'formats': formats,
+ }
+
+
+class KuwoAlbumIE(InfoExtractor):
+ IE_NAME = 'kuwo:album'
+ IE_DESC = '酷我音乐 - 专辑'
+ _VALID_URL = r'http://www\.kuwo\.cn/album/(?P<id>\d+?)/'
+ _TEST = {
+ 'url': 'http://www.kuwo.cn/album/502294/',
+ 'info_dict': {
+ 'id': '502294',
+ 'title': 'M',
+ 'description': 'md5:6a7235a84cc6400ec3b38a7bdaf1d60c',
+ },
+ 'playlist_count': 2,
+ }
+
+ def _real_extract(self, url):
+ album_id = self._match_id(url)
+
+ webpage = self._download_webpage(
+ url, album_id, note='Download album info',
+ errnote='Unable to get album info')
+
+ album_name = self._html_search_regex(
+ r'<div[^>]+class="comm"[^<]+<h1[^>]+title="([^"]+)"', webpage,
+ 'album name')
+ album_intro = remove_start(
+ clean_html(get_element_by_id('intro', webpage)),
+ '%s简介:' % album_name)
+
+ entries = [
+ self.url_result(song_url, 'Kuwo') for song_url in re.findall(
+ r'<p[^>]+class="listen"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+/)"',
+ webpage)
+ ]
+ return self.playlist_result(entries, album_id, album_name, album_intro)
+
+
+class KuwoChartIE(InfoExtractor):
+ IE_NAME = 'kuwo:chart'
+ IE_DESC = '酷我音乐 - 排行榜'
+ _VALID_URL = r'http://yinyue\.kuwo\.cn/billboard_(?P<id>[^.]+).htm'
+ _TEST = {
+ 'url': 'http://yinyue.kuwo.cn/billboard_香港中文龙虎榜.htm',
+ 'info_dict': {
+ 'id': '香港中文龙虎榜',
+ 'title': '香港中文龙虎榜',
+ 'description': 're:\d{4}第\d{2}期',
+ },
+ 'playlist_mincount': 10,
+ }
+
+ def _real_extract(self, url):
+ chart_id = self._match_id(url)
+ webpage = self._download_webpage(
+ url, chart_id, note='Download chart info',
+ errnote='Unable to get chart info')
+
+ chart_name = self._html_search_regex(
+ r'<h1[^>]+class="unDis">([^<]+)</h1>', webpage, 'chart name')
+
+ chart_desc = self._html_search_regex(
+ r'<p[^>]+class="tabDef">(\d{4}第\d{2}期)</p>', webpage, 'chart desc')
+
+ entries = [
+ self.url_result(song_url, 'Kuwo') for song_url in re.findall(
+ r'<a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)/"', webpage)
+ ]
+ return self.playlist_result(entries, chart_id, chart_name, chart_desc)
+
+
+class KuwoSingerIE(InfoExtractor):
+ IE_NAME = 'kuwo:singer'
+ IE_DESC = '酷我音乐 - 歌手'
+ _VALID_URL = r'http://www\.kuwo\.cn/mingxing/(?P<id>[^/]+)'
+ _TESTS = [{
+ 'url': 'http://www.kuwo.cn/mingxing/bruno+mars/',
+ 'info_dict': {
+ 'id': 'bruno+mars',
+ 'title': 'Bruno Mars',
+ },
+ 'playlist_count': 10,
+ }, {
+ 'url': 'http://www.kuwo.cn/mingxing/Ali/music.htm',
+ 'info_dict': {
+ 'id': 'Ali',
+ 'title': 'Ali',
+ },
+ 'playlist_mincount': 95,
+ }]
+
+ def _real_extract(self, url):
+ singer_id = self._match_id(url)
+ webpage = self._download_webpage(
+ url, singer_id, note='Download singer info',
+ errnote='Unable to get singer info')
+
+ singer_name = self._html_search_regex(
+ r'<div class="title clearfix">\s*<h1>([^<]+)<span', webpage, 'singer name'
+ )
+
+ entries = []
+ first_page_only = False if re.search(r'/music(?:_\d+)?\.htm', url) else True
+ for page_num in itertools.count(1):
+ webpage = self._download_webpage(
+ 'http://www.kuwo.cn/mingxing/%s/music_%d.htm' % (singer_id, page_num),
+ singer_id, note='Download song list page #%d' % page_num,
+ errnote='Unable to get song list page #%d' % page_num)
+
+ entries.extend([
+ self.url_result(song_url, 'Kuwo') for song_url in re.findall(
+ r'<p[^>]+class="m_name"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)/',
+ webpage)
+ ][:10 if first_page_only else None])
+
+ if first_page_only or not re.search(r'<a[^>]+href="[^"]+">下一页</a>', webpage):
+ break
+
+ return self.playlist_result(entries, singer_id, singer_name)
+
+
+class KuwoCategoryIE(InfoExtractor):
+ IE_NAME = 'kuwo:category'
+ IE_DESC = '酷我音乐 - 分类'
+ _VALID_URL = r'http://yinyue\.kuwo\.cn/yy/cinfo_(?P<id>\d+?).htm'
+ _TEST = {
+ 'url': 'http://yinyue.kuwo.cn/yy/cinfo_86375.htm',
+ 'info_dict': {
+ 'id': '86375',
+ 'title': '八十年代精选',
+ 'description': '这些都是属于八十年代的回忆!',
+ },
+ 'playlist_count': 30,
+ }
+
+ def _real_extract(self, url):
+ category_id = self._match_id(url)
+ webpage = self._download_webpage(
+ url, category_id, note='Download category info',
+ errnote='Unable to get category info')
+
+ category_name = self._html_search_regex(
+ r'<h1[^>]+title="([^<>]+?)">[^<>]+?</h1>', webpage, 'category name')
+
+ category_desc = remove_start(
+ get_element_by_id('intro', webpage).strip(),
+ '%s简介:' % category_name)
+
+ jsonm = self._parse_json(self._html_search_regex(
+ r'var\s+jsonm\s*=\s*([^;]+);', webpage, 'category songs'), category_id)
+
+ entries = [
+ self.url_result('http://www.kuwo.cn/yinyue/%s/' % song['musicrid'], 'Kuwo')
+ for song in jsonm['musiclist']
+ ]
+ return self.playlist_result(entries, category_id, category_name, category_desc)
+
+
+class KuwoMvIE(KuwoBaseIE):
+ IE_NAME = 'kuwo:mv'
+ IE_DESC = '酷我音乐 - MV'
+ _VALID_URL = r'http://www\.kuwo\.cn/mv/(?P<id>\d+?)/'
+ _TEST = {
+ 'url': 'http://www.kuwo.cn/mv/6480076/',
+ 'info_dict': {
+ 'id': '6480076',
+ 'ext': 'mkv',
+ 'title': '我们家MV',
+ 'creator': '2PM',
+ },
+ }
+ _FORMATS = KuwoBaseIE._FORMATS + [
+ {'format': 'mkv', 'ext': 'mkv', 'preference': 250},
+ {'format': 'mp4', 'ext': 'mp4', 'preference': 200},
+ ]
+
+ def _real_extract(self, url):
+ song_id = self._match_id(url)
+ webpage = self._download_webpage(
+ url, song_id, note='Download mv detail info: %s' % song_id,
+ errnote='Unable to get mv detail info: %s' % song_id)
+
+ mobj = re.search(
+ r'<h1[^>]+title="(?P<song>[^"]+)">[^<]+<span[^>]+title="(?P<singer>[^"]+)"',
+ webpage)
+ if mobj:
+ song_name = mobj.group('song')
+ singer_name = mobj.group('singer')
+ else:
+ raise ExtractorError('Unable to find song or singer names')
+
+ formats = self._get_formats(song_id)
+
+ return {
+ 'id': song_id,
+ 'title': song_name,
+ 'creator': singer_name,
+ 'formats': formats,
+ }
class LetvIE(InfoExtractor):
+ IE_DESC = '乐视网'
_VALID_URL = r'http://www\.letv\.com/ptv/vplay/(?P<id>\d+).html'
_TESTS = [{
from ..utils import (
determine_ext,
int_or_none,
+ remove_end,
unified_strdate,
ExtractorError,
)
'title': 'В Сети появилось видео захвата «Правым сектором» колхозных полей ',
'description': 'Жители двух поселков Днепропетровской области не простили радикалам угрозу лишения плодородных земель и пошли в лобовую. ',
'upload_date': '20150402',
- 'uploader': 'embed.life.ru',
}
}, {
'url': 'http://lifenews.ru/news/153461',
'title': 'В Москве спасли потерявшегося медвежонка, который спрятался на дереве',
'description': 'Маленький хищник не смог найти дорогу домой и обрел временное убежище на тополе недалеко от жилого массива, пока его не нашла соседская собака.',
'upload_date': '20150505',
- 'uploader': 'embed.life.ru',
}
}, {
'url': 'http://lifenews.ru/video/13035',
if not videos and not iframe_link:
raise ExtractorError('No media links available for %s' % video_id)
- title = self._og_search_title(webpage)
- TITLE_SUFFIX = ' - Первый по срочным новостям — LIFE | NEWS'
- if title.endswith(TITLE_SUFFIX):
- title = title[:-len(TITLE_SUFFIX)]
+ title = remove_end(
+ self._og_search_title(webpage),
+ ' - Первый по срочным новостям — LIFE | NEWS')
description = self._og_search_description(webpage)
view_count = self._html_search_regex(
r'<div class=\'views\'>\s*(\d+)\s*</div>', webpage, 'view count', fatal=False)
comment_count = self._html_search_regex(
- r'<div class=\'comments\'>\s*<span class=\'counter\'>\s*(\d+)\s*</span>', webpage, 'comment count', fatal=False)
+ r'=\'commentCount\'[^>]*>\s*(\d+)\s*<',
+ webpage, 'comment count', fatal=False)
upload_date = self._html_search_regex(
- r'<time datetime=\'([^\']+)\'>', webpage, 'upload date', fatal=False)
+ r'<time[^>]*datetime=\'([^\']+)\'', webpage, 'upload date', fatal=False)
if upload_date is not None:
upload_date = unified_strdate(upload_date)
'title': 'Man is Fatally Struck by Reckless Car While Packing up a Moving Truck',
'age_limit': 18,
}
+ }, {
+ # Covers https://github.com/rg3/youtube-dl/pull/5983
+ 'url': 'http://www.liveleak.com/view?i=801_1409392012',
+ 'md5': '0b3bec2d888c20728ca2ad3642f0ef15',
+ 'info_dict': {
+ 'id': '801_1409392012',
+ 'ext': 'mp4',
+ 'description': "Happened on 27.7.2014. \r\nAt 0:53 you can see people still swimming at near beach.",
+ 'uploader': 'bony333',
+ 'title': 'Crazy Hungarian tourist films close call waterspout in Croatia'
+ }
}]
def _real_extract(self, url):
'url': s['file'],
} for i, s in enumerate(sources)]
for i, s in enumerate(sources):
- orig_url = s['file'].replace('.h264_base.mp4', '')
+ # Removing '.h264_*.mp4' gives the raw video, which is essentially
+ # the same video without the LiveLeak logo at the top (see
+ # https://github.com/rg3/youtube-dl/pull/4768)
+ orig_url = re.sub(r'\.h264_.+?\.mp4', '', s['file'])
if s['file'] != orig_url:
formats.append({
'format_id': 'original-%s' % i,
return
login_form = {
- 'username': username,
- 'password': password,
+ 'username': username.encode('utf-8'),
+ 'password': password.encode('utf-8'),
'remember': 'false',
'stayPut': 'false'
}
request = compat_urllib_request.Request(
- self._LOGIN_URL, compat_urllib_parse.urlencode(login_form))
+ self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
login_page = self._download_webpage(
request, None, 'Logging in as %s' % username)
'stayPut': 'false',
}
request = compat_urllib_request.Request(
- self._LOGIN_URL, compat_urllib_parse.urlencode(confirm_form))
+ self._LOGIN_URL, compat_urllib_parse.urlencode(confirm_form).encode('utf-8'))
login_page = self._download_webpage(
request, None,
'Confirming log in and log out from another device')
--- /dev/null
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .vimple import SprutoBaseIE
+
+
+class MyviIE(SprutoBaseIE):
+ _VALID_URL = r'''(?x)
+ https?://
+ myvi\.(?:ru/player|tv)/
+ (?:
+ (?:
+ embed/html|
+ flash|
+ api/Video/Get
+ )/|
+ content/preloader\.swf\?.*\bid=
+ )
+ (?P<id>[\da-zA-Z_-]+)
+ '''
+ _TESTS = [{
+ 'url': 'http://myvi.ru/player/embed/html/oOy4euHA6LVwNNAjhD9_Jq5Ha2Qf0rtVMVFMAZav8wObeRTZaCATzucDQIDph8hQU0',
+ 'md5': '571bbdfba9f9ed229dc6d34cc0f335bf',
+ 'info_dict': {
+ 'id': 'f16b2bbd-cde8-481c-a981-7cd48605df43',
+ 'ext': 'mp4',
+ 'title': 'хозяин жизни',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 25,
+ },
+ }, {
+ 'url': 'http://myvi.ru/player/content/preloader.swf?id=oOy4euHA6LVwNNAjhD9_Jq5Ha2Qf0rtVMVFMAZav8wOYf1WFpPfc_bWTKGVf_Zafr0',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://myvi.ru/player/api/Video/Get/oOy4euHA6LVwNNAjhD9_Jq5Ha2Qf0rtVMVFMAZav8wObeRTZaCATzucDQIDph8hQU0',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://myvi.tv/embed/html/oTGTNWdyz4Zwy_u1nraolwZ1odenTd9WkTnRfIL9y8VOgHYqOHApE575x4_xxS9Vn0?ap=0',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://myvi.ru/player/flash/ocp2qZrHI-eZnHKQBK4cZV60hslH8LALnk0uBfKsB-Q4WnY26SeGoYPi8HWHxu0O30',
+ 'only_matching': True,
+ }]
+
+ @classmethod
+ def _extract_url(cls, webpage):
+ mobj = re.search(
+ r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//myvi\.(?:ru/player|tv)/(?:embed/html|flash)/[^"]+)\1', webpage)
+ if mobj:
+ return mobj.group('url')
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ spruto = self._download_json(
+ 'http://myvi.ru/player/api/Video/Get/%s?sig' % video_id, video_id)['sprutoData']
+
+ return self._extract_spruto(spruto, video_id)
--- /dev/null
+# coding: utf-8
+from __future__ import unicode_literals
+
+from hashlib import md5
+from base64 import b64encode
+from datetime import datetime
+import re
+
+from .common import InfoExtractor
+from ..compat import (
+ compat_urllib_request,
+ compat_urllib_parse,
+ compat_str,
+ compat_itertools_count,
+)
+
+
+class NetEaseMusicBaseIE(InfoExtractor):
+ _FORMATS = ['bMusic', 'mMusic', 'hMusic']
+ _NETEASE_SALT = '3go8&$8*3*3h0k(2)2'
+ _API_BASE = 'http://music.163.com/api/'
+
+ @classmethod
+ def _encrypt(cls, dfsid):
+ salt_bytes = bytearray(cls._NETEASE_SALT.encode('utf-8'))
+ string_bytes = bytearray(compat_str(dfsid).encode('ascii'))
+ salt_len = len(salt_bytes)
+ for i in range(len(string_bytes)):
+ string_bytes[i] = string_bytes[i] ^ salt_bytes[i % salt_len]
+ m = md5()
+ m.update(bytes(string_bytes))
+ result = b64encode(m.digest()).decode('ascii')
+ return result.replace('/', '_').replace('+', '-')
+
+ @classmethod
+ def extract_formats(cls, info):
+ formats = []
+ for song_format in cls._FORMATS:
+ details = info.get(song_format)
+ if not details:
+ continue
+ formats.append({
+ 'url': 'http://m1.music.126.net/%s/%s.%s' %
+ (cls._encrypt(details['dfsId']), details['dfsId'],
+ details['extension']),
+ 'ext': details.get('extension'),
+ 'abr': details.get('bitrate', 0) / 1000,
+ 'format_id': song_format,
+ 'filesize': details.get('size'),
+ 'asr': details.get('sr')
+ })
+ return formats
+
+ @classmethod
+ def convert_milliseconds(cls, ms):
+ return int(round(ms / 1000.0))
+
+ def query_api(self, endpoint, video_id, note):
+ req = compat_urllib_request.Request('%s%s' % (self._API_BASE, endpoint))
+ req.add_header('Referer', self._API_BASE)
+ return self._download_json(req, video_id, note)
+
+
+class NetEaseMusicIE(NetEaseMusicBaseIE):
+ IE_NAME = 'netease:song'
+ IE_DESC = '网易云音乐'
+ _VALID_URL = r'https?://music\.163\.com/(#/)?song\?id=(?P<id>[0-9]+)'
+ _TESTS = [{
+ 'url': 'http://music.163.com/#/song?id=32102397',
+ 'md5': 'f2e97280e6345c74ba9d5677dd5dcb45',
+ 'info_dict': {
+ 'id': '32102397',
+ 'ext': 'mp3',
+ 'title': 'Bad Blood (feat. Kendrick Lamar)',
+ 'creator': 'Taylor Swift / Kendrick Lamar',
+ 'upload_date': '20150517',
+ 'timestamp': 1431878400,
+ 'description': 'md5:a10a54589c2860300d02e1de821eb2ef',
+ },
+ }, {
+ 'note': 'No lyrics translation.',
+ 'url': 'http://music.163.com/#/song?id=29822014',
+ 'info_dict': {
+ 'id': '29822014',
+ 'ext': 'mp3',
+ 'title': '听见下雨的声音',
+ 'creator': '周杰伦',
+ 'upload_date': '20141225',
+ 'timestamp': 1419523200,
+ 'description': 'md5:a4d8d89f44656af206b7b2555c0bce6c',
+ },
+ }, {
+ 'note': 'No lyrics.',
+ 'url': 'http://music.163.com/song?id=17241424',
+ 'info_dict': {
+ 'id': '17241424',
+ 'ext': 'mp3',
+ 'title': 'Opus 28',
+ 'creator': 'Dustin O\'Halloran',
+ 'upload_date': '20080211',
+ 'timestamp': 1202745600,
+ },
+ }, {
+ 'note': 'Has translated name.',
+ 'url': 'http://music.163.com/#/song?id=22735043',
+ 'info_dict': {
+ 'id': '22735043',
+ 'ext': 'mp3',
+ 'title': '소원을 말해봐 (Genie)',
+ 'creator': '少女时代',
+ 'description': 'md5:79d99cc560e4ca97e0c4d86800ee4184',
+ 'upload_date': '20100127',
+ 'timestamp': 1264608000,
+ 'alt_title': '说出愿望吧(Genie)',
+ }
+ }]
+
+ def _process_lyrics(self, lyrics_info):
+ original = lyrics_info.get('lrc', {}).get('lyric')
+ translated = lyrics_info.get('tlyric', {}).get('lyric')
+
+ if not translated:
+ return original
+
+ lyrics_expr = r'(\[[0-9]{2}:[0-9]{2}\.[0-9]{2,}\])([^\n]+)'
+ original_ts_texts = re.findall(lyrics_expr, original)
+ translation_ts_dict = dict(
+ (time_stamp, text) for time_stamp, text in re.findall(lyrics_expr, translated)
+ )
+ lyrics = '\n'.join([
+ '%s%s / %s' % (time_stamp, text, translation_ts_dict.get(time_stamp, ''))
+ for time_stamp, text in original_ts_texts
+ ])
+ return lyrics
+
+ def _real_extract(self, url):
+ song_id = self._match_id(url)
+
+ params = {
+ 'id': song_id,
+ 'ids': '[%s]' % song_id
+ }
+ info = self.query_api(
+ 'song/detail?' + compat_urllib_parse.urlencode(params),
+ song_id, 'Downloading song info')['songs'][0]
+
+ formats = self.extract_formats(info)
+ self._sort_formats(formats)
+
+ lyrics_info = self.query_api(
+ 'song/lyric?id=%s&lv=-1&tv=-1' % song_id,
+ song_id, 'Downloading lyrics data')
+ lyrics = self._process_lyrics(lyrics_info)
+
+ alt_title = None
+ if info.get('transNames'):
+ alt_title = '/'.join(info.get('transNames'))
+
+ return {
+ 'id': song_id,
+ 'title': info['name'],
+ 'alt_title': alt_title,
+ 'creator': ' / '.join([artist['name'] for artist in info.get('artists', [])]),
+ 'timestamp': self.convert_milliseconds(info.get('album', {}).get('publishTime')),
+ 'thumbnail': info.get('album', {}).get('picUrl'),
+ 'duration': self.convert_milliseconds(info.get('duration', 0)),
+ 'description': lyrics,
+ 'formats': formats,
+ }
+
+
+class NetEaseMusicAlbumIE(NetEaseMusicBaseIE):
+ IE_NAME = 'netease:album'
+ IE_DESC = '网易云音乐 - 专辑'
+ _VALID_URL = r'https?://music\.163\.com/(#/)?album\?id=(?P<id>[0-9]+)'
+ _TEST = {
+ 'url': 'http://music.163.com/#/album?id=220780',
+ 'info_dict': {
+ 'id': '220780',
+ 'title': 'B\'day',
+ },
+ 'playlist_count': 23,
+ }
+
+ def _real_extract(self, url):
+ album_id = self._match_id(url)
+
+ info = self.query_api(
+ 'album/%s?id=%s' % (album_id, album_id),
+ album_id, 'Downloading album data')['album']
+
+ name = info['name']
+ desc = info.get('description')
+ entries = [
+ self.url_result('http://music.163.com/#/song?id=%s' % song['id'],
+ 'NetEaseMusic', song['id'])
+ for song in info['songs']
+ ]
+ return self.playlist_result(entries, album_id, name, desc)
+
+
+class NetEaseMusicSingerIE(NetEaseMusicBaseIE):
+ IE_NAME = 'netease:singer'
+ IE_DESC = '网易云音乐 - 歌手'
+ _VALID_URL = r'https?://music\.163\.com/(#/)?artist\?id=(?P<id>[0-9]+)'
+ _TESTS = [{
+ 'note': 'Singer has aliases.',
+ 'url': 'http://music.163.com/#/artist?id=10559',
+ 'info_dict': {
+ 'id': '10559',
+ 'title': '张惠妹 - aMEI;阿密特',
+ },
+ 'playlist_count': 50,
+ }, {
+ 'note': 'Singer has translated name.',
+ 'url': 'http://music.163.com/#/artist?id=124098',
+ 'info_dict': {
+ 'id': '124098',
+ 'title': '李昇基 - 이승기',
+ },
+ 'playlist_count': 50,
+ }]
+
+ def _real_extract(self, url):
+ singer_id = self._match_id(url)
+
+ info = self.query_api(
+ 'artist/%s?id=%s' % (singer_id, singer_id),
+ singer_id, 'Downloading singer data')
+
+ name = info['artist']['name']
+ if info['artist']['trans']:
+ name = '%s - %s' % (name, info['artist']['trans'])
+ if info['artist']['alias']:
+ name = '%s - %s' % (name, ';'.join(info['artist']['alias']))
+
+ entries = [
+ self.url_result('http://music.163.com/#/song?id=%s' % song['id'],
+ 'NetEaseMusic', song['id'])
+ for song in info['hotSongs']
+ ]
+ return self.playlist_result(entries, singer_id, name)
+
+
+class NetEaseMusicListIE(NetEaseMusicBaseIE):
+ IE_NAME = 'netease:playlist'
+ IE_DESC = '网易云音乐 - 歌单'
+ _VALID_URL = r'https?://music\.163\.com/(#/)?(playlist|discover/toplist)\?id=(?P<id>[0-9]+)'
+ _TESTS = [{
+ 'url': 'http://music.163.com/#/playlist?id=79177352',
+ 'info_dict': {
+ 'id': '79177352',
+ 'title': 'Billboard 2007 Top 100',
+ 'description': 'md5:12fd0819cab2965b9583ace0f8b7b022'
+ },
+ 'playlist_count': 99,
+ }, {
+ 'note': 'Toplist/Charts sample',
+ 'url': 'http://music.163.com/#/discover/toplist?id=3733003',
+ 'info_dict': {
+ 'id': '3733003',
+ 'title': 're:韩国Melon排行榜周榜 [0-9]{4}-[0-9]{2}-[0-9]{2}',
+ 'description': 'md5:73ec782a612711cadc7872d9c1e134fc',
+ },
+ 'playlist_count': 50,
+ }]
+
+ def _real_extract(self, url):
+ list_id = self._match_id(url)
+
+ info = self.query_api(
+ 'playlist/detail?id=%s&lv=-1&tv=-1' % list_id,
+ list_id, 'Downloading playlist data')['result']
+
+ name = info['name']
+ desc = info.get('description')
+
+ if info.get('specialType') == 10: # is a chart/toplist
+ datestamp = datetime.fromtimestamp(
+ self.convert_milliseconds(info['updateTime'])).strftime('%Y-%m-%d')
+ name = '%s %s' % (name, datestamp)
+
+ entries = [
+ self.url_result('http://music.163.com/#/song?id=%s' % song['id'],
+ 'NetEaseMusic', song['id'])
+ for song in info['tracks']
+ ]
+ return self.playlist_result(entries, list_id, name, desc)
+
+
+class NetEaseMusicMvIE(NetEaseMusicBaseIE):
+ IE_NAME = 'netease:mv'
+ IE_DESC = '网易云音乐 - MV'
+ _VALID_URL = r'https?://music\.163\.com/(#/)?mv\?id=(?P<id>[0-9]+)'
+ _TEST = {
+ 'url': 'http://music.163.com/#/mv?id=415350',
+ 'info_dict': {
+ 'id': '415350',
+ 'ext': 'mp4',
+ 'title': '이럴거면 그러지말지',
+ 'description': '白雅言自作曲唱甜蜜爱情',
+ 'creator': '白雅言',
+ 'upload_date': '20150520',
+ },
+ }
+
+ def _real_extract(self, url):
+ mv_id = self._match_id(url)
+
+ info = self.query_api(
+ 'mv/detail?id=%s&type=mp4' % mv_id,
+ mv_id, 'Downloading mv info')['data']
+
+ formats = [
+ {'url': mv_url, 'ext': 'mp4', 'format_id': '%sp' % brs, 'height': int(brs)}
+ for brs, mv_url in info['brs'].items()
+ ]
+ self._sort_formats(formats)
+
+ return {
+ 'id': mv_id,
+ 'title': info['name'],
+ 'description': info.get('desc') or info.get('briefDesc'),
+ 'creator': info['artistName'],
+ 'upload_date': info['publishTime'].replace('-', ''),
+ 'formats': formats,
+ 'thumbnail': info.get('cover'),
+ 'duration': self.convert_milliseconds(info.get('duration', 0)),
+ }
+
+
+class NetEaseMusicProgramIE(NetEaseMusicBaseIE):
+ IE_NAME = 'netease:program'
+ IE_DESC = '网易云音乐 - 电台节目'
+ _VALID_URL = r'https?://music\.163\.com/(#/?)program\?id=(?P<id>[0-9]+)'
+ _TESTS = [{
+ 'url': 'http://music.163.com/#/program?id=10109055',
+ 'info_dict': {
+ 'id': '10109055',
+ 'ext': 'mp3',
+ 'title': '不丹足球背后的故事',
+ 'description': '喜马拉雅人的足球梦 ...',
+ 'creator': '大话西藏',
+ 'timestamp': 1434179342,
+ 'upload_date': '20150613',
+ 'duration': 900,
+ },
+ }, {
+ 'note': 'This program has accompanying songs.',
+ 'url': 'http://music.163.com/#/program?id=10141022',
+ 'info_dict': {
+ 'id': '10141022',
+ 'title': '25岁,你是自在如风的少年<27°C>',
+ 'description': 'md5:8d594db46cc3e6509107ede70a4aaa3b',
+ },
+ 'playlist_count': 4,
+ }, {
+ 'note': 'This program has accompanying songs.',
+ 'url': 'http://music.163.com/#/program?id=10141022',
+ 'info_dict': {
+ 'id': '10141022',
+ 'ext': 'mp3',
+ 'title': '25岁,你是自在如风的少年<27°C>',
+ 'description': 'md5:8d594db46cc3e6509107ede70a4aaa3b',
+ 'timestamp': 1434450841,
+ 'upload_date': '20150616',
+ },
+ 'params': {
+ 'noplaylist': True
+ }
+ }]
+
+ def _real_extract(self, url):
+ program_id = self._match_id(url)
+
+ info = self.query_api(
+ 'dj/program/detail?id=%s' % program_id,
+ program_id, 'Downloading program info')['program']
+
+ name = info['name']
+ description = info['description']
+
+ if not info['songs'] or self._downloader.params.get('noplaylist'):
+ if info['songs']:
+ self.to_screen(
+ 'Downloading just the main audio %s because of --no-playlist'
+ % info['mainSong']['id'])
+
+ formats = self.extract_formats(info['mainSong'])
+ self._sort_formats(formats)
+
+ return {
+ 'id': program_id,
+ 'title': name,
+ 'description': description,
+ 'creator': info['dj']['brand'],
+ 'timestamp': self.convert_milliseconds(info['createTime']),
+ 'thumbnail': info['coverUrl'],
+ 'duration': self.convert_milliseconds(info.get('duration', 0)),
+ 'formats': formats,
+ }
+
+ self.to_screen(
+ 'Downloading playlist %s - add --no-playlist to just download the main audio %s'
+ % (program_id, info['mainSong']['id']))
+
+ song_ids = [info['mainSong']['id']]
+ song_ids.extend([song['id'] for song in info['songs']])
+ entries = [
+ self.url_result('http://music.163.com/#/song?id=%s' % song_id,
+ 'NetEaseMusic', song_id)
+ for song_id in song_ids
+ ]
+ return self.playlist_result(entries, program_id, name, description)
+
+
+class NetEaseMusicDjRadioIE(NetEaseMusicBaseIE):
+ IE_NAME = 'netease:djradio'
+ IE_DESC = '网易云音乐 - 电台'
+ _VALID_URL = r'https?://music\.163\.com/(#/)?djradio\?id=(?P<id>[0-9]+)'
+ _TEST = {
+ 'url': 'http://music.163.com/#/djradio?id=42',
+ 'info_dict': {
+ 'id': '42',
+ 'title': '声音蔓延',
+ 'description': 'md5:766220985cbd16fdd552f64c578a6b15'
+ },
+ 'playlist_mincount': 40,
+ }
+ _PAGE_SIZE = 1000
+
+ def _real_extract(self, url):
+ dj_id = self._match_id(url)
+
+ name = None
+ desc = None
+ entries = []
+ for offset in compat_itertools_count(start=0, step=self._PAGE_SIZE):
+ info = self.query_api(
+ 'dj/program/byradio?asc=false&limit=%d&radioId=%s&offset=%d'
+ % (self._PAGE_SIZE, dj_id, offset),
+ dj_id, 'Downloading dj programs - %d' % offset)
+
+ entries.extend([
+ self.url_result(
+ 'http://music.163.com/#/program?id=%s' % program['id'],
+ 'NetEaseMusicProgram', program['id'])
+ for program in info['programs']
+ ])
+
+ if name is None:
+ radio = info['programs'][0]['radio']
+ name = radio['name']
+ desc = radio['desc']
+
+ if not info['more']:
+ break
+
+ return self.playlist_result(entries, dj_id, name, desc)
page = self._download_webpage(url, video_id, 'Downloading page')
video_guid = self._html_search_regex(
- r'<meta property="og:video" content="https?://(?:www\.)?newstube\.ru/freshplayer\.swf\?guid=(?P<guid>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})',
+ r'<meta property="og:video:url" content="https?://(?:www\.)?newstube\.ru/freshplayer\.swf\?guid=(?P<guid>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})',
page, 'video GUID')
player = self._download_xml(
class NextMediaIE(InfoExtractor):
+ IE_DESC = '蘋果日報'
_VALID_URL = r'http://hk.apple.nextmedia.com/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)'
_TESTS = [{
'url': 'http://hk.apple.nextmedia.com/realtime/news/20141108/53109199',
class NextMediaActionNewsIE(NextMediaIE):
+ IE_DESC = '蘋果日報 - 動新聞'
_VALID_URL = r'http://hk.dv.nextmedia.com/actionnews/[^/]+/(?P<date>\d+)/(?P<id>\d+)/\d+'
_TESTS = [{
'url': 'http://hk.dv.nextmedia.com/actionnews/hit/20150121/19009428/20061460',
class AppleDailyIE(NextMediaIE):
+ IE_DESC = '臺灣蘋果日報'
_VALID_URL = r'http://(www|ent).appledaily.com.tw/(?:animation|appledaily|enews|realtimenews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
_TESTS = [{
'url': 'http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694',
_VALID_URL = r'''(?x)https?://
(?P<host>(?:www\.)?(?:nfl\.com|.*?\.clubs\.nfl\.com))/
(?:.+?/)*
- (?P<id>(?:\d[a-z]{2}\d{13}|\w{8}\-(?:\w{4}\-){3}\w{12}))'''
+ (?P<id>(?:[a-z0-9]{16}|\w{8}\-(?:\w{4}\-){3}\w{12}))'''
_TESTS = [
{
'url': 'http://www.nfl.com/videos/nfl-game-highlights/0ap3000000398478/Week-3-Redskins-vs-Eagles-highlights',
'upload_date': '20150202',
},
},
+ {
+ 'url': 'http://www.nfl.com/videos/nfl-network-top-ten/09000d5d810a6bd4/Top-10-Gutsiest-Performances-Jack-Youngblood',
+ 'only_matching': True,
+ }
]
@staticmethod
extension = xpath_text(video_info, './/movie_type')
if not extension:
extension = determine_ext(video_real_url)
- video_format = extension.upper()
thumbnail = (
xpath_text(video_info, './/thumbnail_url') or
'url': video_real_url,
'title': title,
'ext': extension,
- 'format': video_format,
+ 'format_id': 'economy' if video_real_url.endswith('low') else 'normal',
'thumbnail': thumbnail,
'description': description,
'uploader': uploader,
if episode_number:
title += ' #' + compat_str(episode_number)
if episode:
- title += ' - ' + episode
+ title += ' - ' + compat_str(episode)
description = show.get('show_resume') or show.get('family_resume')
token_page = self._download_webpage(
'http://ida.omroep.nl/npoplayer/i.js',
video_id, note='Downloading token')
- return self._search_regex(
+ token = self._search_regex(
r'npoplayer\.token = "(.+?)"', token_page, 'token')
+ # Decryption algorithm extracted from http://npoplayer.omroep.nl/csjs/npoplayer-min.js
+ token_l = list(token)
+ first = second = None
+ for i in range(5, len(token_l) - 4):
+ if token_l[i].isdigit():
+ if first is None:
+ first = i
+ elif second is None:
+ second = i
+ if first is None or second is None:
+ first = 12
+ second = 13
+
+ token_l[first], token_l[second] = token_l[second], token_l[first]
+
+ return ''.join(token_l)
class NPOIE(NPOBaseIE):
def _get_info(self, video_id):
metadata = self._download_json(
- 'http://e.omroep.nl/metadata/aflevering/%s' % video_id,
+ 'http://e.omroep.nl/metadata/%s' % video_id,
video_id,
# We have to remove the javascript callback
transform_source=strip_jsonp,
class NRKIE(InfoExtractor):
- _VALID_URL = r'(?:nrk:|http://(?:www\.)?nrk\.no/video/PS\*)(?P<id>\d+)'
+ _VALID_URL = r'(?:nrk:|https?://(?:www\.)?nrk\.no/video/PS\*)(?P<id>\d+)'
_TESTS = [
{
class NRKPlaylistIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?nrk\.no/(?!video)(?:[^/]+/)+(?P<id>[^/]+)'
+ _VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video)(?:[^/]+/)+(?P<id>[^/]+)'
_TESTS = [{
'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',
class NRKTVIE(InfoExtractor):
- _VALID_URL = r'(?P<baseurl>http://tv\.nrk(?:super)?\.no/)(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?'
+ _VALID_URL = r'(?P<baseurl>https?://tv\.nrk(?:super)?\.no/)(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?'
_TESTS = [
{
- 'url': 'http://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
+ 'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
'md5': 'adf2c5454fa2bf032f47a9f8fb351342',
'info_dict': {
'id': 'MUHH48000314',
},
},
{
- 'url': 'http://tv.nrk.no/program/mdfp15000514',
+ 'url': 'https://tv.nrk.no/program/mdfp15000514',
'md5': '383650ece2b25ecec996ad7b5bb2a384',
'info_dict': {
'id': 'mdfp15000514',
},
{
# single playlist video
- 'url': 'http://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
+ 'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
'md5': 'adbd1dbd813edaf532b0a253780719c2',
'info_dict': {
'id': 'MSPO40010515-part2',
'skip': 'Only works from Norway',
},
{
- 'url': 'http://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
+ 'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
'playlist': [
{
'md5': '9480285eff92d64f06e02a5367970a7a',
--- /dev/null
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import determine_ext
+
+
+class OnionStudiosIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?onionstudios\.com/(?:videos/[^/]+-|embed\?.*\bid=)(?P<id>\d+)(?!-)'
+
+ _TESTS = [{
+ 'url': 'http://www.onionstudios.com/videos/hannibal-charges-forward-stops-for-a-cocktail-2937',
+ 'md5': 'd4851405d31adfadf71cd7a487b765bb',
+ 'info_dict': {
+ 'id': '2937',
+ 'ext': 'mp4',
+ 'title': 'Hannibal charges forward, stops for a cocktail',
+ 'description': 'md5:545299bda6abf87e5ec666548c6a9448',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'uploader': 'The A.V. Club',
+ 'uploader_id': 'TheAVClub',
+ },
+ }, {
+ 'url': 'http://www.onionstudios.com/embed?id=2855&autoplay=true',
+ 'only_matching': True,
+ }]
+
+ @staticmethod
+ def _extract_url(webpage):
+ mobj = re.search(
+ r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?onionstudios\.com/embed.+?)\1', webpage)
+ if mobj:
+ return mobj.group('url')
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(
+ 'http://www.onionstudios.com/embed?id=%s' % video_id, video_id)
+
+ formats = []
+ for src in re.findall(r'<source[^>]+src="([^"]+)"', webpage):
+ if determine_ext(src) != 'm3u8': # m3u8 always results in 403
+ formats.append({
+ 'url': src,
+ })
+ self._sort_formats(formats)
+
+ title = self._search_regex(
+ r'share_title\s*=\s*"([^"]+)"', webpage, 'title')
+ description = self._search_regex(
+ r'share_description\s*=\s*"([^"]+)"', webpage,
+ 'description', default=None)
+ thumbnail = self._search_regex(
+ r'poster="([^"]+)"', webpage, 'thumbnail', default=False)
+
+ uploader_id = self._search_regex(
+ r'twitter_handle\s*=\s*"([^"]+)"',
+ webpage, 'uploader id', fatal=False)
+ uploader = self._search_regex(
+ r'window\.channelName\s*=\s*"Embedded:([^"]+)"',
+ webpage, 'uploader', default=False)
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'uploader': uploader,
+ 'uploader_id': uploader_id,
+ 'formats': formats,
+ }
+# coding: utf-8
from __future__ import unicode_literals
import re
'description': 'md5:ba0c207295339c8d6eced00b7c363c6a',
'duration': 3190,
},
+ 'params': {
+ 'skip_download': True, # requires ffmpeg
+ },
},
{
'url': 'http://www.pbs.org/wgbh/pages/frontline/losing-iraq/',
'description': 'md5:f5bfbefadf421e8bb8647602011caf8e',
'duration': 5050,
},
+ 'params': {
+ 'skip_download': True, # requires ffmpeg
+ }
},
{
'url': 'http://www.pbs.org/newshour/bb/education-jan-june12-cyberschools_02-23/',
'title': 'Dudamel Conducts Verdi Requiem at the Hollywood Bowl - Full',
'duration': 6559,
'thumbnail': 're:^https?://.*\.jpg$',
- }
+ },
+ 'params': {
+ 'skip_download': True, # requires ffmpeg
+ },
},
{
'url': 'http://www.pbs.org/wgbh/nova/earth/killer-typhoon.html',
'duration': 3172,
'thumbnail': 're:^https?://.*\.jpg$',
'upload_date': '20140122',
- }
+ },
+ 'params': {
+ 'skip_download': True, # requires ffmpeg
+ },
},
{
'url': 'http://www.pbs.org/wgbh/pages/frontline/united-states-of-secrets/',
'id': 'united-states-of-secrets',
},
'playlist_count': 2,
+ },
+ {
+ 'url': 'http://www.pbs.org/wgbh/americanexperience/films/death/player/',
+ 'info_dict': {
+ 'id': '2280706814',
+ 'display_id': 'player',
+ 'ext': 'mp4',
+ 'title': 'Death and the Civil War',
+ 'description': 'American Experience, TV’s most-watched history series, brings to life the compelling stories from our past that inform our understanding of the world today.',
+ 'duration': 6705,
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ },
+ 'params': {
+ 'skip_download': True, # requires ffmpeg
+ },
}
]
return media_id, presumptive_id, upload_date
url = self._search_regex(
- r'<iframe\s+(?:class|id)=["\']partnerPlayer["\'].*?\s+src=["\'](.*?)["\']>',
+ r'<iframe\s+[^>]*\s+src=["\']([^\'"]+partnerplayer[^\'"]+)["\']',
webpage, 'player URL')
mobj = re.match(self._VALID_URL, url)
rating_str = rating_str.rpartition('-')[2]
age_limit = US_RATINGS.get(rating_str)
+ subtitles = {}
+ closed_captions_url = info.get('closed_captions_url')
+ if closed_captions_url:
+ subtitles['en'] = [{
+ 'ext': 'ttml',
+ 'url': closed_captions_url,
+ }]
+
return {
'id': video_id,
'display_id': display_id,
'age_limit': age_limit,
'upload_date': upload_date,
'formats': formats,
+ 'subtitles': subtitles,
}
--- /dev/null
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ int_or_none,
+ remove_end,
+ remove_start,
+ str_to_int,
+ unified_strdate,
+)
+
+
+class PinkbikeIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:(?:www\.)?pinkbike\.com/video/|es\.pinkbike\.org/i/kvid/kvid-y5\.swf\?id=)(?P<id>[0-9]+)'
+ _TESTS = [{
+ 'url': 'http://www.pinkbike.com/video/402811/',
+ 'md5': '4814b8ca7651034cd87e3361d5c2155a',
+ 'info_dict': {
+ 'id': '402811',
+ 'ext': 'mp4',
+ 'title': 'Brandon Semenuk - RAW 100',
+ 'description': 'Official release: www.redbull.ca/rupertwalker',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 100,
+ 'upload_date': '20150406',
+ 'uploader': 'revelco',
+ 'location': 'Victoria, British Columbia, Canada',
+ 'view_count': int,
+ 'comment_count': int,
+ }
+ }, {
+ 'url': 'http://es.pinkbike.org/i/kvid/kvid-y5.swf?id=406629',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(
+ 'http://www.pinkbike.com/video/%s' % video_id, video_id)
+
+ formats = []
+ for _, format_id, src in re.findall(
+ r'data-quality=((?:\\)?["\'])(.+?)\1[^>]+src=\1(.+?)\1', webpage):
+ height = int_or_none(self._search_regex(
+ r'^(\d+)[pP]$', format_id, 'height', default=None))
+ formats.append({
+ 'url': src,
+ 'format_id': format_id,
+ 'height': height,
+ })
+ self._sort_formats(formats)
+
+ title = remove_end(self._og_search_title(webpage), ' Video - Pinkbike')
+ description = self._html_search_regex(
+ r'(?s)id="media-description"[^>]*>(.+?)<',
+ webpage, 'description', default=None) or remove_start(
+ self._og_search_description(webpage), title + '. ')
+ thumbnail = self._og_search_thumbnail(webpage)
+ duration = int_or_none(self._html_search_meta(
+ 'video:duration', webpage, 'duration'))
+
+ uploader = self._search_regex(
+ r'un:\s*"([^"]+)"', webpage, 'uploader', fatal=False)
+ upload_date = unified_strdate(self._search_regex(
+ r'class="fullTime"[^>]+title="([^"]+)"',
+ webpage, 'upload date', fatal=False))
+
+ location = self._html_search_regex(
+ r'(?s)<dt>Location</dt>\s*<dd>(.+?)<',
+ webpage, 'location', fatal=False)
+
+ def extract_count(webpage, label):
+ return str_to_int(self._search_regex(
+ r'<span[^>]+class="stat-num"[^>]*>([\d,.]+)</span>\s*<span[^>]+class="stat-label"[^>]*>%s' % label,
+ webpage, label, fatal=False))
+
+ view_count = extract_count(webpage, 'Views')
+ comment_count = extract_count(webpage, 'Comments')
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'duration': duration,
+ 'upload_date': upload_date,
+ 'uploader': uploader,
+ 'location': location,
+ 'view_count': view_count,
+ 'comment_count': comment_count,
+ 'formats': formats
+ }
'id': '3586',
'ext': 'flv',
'title': 'md5:e829428ee28b1deed00de90de49d1da1',
- }
+ },
+ 'skip': 'Not accessible from Travis CI server',
}
_SONG_FORMATS = {
if m_error:
raise ExtractorError(m_error.group('msg'), expected=True)
- fields = re.findall(
- r'type="hidden" name="([^"]+)"\s+value="([^"]+)">', orig_webpage)
- data = dict(fields)
+ data = self._form_hidden_inputs(orig_webpage)
self._sleep(2, video_id)
class PornHubIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?pornhub\.com/view_video\.php\?viewkey=(?P<id>[0-9a-f]+)'
- _TEST = {
+ _VALID_URL = r'https?://(?:www\.)?pornhub\.com/(?:view_video\.php\?viewkey=|embed/)(?P<id>[0-9a-z]+)'
+ _TESTS = [{
'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
'md5': '882f488fa1f0026f023f33576004a2ed',
'info_dict': {
"title": "Seductive Indian beauty strips down and fingers her pink pussy",
"age_limit": 18
}
- }
+ }, {
+ 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d',
+ 'only_matching': True,
+ }]
+
+ @classmethod
+ def _extract_url(cls, webpage):
+ mobj = re.search(
+ r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?pornhub\.com/embed/\d+)\1', webpage)
+ if mobj:
+ return mobj.group('url')
def _extract_count(self, pattern, webpage, name):
return str_to_int(self._search_regex(
def _real_extract(self, url):
video_id = self._match_id(url)
- req = compat_urllib_request.Request(url)
+ req = compat_urllib_request.Request(
+ 'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
if '>File not exist<' in webpage:
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
- fields = dict(re.findall(r'''(?x)<input\s+
- type="hidden"\s+
- name="([^"]+)"\s+
- (?:id="[^"]+"\s+)?
- value="([^"]*)"
- ''', webpage))
+ fields = self._form_hidden_inputs(webpage)
headers = {
'Referer': url,
raise ExtractorError('Video %s does not exist' % video_id,
expected=True)
- fields = dict(re.findall(r'''(?x)type="hidden"\s+
- name="(.+?)"\s+
- value="(.*?)"
- ''', webpage))
+ fields = self._form_hidden_inputs(webpage)
post = compat_urllib_parse.urlencode(fields)
req = compat_urllib_request.Request(url, post)
req.add_header('Content-type', 'application/x-www-form-urlencoded')
r'<header class="clearfix">\s*<h3>(.+?)</h3>',
r'<!-- start video -->\s*<h1>(.+?)</h1>',
r'<h1 class="att-name">\s*(.+?)</h1>',
+ r'<header class="module_header">\s*<h2>([^<]+)</h2>\s*</header>',
]
_DESCRIPTION_REGEXES = [
r'<p itemprop="description">\s*(.+?)</p>',
def _extract_clip(self, url, webpage):
clip_id = self._html_search_regex(self._CLIPID_REGEXES, webpage, 'clip id')
- access_token = 'testclient'
- client_name = 'kolibri-1.2.5'
+ access_token = 'prosieben'
+ client_name = 'kolibri-1.12.6'
client_location = url
videos_api_url = 'http://vas.sim-technik.de/vas/live/v2/videos?%s' % compat_urllib_parse.urlencode({
for source in urls_sources:
protocol = source['protocol']
if protocol == 'rtmp' or protocol == 'rtmpe':
- mobj = re.search(r'^(?P<url>rtmpe?://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', source['url'])
+ mobj = re.search(r'^(?P<url>rtmpe?://[^/]+)/(?P<path>.+)$', source['url'])
if not mobj:
continue
+ path = mobj.group('path')
+ mp4colon_index = path.rfind('mp4:')
+ app = path[:mp4colon_index]
+ play_path = path[mp4colon_index:]
formats.append({
- 'url': mobj.group('url'),
- 'app': mobj.group('app'),
- 'play_path': mobj.group('playpath'),
+ 'url': '%s/%s' % (mobj.group('url'), app),
+ 'app': app,
+ 'play_path': play_path,
'player_url': 'http://livepassdl.conviva.com/hf/ver/2.79.0.17083/LivePassModuleMain.swf',
'page_url': 'http://www.prosieben.de',
'vbr': fix_bitrate(source['bitrate']),
from ..utils import (
strip_jsonp,
unescapeHTML,
+ clean_html,
)
from ..compat import compat_urllib_request
class QQMusicIE(InfoExtractor):
IE_NAME = 'qqmusic'
+ IE_DESC = 'QQ音乐'
_VALID_URL = r'http://y.qq.com/#type=song&mid=(?P<id>[0-9A-Za-z]+)'
_TESTS = [{
'url': 'http://y.qq.com/#type=song&mid=004295Et37taLD',
'upload_date': '20141227',
'creator': '林俊杰',
'description': 'md5:d327722d0361576fde558f1ac68a7065',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ }
+ }, {
+ 'note': 'There is no mp3-320 version of this song.',
+ 'url': 'http://y.qq.com/#type=song&mid=004MsGEo3DdNxV',
+ 'md5': 'fa3926f0c585cda0af8fa4f796482e3e',
+ 'info_dict': {
+ 'id': '004MsGEo3DdNxV',
+ 'ext': 'mp3',
+ 'title': '如果',
+ 'upload_date': '20050626',
+ 'creator': '李季美',
+ 'description': 'md5:46857d5ed62bc4ba84607a805dccf437',
+ 'thumbnail': 're:^https?://.*\.jpg$',
}
}]
if lrc_content:
lrc_content = lrc_content.replace('\\n', '\n')
+ thumbnail_url = None
+ albummid = self._search_regex(
+ [r'albummid:\'([0-9a-zA-Z]+)\'', r'"albummid":"([0-9a-zA-Z]+)"'],
+ detail_info_page, 'album mid', default=None)
+ if albummid:
+ thumbnail_url = "http://i.gtimg.cn/music/photo/mid_album_500/%s/%s/%s.jpg" \
+ % (albummid[-2:-1], albummid[-1], albummid)
+
guid = self.m_r_get_ruin()
vkey = self._download_json(
'preference': details['preference'],
'abr': details.get('abr'),
})
+ self._check_formats(formats, mid)
self._sort_formats(formats)
return {
'upload_date': publish_time,
'creator': singer,
'description': lrc_content,
+ 'thumbnail': thumbnail_url,
}
class QQMusicSingerIE(QQPlaylistBaseIE):
IE_NAME = 'qqmusic:singer'
+ IE_DESC = 'QQ音乐 - 歌手'
_VALID_URL = r'http://y.qq.com/#type=singer&mid=(?P<id>[0-9A-Za-z]+)'
_TEST = {
'url': 'http://y.qq.com/#type=singer&mid=001BLpXF2DyJe2',
class QQMusicAlbumIE(QQPlaylistBaseIE):
IE_NAME = 'qqmusic:album'
+ IE_DESC = 'QQ音乐 - 专辑'
_VALID_URL = r'http://y.qq.com/#type=album&mid=(?P<id>[0-9A-Za-z]+)'
- _TEST = {
- 'url': 'http://y.qq.com/#type=album&mid=000gXCTb2AhRR1&play=0',
+ _TESTS = [{
+ 'url': 'http://y.qq.com/#type=album&mid=000gXCTb2AhRR1',
'info_dict': {
'id': '000gXCTb2AhRR1',
'title': '我们都是这样长大的',
- 'description': 'md5:d216c55a2d4b3537fe4415b8767d74d6',
+ 'description': 'md5:179c5dce203a5931970d306aa9607ea6',
},
'playlist_count': 4,
- }
+ }, {
+ 'url': 'http://y.qq.com/#type=album&mid=002Y5a3b3AlCu3',
+ 'info_dict': {
+ 'id': '002Y5a3b3AlCu3',
+ 'title': '그리고...',
+ 'description': 'md5:a48823755615508a95080e81b51ba729',
+ },
+ 'playlist_count': 8,
+ }]
def _real_extract(self, url):
mid = self._match_id(url)
- album_page = self._download_webpage(
- self.qq_static_url('album', mid), mid, 'Download album page')
+ album = self._download_json(
+ 'http://i.y.qq.com/v8/fcg-bin/fcg_v8_album_info_cp.fcg?albummid=%s&format=json' % mid,
+ mid, 'Download album page')['data']
- entries = self.get_entries_from_page(album_page)
-
- album_name = self._html_search_regex(
- r"albumname\s*:\s*'([^']+)',", album_page, 'album name',
- default=None)
-
- album_detail = self._html_search_regex(
- r'<div class="album_detail close_detail">\s*<p>((?:[^<>]+(?:<br />)?)+)</p>',
- album_page, 'album details', default=None)
+ entries = [
+ self.url_result(
+ 'http://y.qq.com/#type=song&mid=' + song['songmid'], 'QQMusic', song['songmid']
+ ) for song in album['list']
+ ]
+ album_name = album.get('name')
+ album_detail = album.get('desc')
+ if album_detail is not None:
+ album_detail = album_detail.strip()
return self.playlist_result(entries, mid, album_name, album_detail)
class QQMusicToplistIE(QQPlaylistBaseIE):
IE_NAME = 'qqmusic:toplist'
+ IE_DESC = 'QQ音乐 - 排行榜'
_VALID_URL = r'http://y\.qq\.com/#type=toplist&p=(?P<id>(top|global)_[0-9]+)'
_TESTS = [{
list_name = topinfo.get('ListName')
list_description = topinfo.get('info')
return self.playlist_result(entries, list_id, list_name, list_description)
+
+
+class QQMusicPlaylistIE(QQPlaylistBaseIE):
+ IE_NAME = 'qqmusic:playlist'
+ IE_DESC = 'QQ音乐 - 歌单'
+ _VALID_URL = r'http://y\.qq\.com/#type=taoge&id=(?P<id>[0-9]+)'
+
+ _TEST = {
+ 'url': 'http://y.qq.com/#type=taoge&id=3462654915',
+ 'info_dict': {
+ 'id': '3462654915',
+ 'title': '韩国5月新歌精选下旬',
+ 'description': 'md5:d2c9d758a96b9888cf4fe82f603121d4',
+ },
+ 'playlist_count': 40,
+ }
+
+ def _real_extract(self, url):
+ list_id = self._match_id(url)
+
+ list_json = self._download_json(
+ 'http://i.y.qq.com/qzone-music/fcg-bin/fcg_ucc_getcdinfo_byids_cp.fcg?type=1&json=1&utf8=1&onlysong=0&disstid=%s'
+ % list_id, list_id, 'Download list page',
+ transform_source=strip_jsonp)['cdlist'][0]
+
+ entries = [
+ self.url_result(
+ 'http://y.qq.com/#type=song&mid=' + song['songmid'], 'QQMusic', song['songmid']
+ ) for song in list_json['songlist']
+ ]
+
+ list_name = list_json.get('dissname')
+ list_description = clean_html(unescapeHTML(list_json.get('desc')))
+ return self.playlist_result(entries, list_id, list_name, list_description)
'thumbnail': 're:^https?://.*\.(?:png|jpg|gif)$',
'view_count': int,
},
+ 'skip': 'Not accessible from Travis CI server',
}
def _real_extract(self, url):
}
}
+ _QUALITIES = [
+ ('mobile', 'mobile'),
+ ('web', 'SD'),
+ ('url', 'MD'),
+ ('high', 'HD'),
+ ]
+
def _real_extract(self, url):
video_id = self._match_id(url)
r'data-video="([^"]+)"', webpage, 'data video')),
video_id)
- video_url = data.get('downloadUrl') or data.get('url')
-
if data.get('provider').lower() == 'youtube':
+ video_url = data.get('downloadUrl') or data.get('url')
return self.url_result(video_url, 'Youtube')
+ formats = []
+ for key, format_id in self._QUALITIES:
+ format_url = data['sources'].get(key)
+ if format_url:
+ formats.append({
+ 'format_id': format_id,
+ 'url': format_url,
+ })
return {
'id': video_id,
- 'url': video_url,
+ 'formats': formats,
'title': data['title'],
'description': data.get('description') or data.get('subtitle'),
'thumbnail': data.get('thumbnail'),
IE_NAME = 'rtl.nl'
IE_DESC = 'rtl.nl and rtlxl.nl'
_VALID_URL = r'''(?x)
- https?://(www\.)?
+ https?://(?:www\.)?
(?:
rtlxl\.nl/\#!/[^/]+/|
- rtl\.nl/system/videoplayer/[^?#]+?/video_embed\.html\#uuid=
+ rtl\.nl/system/videoplayer/(?:[^/]+/)+(?:video_)?embed\.html\b.+?\buuid=
)
(?P<id>[0-9a-f-]+)'''
'upload_date': '20150215',
'description': 'Er zijn nieuwe beelden vrijgegeven die vlak na de aanslag in Kopenhagen zijn gemaakt. Op de video is goed te zien hoe omstanders zich bekommeren om één van de slachtoffers, terwijl de eerste agenten ter plaatse komen.',
}
+ }, {
+ # encrypted m3u8 streams, georestricted
+ 'url': 'http://www.rtlxl.nl/#!/afl-2-257632/52a74543-c504-4cde-8aa8-ec66fe8d68a7',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://www.rtl.nl/system/videoplayer/derden/embed.html#!/uuid=bb0353b0-d6a4-1dad-90e9-18fe75b8d1f0',
+ 'only_matching': True,
}]
def _real_extract(self, url):
uuid = self._match_id(url)
info = self._download_json(
- 'http://www.rtl.nl/system/s4m/vfd/version=2/uuid=%s/fmt=flash/' % uuid,
+ 'http://www.rtl.nl/system/s4m/vfd/version=2/uuid=%s/fmt=adaptive/' % uuid,
uuid)
material = info['material'][0]
subtitle = material['title'] or info['episodes'][0]['name']
description = material.get('synopsis') or info['episodes'][0]['synopsis']
+ meta = info.get('meta', {})
+
# Use unencrypted m3u8 streams (See https://github.com/rg3/youtube-dl/issues/4118)
- videopath = material['videopath'].replace('.f4m', '.m3u8')
- m3u8_url = 'http://manifest.us.rtl.nl' + videopath
+ # NB: nowadays, recent ffmpeg and avconv can handle these encrypted streams, so
+ # this adaptive -> flash workaround is not required in general, but it also
+ # allows bypassing georestriction therefore is retained for now.
+ videopath = material['videopath'].replace('/adaptive/', '/flash/')
+ m3u8_url = meta.get('videohost', 'http://manifest.us.rtl.nl') + videopath
formats = self._extract_m3u8_formats(m3u8_url, uuid, ext='mp4')
self._sort_formats(formats)
thumbnails = []
- meta = info.get('meta', {})
+
for p in ('poster_base_url', '"thumb_base_url"'):
if not meta.get(p):
continue
library/view/[^/]+|
api/v1/book
)/
- (?P<course_id>\d+)/
+ (?P<course_id>[^/]+)/
(?:chapter(?:-content)?/)?
(?P<part>part\d+)\.html
'''
}, {
'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
'only_matching': True,
+ }, {
+ # non-digits in course id
+ 'url': 'https://www.safaribooksonline.com/library/view/create-a-nodejs/100000006A0210/part00.html',
+ 'only_matching': True,
}]
def _real_extract(self, url):
IE_NAME = 'safari:course'
IE_DESC = 'safaribooksonline.com online courses'
- _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)/(?P<id>\d+)/?(?:[#?]|$)'
+ _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)/(?P<id>[^/]+)/?(?:[#?]|$)'
_TESTS = [{
'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
from __future__ import unicode_literals
-import re
import base64
from .common import InfoExtractor
raise ExtractorError(
'Video %s does not exist' % video_id, expected=True)
- download_form = dict(re.findall(
- r'<input type="hidden" name="([^"]+)" value="([^"]*)"', webpage))
+ download_form = self._form_hidden_inputs(webpage)
request = compat_urllib_request.Request(
url, compat_urllib_parse.urlencode(download_form))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
'thumbnail': 'http://frame4.loadup.ru/03/ed/57591.2.3.jpg',
},
},
- # video-password
+ # video-password, not approved by moderator
{
'url': 'http://smotri.com/video/view/?id=v1390466a13c',
'md5': 'f6331cef33cad65a0815ee482a54440b',
},
'skip': 'Video is not approved by moderator',
},
- # age limit + video-password
+ # video-password
+ {
+ 'url': 'http://smotri.com/video/view/?id=v6984858774#',
+ 'md5': 'f11e01d13ac676370fc3b95b9bda11b0',
+ 'info_dict': {
+ 'id': 'v6984858774',
+ 'ext': 'mp4',
+ 'title': 'Дача Солженицина ПАРОЛЬ 223322',
+ 'uploader': 'psavari1',
+ 'uploader_id': 'psavari1',
+ 'upload_date': '20081103',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ },
+ 'params': {
+ 'videopassword': '223322',
+ },
+ },
+ # age limit + video-password, not approved by moderator
{
'url': 'http://smotri.com/video/view/?id=v15408898bcf',
'md5': '91e909c9f0521adf5ee86fbe073aad70',
},
'skip': 'Video is not approved by moderator',
},
- # not approved by moderator, but available
+ # age limit + video-password
{
- 'url': 'http://smotri.com/video/view/?id=v28888533b73',
- 'md5': 'f44bc7adac90af518ef1ecf04893bb34',
+ 'url': 'http://smotri.com/video/view/?id=v7780025814',
+ 'md5': 'b4599b068422559374a59300c5337d72',
'info_dict': {
- 'id': 'v28888533b73',
+ 'id': 'v7780025814',
'ext': 'mp4',
- 'title': 'Russian Spies Killed By ISIL Child Soldier',
- 'uploader': 'Mopeder',
- 'uploader_id': 'mopeder',
- 'duration': 71,
- 'thumbnail': 'http://frame9.loadup.ru/d7/32/2888853.2.3.jpg',
- 'upload_date': '20150114',
+ 'title': 'Sexy Beach (пароль 123)',
+ 'uploader': 'вАся',
+ 'uploader_id': 'asya_prosto',
+ 'upload_date': '20081218',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'age_limit': 18,
+ },
+ 'params': {
+ 'videopassword': '123'
},
},
# swf player
'getvideoinfo': '1',
}
+ video_password = self._downloader.params.get('videopassword', None)
+ if video_password:
+ video_form['pass'] = hashlib.md5(video_password.encode('utf-8')).hexdigest()
+
request = compat_urllib_request.Request(
'http://smotri.com/video/view/url/bot/', compat_urllib_parse.urlencode(video_form))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
video_url = video.get('_vidURL') or video.get('_vidURL_mp4')
if not video_url:
- if video.get('_moderate_no') or not video.get('moderated'):
+ if video.get('_moderate_no'):
raise ExtractorError(
'Video %s has not been approved by moderator' % video_id, expected=True)
if video.get('error'):
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+ if video.get('_pass_protected') == 1:
+ msg = ('Invalid video password' if video_password
+ else 'This video is protected by a password, use the --video-password option')
+ raise ExtractorError(msg, expected=True)
+
title = video['title']
thumbnail = video['_imgURL']
upload_date = unified_strdate(video['added'])
--- /dev/null
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ ExtractorError,
+ clean_html,
+ determine_ext,
+ int_or_none,
+ js_to_json,
+ parse_duration,
+)
+
+
+class SnagFilmsEmbedIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:(?:www|embed)\.)?snagfilms\.com/embed/player\?.*\bfilmId=(?P<id>[\da-f-]{36})'
+ _TESTS = [{
+ 'url': 'http://embed.snagfilms.com/embed/player?filmId=74849a00-85a9-11e1-9660-123139220831&w=500',
+ 'md5': '2924e9215c6eff7a55ed35b72276bd93',
+ 'info_dict': {
+ 'id': '74849a00-85a9-11e1-9660-123139220831',
+ 'ext': 'mp4',
+ 'title': '#whilewewatch',
+ }
+ }, {
+ 'url': 'http://www.snagfilms.com/embed/player?filmId=0000014c-de2f-d5d6-abcf-ffef58af0017',
+ 'only_matching': True,
+ }]
+
+ @staticmethod
+ def _extract_url(webpage):
+ mobj = re.search(
+ r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:embed\.)?snagfilms\.com/embed/player.+?)\1',
+ webpage)
+ if mobj:
+ return mobj.group('url')
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, video_id)
+
+ if '>This film is not playable in your area.<' in webpage:
+ raise ExtractorError(
+ 'Film %s is not playable in your area.' % video_id, expected=True)
+
+ formats = []
+ for source in self._parse_json(js_to_json(self._search_regex(
+ r'(?s)sources:\s*(\[.+?\]),', webpage, 'json')), video_id):
+ file_ = source.get('file')
+ if not file_:
+ continue
+ type_ = source.get('type')
+ format_id = source.get('label')
+ ext = determine_ext(file_)
+ if any(_ == 'm3u8' for _ in (type_, ext)):
+ formats.extend(self._extract_m3u8_formats(
+ file_, video_id, 'mp4', m3u8_id='hls'))
+ else:
+ bitrate = int_or_none(self._search_regex(
+ r'(\d+)kbps', file_, 'bitrate', default=None))
+ height = int_or_none(self._search_regex(
+ r'^(\d+)[pP]$', format_id, 'height', default=None))
+ formats.append({
+ 'url': file_,
+ 'format_id': format_id,
+ 'tbr': bitrate,
+ 'height': height,
+ })
+ self._sort_formats(formats)
+
+ title = self._search_regex(
+ [r"title\s*:\s*'([^']+)'", r'<title>([^<]+)</title>'],
+ webpage, 'title')
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'formats': formats,
+ }
+
+
+class SnagFilmsIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?snagfilms\.com/(?:films/title|show)/(?P<id>[^?#]+)'
+ _TESTS = [{
+ 'url': 'http://www.snagfilms.com/films/title/lost_for_life',
+ 'md5': '19844f897b35af219773fd63bdec2942',
+ 'info_dict': {
+ 'id': '0000014c-de2f-d5d6-abcf-ffef58af0017',
+ 'display_id': 'lost_for_life',
+ 'ext': 'mp4',
+ 'title': 'Lost for Life',
+ 'description': 'md5:fbdacc8bb6b455e464aaf98bc02e1c82',
+ 'thumbnail': 're:^https?://.*\.jpg',
+ 'duration': 4489,
+ 'categories': ['Documentary', 'Crime', 'Award Winning', 'Festivals']
+ }
+ }, {
+ 'url': 'http://www.snagfilms.com/show/the_world_cut_project/india',
+ 'md5': 'e6292e5b837642bbda82d7f8bf3fbdfd',
+ 'info_dict': {
+ 'id': '00000145-d75c-d96e-a9c7-ff5c67b20000',
+ 'display_id': 'the_world_cut_project/india',
+ 'ext': 'mp4',
+ 'title': 'India',
+ 'description': 'md5:5c168c5a8f4719c146aad2e0dfac6f5f',
+ 'thumbnail': 're:^https?://.*\.jpg',
+ 'duration': 979,
+ 'categories': ['Documentary', 'Sports', 'Politics']
+ }
+ }, {
+ # Film is not playable in your area.
+ 'url': 'http://www.snagfilms.com/films/title/inside_mecca',
+ 'only_matching': True,
+ }, {
+ # Film is not available.
+ 'url': 'http://www.snagfilms.com/show/augie_alone/flirting',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ display_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, display_id)
+
+ if ">Sorry, the Film you're looking for is not available.<" in webpage:
+ raise ExtractorError(
+ 'Film %s is not available.' % display_id, expected=True)
+
+ film_id = self._search_regex(r'filmId=([\da-f-]{36})"', webpage, 'film id')
+
+ snag = self._parse_json(
+ self._search_regex(
+ 'Snag\.page\.data\s*=\s*(\[.+?\]);', webpage, 'snag'),
+ display_id)
+
+ for item in snag:
+ if item.get('data', {}).get('film', {}).get('id') == film_id:
+ data = item['data']['film']
+ title = data['title']
+ description = clean_html(data.get('synopsis'))
+ thumbnail = data.get('image')
+ duration = int_or_none(data.get('duration') or data.get('runtime'))
+ categories = [
+ category['title'] for category in data.get('categories', [])
+ if category.get('title')]
+ break
+ else:
+ title = self._search_regex(
+ r'itemprop="title">([^<]+)<', webpage, 'title')
+ description = self._html_search_regex(
+ r'(?s)<div itemprop="description" class="film-synopsis-inner ">(.+?)</div>',
+ webpage, 'description', default=None) or self._og_search_description(webpage)
+ thumbnail = self._og_search_thumbnail(webpage)
+ duration = parse_duration(self._search_regex(
+ r'<span itemprop="duration" class="film-duration strong">([^<]+)<',
+ webpage, 'duration', fatal=False))
+ categories = re.findall(r'<a href="/movies/[^"]+">([^<]+)</a>', webpage)
+
+ return {
+ '_type': 'url_transparent',
+ 'url': 'http://embed.snagfilms.com/embed/player?filmId=%s' % film_id,
+ 'id': film_id,
+ 'display_id': display_id,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'duration': duration,
+ 'categories': categories,
+ }
from .common import InfoExtractor
from ..compat import (
compat_str,
- compat_urllib_request
+ compat_urllib_request,
+ compat_urllib_parse,
+)
+from ..utils import (
+ ExtractorError,
)
-from ..utils import ExtractorError
class SohuIE(InfoExtractor):
'skip': 'On available in China',
}, {
'url': 'http://tv.sohu.com/20150305/n409385080.shtml',
- 'md5': 'ac9a5d322b4bf9ae184d53e4711e4f1a',
+ 'md5': '699060e75cf58858dd47fb9c03c42cfb',
'info_dict': {
'id': '409385080',
'ext': 'mp4',
}
}, {
'url': 'http://my.tv.sohu.com/us/232799889/78693464.shtml',
- 'md5': '49308ff6dafde5ece51137d04aec311e',
+ 'md5': '9bf34be48f2f4dadcb226c74127e203c',
'info_dict': {
'id': '78693464',
'ext': 'mp4',
'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
},
'playlist': [{
- 'md5': '492923eac023ba2f13ff69617c32754a',
+ 'md5': 'bdbfb8f39924725e6589c146bc1883ad',
'info_dict': {
'id': '78910339_part1',
'ext': 'mp4',
'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
}
}, {
- 'md5': 'de604848c0e8e9c4a4dde7e1347c0637',
+ 'md5': '3e1f46aaeb95354fd10e7fca9fc1804e',
'info_dict': {
'id': '78910339_part2',
'ext': 'mp4',
'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
}
}, {
- 'md5': '93584716ee0657c0b205b8aa3d27aa13',
+ 'md5': '8407e634175fdac706766481b9443450',
'info_dict': {
'id': '78910339_part3',
'ext': 'mp4',
for i in range(part_count):
formats = []
for format_id, format_data in formats_json.items():
+ allot = format_data['allot']
+
data = format_data['data']
+ clips_url = data['clipsURL']
+ su = data['su']
- # URLs starts with http://newflv.sohu.ccgslb.net/ is not usable
- # so retry until got a working URL
video_url = 'newflv.sohu.ccgslb.net'
+ cdnId = None
retries = 0
- while 'newflv.sohu.ccgslb.net' in video_url and retries < 5:
- download_note = 'Download information from CDN gateway for format ' + format_id
+
+ while 'newflv.sohu.ccgslb.net' in video_url:
+ params = {
+ 'prot': 9,
+ 'file': clips_url[i],
+ 'new': su[i],
+ 'prod': 'flash',
+ }
+
+ if cdnId is not None:
+ params['idc'] = cdnId
+
+ download_note = 'Downloading %s video URL part %d of %d' % (
+ format_id, i + 1, part_count)
+
if retries > 0:
download_note += ' (retry #%d)' % retries
+ part_info = self._parse_json(self._download_webpage(
+ 'http://%s/?%s' % (allot, compat_urllib_parse.urlencode(params)),
+ video_id, download_note), video_id)
+
+ video_url = part_info['url']
+ cdnId = part_info.get('nid')
+
retries += 1
- cdn_info = self._download_json(
- 'http://data.vod.itc.cn/cdnList?new=' + data['su'][i],
- video_id, download_note)
- video_url = cdn_info['url']
+ if retries > 5:
+ raise ExtractorError('Failed to get video URL')
formats.append({
'url': video_url,
_VALID_URL = r'''(?x)^(?:https?://)?
(?:(?:(?:www\.|m\.)?soundcloud\.com/
(?P<uploader>[\w\d-]+)/
- (?!sets/|likes/?(?:$|[?#]))
+ (?!sets/|(?:likes|tracks)/?(?:$|[?#]))
(?P<title>[\w\d-]+)/?
(?P<token>[^?]+?)?(?:[?].*)?$)
|(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+)
'title': 'The Royal Concept',
},
'playlist_mincount': 1,
+ }, {
+ 'url': 'https://soundcloud.com/the-akashic-chronicler/tracks',
+ 'only_matching': True,
}]
def _real_extract(self, url):
'description': 'Crazy Bitch X rated music video.',
'uploader': 'oreusz',
'uploader_id': '124697',
- 'upload_date': '20070508',
+ 'upload_date': '20070507',
'age_limit': 18,
}
}
title = self._html_search_regex(
r'<h1>([^<]+)', webpage, 'title')
description = self._html_search_regex(
- r'<div\s+id="descriptionContent">([^<]+)<',
+ r'(?s)<div\s+id="descriptionContent">(.+?)</div>',
webpage, 'description', fatal=False)
thumbnail = self._html_search_regex(
r'playerData\.screenShot\s*=\s*["\']([^"\']+)["\']',
r'<div id="viewsCounter"><span>([\d,\.]+)</span> views</div>',
webpage, 'view count', fatal=False))
comment_count = str_to_int(self._html_search_regex(
- r'Comments<span[^>]+>\s*\(([\d,\.]+)\)</span>',
+ r'<span\s+id="spCommentCount"[^>]*>([\d,\.]+)</span>',
webpage, 'comment count', fatal=False))
video_urls = list(map(
compat_urllib_parse.unquote,
- re.findall(r'playerData\.cdnPath[0-9]{3,}\s*=\s*["\']([^"\']+)["\']', webpage)))
+ re.findall(r'playerData\.cdnPath[0-9]{3,}\s*=\s*(?:encodeURIComponent\()?["\']([^"\']+)["\']', webpage)))
if webpage.find('flashvars\.encrypted = "true"') != -1:
password = self._search_regex(
r'flashvars\.video_title = "([^"]+)',
'rtmp_live': True,
})
elif determine_ext(endpoint) == 'm3u8':
- formats.extend(self._extract_m3u8_formats(
+ m3u8_formats = self._extract_m3u8_formats(
endpoint.replace('[video]', play_path),
video_id, 'm4v',
preference=1, # Prefer hls since it allows to workaround georestriction
- m3u8_id='hls'))
+ m3u8_id='hls', fatal=False)
+ if m3u8_formats is not False:
+ formats.extend(m3u8_formats)
else:
formats.append({
'url': endpoint,
# coding: utf-8
from __future__ import unicode_literals
-import json
-import re
-
from .common import InfoExtractor
from ..utils import unified_strdate
song
)/(?P<id>[A-Za-z0-9]+)/?$'''
_SONG_URL_TEMPLATE = 'http://thesixtyone.com/s/{0:}'
- _SONG_FILE_URL_TEMPLATE = 'http://{audio_server:}.thesixtyone.com/thesixtyone_production/audio/{0:}_stream'
+ _SONG_FILE_URL_TEMPLATE = 'http://{audio_server:}/thesixtyone_production/audio/{0:}_stream'
_THUMBNAIL_URL_TEMPLATE = '{photo_base_url:}_desktop'
_TESTS = [
{
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- song_id = mobj.group('id')
+ song_id = self._match_id(url)
webpage = self._download_webpage(
self._SONG_URL_TEMPLATE.format(song_id), song_id)
- song_data = json.loads(self._search_regex(
- r'"%s":\s(\{.*?\})' % song_id, webpage, 'song_data'))
+ song_data = self._parse_json(self._search_regex(
+ r'"%s":\s(\{.*?\})' % song_id, webpage, 'song_data'), song_id)
+
+ if self._search_regex(r'(t61\.s3_audio_load\s*=\s*1\.0;)', webpage, 's3_audio_load marker', default=None):
+ song_data['audio_server'] = 's3.amazonaws.com'
+ else:
+ song_data['audio_server'] = song_data['audio_server'] + '.thesixtyone.com'
+
keys = [self._DECODE_MAP.get(s, s) for s in song_data['key']]
url = self._SONG_FILE_URL_TEMPLATE.format(
"".join(reversed(keys)), **song_data)
--- /dev/null
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class ThisAmericanLifeIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?thisamericanlife\.org/(?:radio-archives/episode/|play_full\.php\?play=)(?P<id>\d+)'
+ _TESTS = [{
+ 'url': 'http://www.thisamericanlife.org/radio-archives/episode/487/harper-high-school-part-one',
+ 'md5': '8f7d2da8926298fdfca2ee37764c11ce',
+ 'info_dict': {
+ 'id': '487',
+ 'ext': 'm4a',
+ 'title': '487: Harper High School, Part One',
+ 'description': 'md5:ee40bdf3fb96174a9027f76dbecea655',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ },
+ }, {
+ 'url': 'http://www.thisamericanlife.org/play_full.php?play=487',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(
+ 'http://www.thisamericanlife.org/radio-archives/episode/%s' % video_id, video_id)
+
+ return {
+ 'id': video_id,
+ 'url': 'http://stream.thisamericanlife.org/{0}/stream/{0}_64k.m3u8'.format(video_id),
+ 'protocol': 'm3u8_native',
+ 'ext': 'm4a',
+ 'acodec': 'aac',
+ 'vcodec': 'none',
+ 'abr': 64,
+ 'title': self._html_search_meta(r'twitter:title', webpage, 'title', fatal=True),
+ 'description': self._html_search_meta(r'description', webpage, 'description'),
+ 'thumbnail': self._og_search_thumbnail(webpage),
+ }
import re
from .common import InfoExtractor
+from ..compat import compat_str
from ..utils import (
- parse_duration,
fix_xml_ampersands,
+ float_or_none,
+ int_or_none,
+ parse_duration,
+ str_to_int,
+ xpath_text,
)
-class TNAFlixIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/[^/]+/(?P<display_id>[^/]+)/video(?P<id>\d+)'
-
- _TITLE_REGEX = r'<title>(.+?) - TNAFlix Porn Videos</title>'
- _DESCRIPTION_REGEX = r'<h3 itemprop="description">([^<]+)</h3>'
- _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"'
-
- _TESTS = [
- {
- 'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878',
- 'md5': 'ecf3498417d09216374fc5907f9c6ec0',
- 'info_dict': {
- 'id': '553878',
- 'display_id': 'Carmella-Decesare-striptease',
- 'ext': 'mp4',
- 'title': 'Carmella Decesare - striptease',
- 'description': '',
- 'thumbnail': 're:https?://.*\.jpg$',
- 'duration': 91,
- 'age_limit': 18,
- }
- },
- {
- 'url': 'https://www.tnaflix.com/amateur-porn/bunzHD-Ms.Donk/video358632',
- 'only_matching': True,
- }
+class TNAFlixNetworkBaseIE(InfoExtractor):
+ # May be overridden in descendants if necessary
+ _CONFIG_REGEX = [
+ r'flashvars\.config\s*=\s*escape\("([^"]+)"',
+ r'<input[^>]+name="config\d?" value="([^"]+)"',
]
+ _TITLE_REGEX = r'<input[^>]+name="title" value="([^"]+)"'
+ _DESCRIPTION_REGEX = r'<input[^>]+name="description" value="([^"]+)"'
+ _UPLOADER_REGEX = r'<input[^>]+name="username" value="([^"]+)"'
+ _VIEW_COUNT_REGEX = None
+ _COMMENT_COUNT_REGEX = None
+ _AVERAGE_RATING_REGEX = None
+ _CATEGORIES_REGEX = r'<li[^>]*>\s*<span[^>]+class="infoTitle"[^>]*>Categories:</span>\s*<span[^>]+class="listView"[^>]*>(.+?)</span>\s*</li>'
+
+ def _extract_thumbnails(self, flix_xml):
+
+ def get_child(elem, names):
+ for name in names:
+ child = elem.find(name)
+ if child is not None:
+ return child
+
+ timeline = get_child(flix_xml, ['timeline', 'rolloverBarImage'])
+ if timeline is None:
+ return
+
+ pattern_el = get_child(timeline, ['imagePattern', 'pattern'])
+ if pattern_el is None or not pattern_el.text:
+ return
+
+ first_el = get_child(timeline, ['imageFirst', 'first'])
+ last_el = get_child(timeline, ['imageLast', 'last'])
+ if first_el is None or last_el is None:
+ return
+
+ first_text = first_el.text
+ last_text = last_el.text
+ if not first_text.isdigit() or not last_text.isdigit():
+ return
+
+ first = int(first_text)
+ last = int(last_text)
+ if first > last:
+ return
+
+ width = int_or_none(xpath_text(timeline, './imageWidth', 'thumbnail width'))
+ height = int_or_none(xpath_text(timeline, './imageHeight', 'thumbnail height'))
+
+ return [{
+ 'url': self._proto_relative_url(pattern_el.text.replace('#', compat_str(i)), 'http:'),
+ 'width': width,
+ 'height': height,
+ } for i in range(first, last + 1)]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
webpage = self._download_webpage(url, display_id)
- title = self._html_search_regex(
- self._TITLE_REGEX, webpage, 'title') if self._TITLE_REGEX else self._og_search_title(webpage)
- description = self._html_search_regex(
- self._DESCRIPTION_REGEX, webpage, 'description', fatal=False, default='')
-
- age_limit = self._rta_search(webpage)
-
- duration = parse_duration(self._html_search_meta(
- 'duration', webpage, 'duration', default=None))
-
cfg_url = self._proto_relative_url(self._html_search_regex(
self._CONFIG_REGEX, webpage, 'flashvars.config'), 'http:')
cfg_xml = self._download_xml(
- cfg_url, display_id, note='Downloading metadata',
+ cfg_url, display_id, 'Downloading metadata',
transform_source=fix_xml_ampersands)
- thumbnail = self._proto_relative_url(
- cfg_xml.find('./startThumb').text, 'http:')
-
formats = []
+
+ def extract_video_url(vl):
+ return re.sub('speed=\d+', 'speed=', vl.text)
+
+ video_link = cfg_xml.find('./videoLink')
+ if video_link is not None:
+ formats.append({
+ 'url': extract_video_url(video_link),
+ 'ext': xpath_text(cfg_xml, './videoConfig/type', 'type', default='flv'),
+ })
+
for item in cfg_xml.findall('./quality/item'):
- video_url = re.sub('speed=\d+', 'speed=', item.find('videoLink').text)
- format_id = item.find('res').text
- fmt = {
- 'url': self._proto_relative_url(video_url, 'http:'),
+ video_link = item.find('./videoLink')
+ if video_link is None:
+ continue
+ res = item.find('res')
+ format_id = None if res is None else res.text
+ height = int_or_none(self._search_regex(
+ r'^(\d+)[pP]', format_id, 'height', default=None))
+ formats.append({
+ 'url': self._proto_relative_url(extract_video_url(video_link), 'http:'),
'format_id': format_id,
- }
- m = re.search(r'^(\d+)', format_id)
- if m:
- fmt['height'] = int(m.group(1))
- formats.append(fmt)
+ 'height': height,
+ })
+
self._sort_formats(formats)
+ thumbnail = self._proto_relative_url(
+ xpath_text(cfg_xml, './startThumb', 'thumbnail'), 'http:')
+ thumbnails = self._extract_thumbnails(cfg_xml)
+
+ title = self._html_search_regex(
+ self._TITLE_REGEX, webpage, 'title') if self._TITLE_REGEX else self._og_search_title(webpage)
+
+ age_limit = self._rta_search(webpage)
+
+ duration = parse_duration(self._html_search_meta(
+ 'duration', webpage, 'duration', default=None))
+
+ def extract_field(pattern, name):
+ return self._html_search_regex(pattern, webpage, name, default=None) if pattern else None
+
+ description = extract_field(self._DESCRIPTION_REGEX, 'description')
+ uploader = extract_field(self._UPLOADER_REGEX, 'uploader')
+ view_count = str_to_int(extract_field(self._VIEW_COUNT_REGEX, 'view count'))
+ comment_count = str_to_int(extract_field(self._COMMENT_COUNT_REGEX, 'comment count'))
+ average_rating = float_or_none(extract_field(self._AVERAGE_RATING_REGEX, 'average rating'))
+
+ categories_str = extract_field(self._CATEGORIES_REGEX, 'categories')
+ categories = categories_str.split(', ') if categories_str is not None else []
+
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
+ 'thumbnails': thumbnails,
'duration': duration,
'age_limit': age_limit,
+ 'uploader': uploader,
+ 'view_count': view_count,
+ 'comment_count': comment_count,
+ 'average_rating': average_rating,
+ 'categories': categories,
'formats': formats,
}
+
+
+class TNAFlixIE(TNAFlixNetworkBaseIE):
+ _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/[^/]+/(?P<display_id>[^/]+)/video(?P<id>\d+)'
+
+ _TITLE_REGEX = r'<title>(.+?) - TNAFlix Porn Videos</title>'
+ _DESCRIPTION_REGEX = r'<h3 itemprop="description">([^<]+)</h3>'
+ _UPLOADER_REGEX = r'(?s)<span[^>]+class="infoTitle"[^>]*>Uploaded By:</span>(.+?)<div'
+
+ _TESTS = [{
+ # anonymous uploader, no categories
+ 'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878',
+ 'md5': 'ecf3498417d09216374fc5907f9c6ec0',
+ 'info_dict': {
+ 'id': '553878',
+ 'display_id': 'Carmella-Decesare-striptease',
+ 'ext': 'mp4',
+ 'title': 'Carmella Decesare - striptease',
+ 'thumbnail': 're:https?://.*\.jpg$',
+ 'duration': 91,
+ 'age_limit': 18,
+ 'uploader': 'Anonymous',
+ 'categories': [],
+ }
+ }, {
+ # non-anonymous uploader, categories
+ 'url': 'https://www.tnaflix.com/teen-porn/Educational-xxx-video/video6538',
+ 'md5': '0f5d4d490dbfd117b8607054248a07c0',
+ 'info_dict': {
+ 'id': '6538',
+ 'display_id': 'Educational-xxx-video',
+ 'ext': 'mp4',
+ 'title': 'Educational xxx video',
+ 'description': 'md5:b4fab8f88a8621c8fabd361a173fe5b8',
+ 'thumbnail': 're:https?://.*\.jpg$',
+ 'duration': 164,
+ 'age_limit': 18,
+ 'uploader': 'bobwhite39',
+ 'categories': ['Amateur Porn', 'Squirting Videos', 'Teen Girls 18+'],
+ }
+ }, {
+ 'url': 'https://www.tnaflix.com/amateur-porn/bunzHD-Ms.Donk/video358632',
+ 'only_matching': True,
+ }]
+
+
+class EMPFlixIE(TNAFlixNetworkBaseIE):
+ _VALID_URL = r'https?://(?:www\.)?empflix\.com/videos/(?P<display_id>.+?)-(?P<id>[0-9]+)\.html'
+
+ _UPLOADER_REGEX = r'<span[^>]+class="infoTitle"[^>]*>Uploaded By:</span>(.+?)</li>'
+
+ _TESTS = [{
+ 'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
+ 'md5': 'b1bc15b6412d33902d6e5952035fcabc',
+ 'info_dict': {
+ 'id': '33051',
+ 'display_id': 'Amateur-Finger-Fuck',
+ 'ext': 'mp4',
+ 'title': 'Amateur Finger Fuck',
+ 'description': 'Amateur solo finger fucking.',
+ 'thumbnail': 're:https?://.*\.jpg$',
+ 'duration': 83,
+ 'age_limit': 18,
+ 'uploader': 'cwbike',
+ 'categories': ['Amateur', 'Anal', 'Fisting', 'Home made', 'Solo'],
+ }
+ }, {
+ 'url': 'http://www.empflix.com/videos/[AROMA][ARMD-718]-Aoi-Yoshino-Sawa-25826.html',
+ 'only_matching': True,
+ }]
+
+
+class MovieFapIE(TNAFlixNetworkBaseIE):
+ _VALID_URL = r'https?://(?:www\.)?moviefap\.com/videos/(?P<id>[0-9a-f]+)/(?P<display_id>[^/]+)\.html'
+
+ _VIEW_COUNT_REGEX = r'<br>Views\s*<strong>([\d,.]+)</strong>'
+ _COMMENT_COUNT_REGEX = r'<span[^>]+id="comCount"[^>]*>([\d,.]+)</span>'
+ _AVERAGE_RATING_REGEX = r'Current Rating\s*<br>\s*<strong>([\d.]+)</strong>'
+ _CATEGORIES_REGEX = r'(?s)<div[^>]+id="vid_info"[^>]*>\s*<div[^>]*>.+?</div>(.*?)<br>'
+
+ _TESTS = [{
+ # normal, multi-format video
+ 'url': 'http://www.moviefap.com/videos/be9867c9416c19f54a4a/experienced-milf-amazing-handjob.html',
+ 'md5': '26624b4e2523051b550067d547615906',
+ 'info_dict': {
+ 'id': 'be9867c9416c19f54a4a',
+ 'display_id': 'experienced-milf-amazing-handjob',
+ 'ext': 'mp4',
+ 'title': 'Experienced MILF Amazing Handjob',
+ 'description': 'Experienced MILF giving an Amazing Handjob',
+ 'thumbnail': 're:https?://.*\.jpg$',
+ 'age_limit': 18,
+ 'uploader': 'darvinfred06',
+ 'view_count': int,
+ 'comment_count': int,
+ 'average_rating': float,
+ 'categories': ['Amateur', 'Masturbation', 'Mature', 'Flashing'],
+ }
+ }, {
+ # quirky single-format case where the extension is given as fid, but the video is really an flv
+ 'url': 'http://www.moviefap.com/videos/e5da0d3edce5404418f5/jeune-couple-russe.html',
+ 'md5': 'fa56683e291fc80635907168a743c9ad',
+ 'info_dict': {
+ 'id': 'e5da0d3edce5404418f5',
+ 'display_id': 'jeune-couple-russe',
+ 'ext': 'flv',
+ 'title': 'Jeune Couple Russe',
+ 'description': 'Amateur',
+ 'thumbnail': 're:https?://.*\.jpg$',
+ 'age_limit': 18,
+ 'uploader': 'whiskeyjar',
+ 'view_count': int,
+ 'comment_count': int,
+ 'average_rating': float,
+ 'categories': ['Amateur', 'Teen'],
+ }
+ }]
webpage = self._download_webpage(req, display_id)
flashvars = json.loads(self._html_search_regex(
- r'flashvars\s*=\s*({.+?})', webpage, 'flashvars'))
+ r'flashvars\s*=\s*({.+?});\r?\n', webpage, 'flashvars'))
video_url = flashvars['video_url']
if flashvars.get('encrypted') is True:
import re
from .common import InfoExtractor
+from .pornhub import PornHubIE
+from .vimeo import VimeoIE
class TumblrIE(InfoExtractor):
'timestamp': 1430931613,
},
'add_ie': ['Vidme'],
+ }, {
+ 'url': 'http://camdamage.tumblr.com/post/98846056295/',
+ 'md5': 'a9e0c8371ea1ca306d6554e3fecf50b6',
+ 'info_dict': {
+ 'id': '105463834',
+ 'ext': 'mp4',
+ 'title': 'Cam Damage-HD 720p',
+ 'uploader': 'John Moyer',
+ 'uploader_id': 'user32021558',
+ },
+ 'add_ie': ['Vimeo'],
}]
def _real_extract(self, url):
if vid_me_embed_url is not None:
return self.url_result(vid_me_embed_url, 'Vidme')
+ pornhub_url = PornHubIE._extract_url(webpage)
+ if pornhub_url:
+ return self.url_result(pornhub_url, 'PornHub')
+
+ vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
+ if vimeo_url:
+ return self.url_result(vimeo_url, 'Vimeo')
+
iframe_url = self._search_regex(
r'src=\'(https?://www\.tumblr\.com/video/[^\']+)\'',
webpage, 'iframe url')
--- /dev/null
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ clean_html,
+ int_or_none,
+)
+
+
+class TVCIE(InfoExtractor):
+ _VALID_URL = r'http://(?:www\.)?tvc\.ru/video/iframe/id/(?P<id>\d+)'
+ _TEST = {
+ 'url': 'http://www.tvc.ru/video/iframe/id/74622/isPlay/false/id_stat/channel/?acc_video_id=/channel/brand/id/17/show/episodes/episode_id/39702',
+ 'md5': 'bbc5ff531d1e90e856f60fc4b3afd708',
+ 'info_dict': {
+ 'id': '74622',
+ 'ext': 'mp4',
+ 'title': 'События. "События". Эфир от 22.05.2015 14:30',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 1122,
+ },
+ }
+
+ @classmethod
+ def _extract_url(cls, webpage):
+ mobj = re.search(
+ r'<iframe[^>]+?src=(["\'])(?P<url>(?:http:)?//(?:www\.)?tvc\.ru/video/iframe/id/[^"]+)\1', webpage)
+ if mobj:
+ return mobj.group('url')
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ video = self._download_json(
+ 'http://www.tvc.ru/video/json/id/%s' % video_id, video_id)
+
+ formats = []
+ for info in video.get('path', {}).get('quality', []):
+ video_url = info.get('url')
+ if not video_url:
+ continue
+ format_id = self._search_regex(
+ r'cdnvideo/([^/]+?)(?:-[^/]+?)?/', video_url,
+ 'format id', default=None)
+ formats.append({
+ 'url': video_url,
+ 'format_id': format_id,
+ 'width': int_or_none(info.get('width')),
+ 'height': int_or_none(info.get('height')),
+ 'tbr': int_or_none(info.get('bitrate')),
+ })
+ self._sort_formats(formats)
+
+ return {
+ 'id': video_id,
+ 'title': video['title'],
+ 'thumbnail': video.get('picture'),
+ 'duration': int_or_none(video.get('duration')),
+ 'formats': formats,
+ }
+
+
+class TVCArticleIE(InfoExtractor):
+ _VALID_URL = r'http://(?:www\.)?tvc\.ru/(?!video/iframe/id/)(?P<id>[^?#]+)'
+ _TESTS = [{
+ 'url': 'http://www.tvc.ru/channel/brand/id/29/show/episodes/episode_id/39702/',
+ 'info_dict': {
+ 'id': '74622',
+ 'ext': 'mp4',
+ 'title': 'События. "События". Эфир от 22.05.2015 14:30',
+ 'description': 'md5:ad7aa7db22903f983e687b8a3e98c6dd',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 1122,
+ },
+ }, {
+ 'url': 'http://www.tvc.ru/news/show/id/69944',
+ 'info_dict': {
+ 'id': '75399',
+ 'ext': 'mp4',
+ 'title': 'Эксперты: в столице встал вопрос о максимально безопасных остановках',
+ 'description': 'md5:f2098f71e21f309e89f69b525fd9846e',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 278,
+ },
+ }, {
+ 'url': 'http://www.tvc.ru/channel/brand/id/47/show/episodes#',
+ 'info_dict': {
+ 'id': '2185',
+ 'ext': 'mp4',
+ 'title': 'Ещё не поздно. Эфир от 03.08.2013',
+ 'description': 'md5:51fae9f3f8cfe67abce014e428e5b027',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 3316,
+ },
+ }]
+
+ def _real_extract(self, url):
+ webpage = self._download_webpage(url, self._match_id(url))
+ return {
+ '_type': 'url_transparent',
+ 'ie_key': 'TVC',
+ 'url': self._og_search_video_url(webpage),
+ 'title': clean_html(self._og_search_title(webpage)),
+ 'description': clean_html(self._og_search_description(webpage)),
+ 'thumbnail': self._og_search_thumbnail(webpage),
+ }
viasat4play\.no/programmer|
tv6play\.no/programmer|
tv3play\.dk/programmer|
+ play\.novatv\.bg/programi
)/[^/]+/(?P<id>\d+)
'''
_TESTS = [
'skip_download': True,
},
},
+ {
+ 'url': 'http://play.novatv.bg/programi/zdravei-bulgariya/624952?autostart=true',
+ 'info_dict': {
+ 'id': '624952',
+ 'ext': 'flv',
+ 'title': 'Здравей, България (12.06.2015 г.) ',
+ 'description': 'md5:99f3700451ac5bb71a260268b8daefd7',
+ 'duration': 8838,
+ 'timestamp': 1434100372,
+ 'upload_date': '20150612',
+ },
+ 'params': {
+ # rtmp download
+ 'skip_download': True,
+ },
+ },
]
def _real_extract(self, url):
_API_BASE = 'https://api.twitch.tv'
_USHER_BASE = 'http://usher.twitch.tv'
- _LOGIN_URL = 'https://secure.twitch.tv/user/login'
- _LOGIN_POST_URL = 'https://secure-login.twitch.tv/login'
+ _LOGIN_URL = 'https://secure.twitch.tv/login'
+ _LOGIN_POST_URL = 'https://passport.twitch.tv/authorize'
_NETRC_MACHINE = 'twitch'
def _handle_error(self, response):
login_page = self._download_webpage(
self._LOGIN_URL, None, 'Downloading login page')
- authenticity_token = self._search_regex(
- r'<input name="authenticity_token" type="hidden" value="([^"]+)"',
- login_page, 'authenticity token')
-
- login_form = {
- 'utf8': '✓'.encode('utf-8'),
- 'authenticity_token': authenticity_token,
- 'redirect_on_login': '',
- 'embed_form': 'false',
- 'mp_source_action': 'login-button',
- 'follow': '',
- 'login': username,
- 'password': password,
- }
+ login_form = self._form_hidden_inputs(login_page)
+
+ login_form.update({
+ 'login': username.encode('utf-8'),
+ 'password': password.encode('utf-8'),
+ })
request = compat_urllib_request.Request(
self._LOGIN_POST_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
response = self._download_webpage(
request, None, 'Logging in as %s' % username)
- m = re.search(
- r"id=([\"'])login_error_message\1[^>]*>(?P<msg>[^<]+)", response)
- if m:
+ error_message = self._search_regex(
+ r'<div[^>]+class="subwindow_notice"[^>]*>([^<]+)</div>',
+ response, 'error message', default=None)
+ if error_message:
raise ExtractorError(
- 'Unable to login: %s' % m.group('msg').strip(), expected=True)
+ 'Unable to login. Twitch said: %s' % error_message, expected=True)
+
+ if '>Reset your password<' in response:
+ self.report_warning('Twitch asks you to reset your password, go to https://secure.twitch.tv/reset/submit')
def _prefer_source(self, formats):
try:
_ITEM_SHORTCUT = 'v'
_TEST = {
- 'url': 'http://www.twitch.tv/ksptv/v/3622000',
+ 'url': 'http://www.twitch.tv/riotgames/v/6528877',
'info_dict': {
- 'id': 'v3622000',
+ 'id': 'v6528877',
'ext': 'mp4',
- 'title': '''KSPTV: Squadcast: "Everyone's on vacation so here's Dahud" Edition!''',
+ 'title': 'LCK Summer Split - Week 6 Day 1',
'thumbnail': 're:^https?://.*\.jpg$',
- 'duration': 6951,
- 'timestamp': 1419028564,
- 'upload_date': '20141219',
- 'uploader': 'KSPTV',
- 'uploader_id': 'ksptv',
+ 'duration': 17208,
+ 'timestamp': 1435131709,
+ 'upload_date': '20150624',
+ 'uploader': 'Riot Games',
+ 'uploader_id': 'riotgames',
'view_count': int,
},
'params': {
'%s/api/vods/%s/access_token' % (self._API_BASE, item_id), item_id,
'Downloading %s access token' % self._ITEM_TYPE)
formats = self._extract_m3u8_formats(
- '%s/vod/%s?nauth=%s&nauthsig=%s'
+ '%s/vod/%s?nauth=%s&nauthsig=%s&allow_source=true'
% (self._USHER_BASE, item_id, access_token['token'], access_token['sig']),
item_id, 'mp4')
self._prefer_source(formats)
--- /dev/null
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_request
+from ..utils import (
+ float_or_none,
+ unescapeHTML,
+)
+
+
+class TwitterCardIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?twitter\.com/i/cards/tfw/v1/(?P<id>\d+)'
+ _TEST = {
+ 'url': 'https://twitter.com/i/cards/tfw/v1/560070183650213889',
+ 'md5': 'a74f50b310c83170319ba16de6955192',
+ 'info_dict': {
+ 'id': '560070183650213889',
+ 'ext': 'mp4',
+ 'title': 'TwitterCard',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 30.033,
+ },
+ }
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ # Different formats served for different User-Agents
+ USER_AGENTS = [
+ 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/20.0 (Chrome)', # mp4
+ 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0', # webm
+ ]
+
+ config = None
+ formats = []
+ for user_agent in USER_AGENTS:
+ request = compat_urllib_request.Request(url)
+ request.add_header('User-Agent', user_agent)
+ webpage = self._download_webpage(request, video_id)
+
+ config = self._parse_json(
+ unescapeHTML(self._search_regex(
+ r'data-player-config="([^"]+)"', webpage, 'data player config')),
+ video_id)
+
+ video_url = config['playlist'][0]['source']
+
+ f = {
+ 'url': video_url,
+ }
+
+ m = re.search(r'/(?P<width>\d+)x(?P<height>\d+)/', video_url)
+ if m:
+ f.update({
+ 'width': int(m.group('width')),
+ 'height': int(m.group('height')),
+ })
+ formats.append(f)
+ self._sort_formats(formats)
+
+ thumbnail = config.get('posterImageUrl')
+ duration = float_or_none(config.get('duration'))
+
+ return {
+ 'id': video_id,
+ 'title': 'TwitterCard',
+ 'thumbnail': thumbnail,
+ 'duration': duration,
+ 'formats': formats,
+ }
class UDNEmbedIE(InfoExtractor):
+ IE_DESC = '聯合影音'
_VALID_URL = r'https?://video\.udn\.com/(?:embed|play)/news/(?P<id>\d+)'
_TESTS = [{
'url': 'http://video.udn.com/embed/news/300040',
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
+ compat_urlparse,
)
from ..utils import (
ExtractorError,
def _real_extract(self, url):
video_id = self._match_id(url)
- redirect_page, urlh = self._download_webpage_handle(url, video_id)
- new_location = self._search_regex(r'window\.location = \'(.*)\';',
- redirect_page, 'redirect location')
- redirect_url = urlh.geturl() + new_location
- webpage = self._download_webpage(redirect_url, video_id,
+ # need to get the page 3 times for the correct jsSecretToken cookie
+ # which is necessary for the correct title
+ def get_session_id():
+ redirect_page = self._download_webpage(url, video_id)
+ session_id_url = self._search_regex(
+ r'var\s*url\s*=\s*\'([^\']+)\';', redirect_page,
+ 'session id url')
+ self._download_webpage(
+ compat_urlparse.urljoin(url, session_id_url), video_id,
+ 'Getting session id')
+
+ get_session_id()
+ get_session_id()
+
+ webpage = self._download_webpage(url, video_id,
'Downloading redirect page')
title = self._html_search_regex(r'<title>(.*)</title>',
+# coding: utf-8
from __future__ import unicode_literals
+import json
import time
import hmac
import hashlib
parse_age_limit,
parse_iso8601,
)
+from ..compat import compat_urllib_request
from .common import InfoExtractor
_APP_VERSION = '2.2.5.1428709186'
_APP_SECRET = '-$iJ}@p7!G@SyU/je1bEyWg}upLu-6V6-Lg9VD(]siH,r.,m-r|ulZ,U4LC/SeR)'
- def _prepare_call(self, path, timestamp=None):
+ _NETRC_MACHINE = 'viki'
+
+ _token = None
+
+ def _prepare_call(self, path, timestamp=None, post_data=None):
path += '?' if '?' not in path else '&'
if not timestamp:
timestamp = int(time.time())
query = self._API_QUERY_TEMPLATE % (path, self._APP, timestamp)
+ if self._token:
+ query += '&token=%s' % self._token
sig = hmac.new(
self._APP_SECRET.encode('ascii'),
query.encode('ascii'),
hashlib.sha1
).hexdigest()
- return self._API_URL_TEMPLATE % (query, sig)
+ url = self._API_URL_TEMPLATE % (query, sig)
+ return compat_urllib_request.Request(
+ url, json.dumps(post_data).encode('utf-8')) if post_data else url
- def _call_api(self, path, video_id, note, timestamp=None):
+ def _call_api(self, path, video_id, note, timestamp=None, post_data=None):
resp = self._download_json(
- self._prepare_call(path, timestamp), video_id, note)
+ self._prepare_call(path, timestamp, post_data), video_id, note)
error = resp.get('error')
if error:
if error == 'invalid timestamp':
resp = self._download_json(
- self._prepare_call(path, int(resp['current_timestamp'])),
+ self._prepare_call(path, int(resp['current_timestamp']), post_data),
video_id, '%s (retry)' % note)
error = resp.get('error')
if error:
'%s returned error: %s' % (self.IE_NAME, error),
expected=True)
+ def _real_initialize(self):
+ self._login()
+
+ def _login(self):
+ (username, password) = self._get_login_info()
+ if username is None:
+ return
+
+ login_form = {
+ 'login_id': username,
+ 'password': password,
+ }
+
+ login = self._call_api(
+ 'sessions.json', None,
+ 'Logging in as %s' % username, post_data=login_form)
+
+ self._token = login.get('token')
+ if not self._token:
+ self.report_warning('Unable to get session token, login has probably failed')
+
class VikiIE(VikiBaseIE):
IE_NAME = 'viki'
unified_strdate,
unsmuggle_url,
urlencode_postdata,
+ unescapeHTML,
)
},
]
+ @staticmethod
+ def _extract_vimeo_url(url, webpage):
+ # Look for embedded (iframe) Vimeo player
+ mobj = re.search(
+ r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
+ if mobj:
+ player_url = unescapeHTML(mobj.group('url'))
+ surl = smuggle_url(player_url, {'Referer': url})
+ return surl
+ # Look for embedded (swf embed) Vimeo player
+ mobj = re.search(
+ r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
+ if mobj:
+ return mobj.group(1)
+
def _verify_video_password(self, url, video_id, webpage):
password = self._downloader.params.get('videopassword', None)
if password is None:
password = self._downloader.params.get('videopassword', None)
if password is None:
raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
- fields = dict(re.findall(r'''(?x)<input\s+
- type="hidden"\s+
- name="([^"]+)"\s+
- value="([^"]*)"
- ''', login_form))
+ fields = self._form_hidden_inputs(login_form)
token = self._search_regex(r'xsrft[\s=:"\']+([^"\']+)', webpage, 'login token')
fields['token'] = token
fields['password'] = password
from ..utils import int_or_none
-class VimpleIE(InfoExtractor):
+class SprutoBaseIE(InfoExtractor):
+ def _extract_spruto(self, spruto, video_id):
+ playlist = spruto['playlist'][0]
+ title = playlist['title']
+ video_id = playlist.get('videoId') or video_id
+ thumbnail = playlist.get('posterUrl') or playlist.get('thumbnailUrl')
+ duration = int_or_none(playlist.get('duration'))
+
+ formats = [{
+ 'url': f['url'],
+ } for f in playlist['video']]
+ self._sort_formats(formats)
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'thumbnail': thumbnail,
+ 'duration': duration,
+ 'formats': formats,
+ }
+
+
+class VimpleIE(SprutoBaseIE):
IE_DESC = 'Vimple - one-click video hosting'
_VALID_URL = r'https?://(?:player\.vimple\.ru/iframe|vimple\.ru)/(?P<id>[\da-f-]{32,36})'
_TESTS = [
webpage = self._download_webpage(
'http://player.vimple.ru/iframe/%s' % video_id, video_id)
- playlist = self._parse_json(
+ spruto = self._parse_json(
self._search_regex(
r'sprutoData\s*:\s*({.+?}),\r\n', webpage, 'spruto data'),
- video_id)['playlist'][0]
-
- title = playlist['title']
- video_id = playlist.get('videoId') or video_id
- thumbnail = playlist.get('posterUrl') or playlist.get('thumbnailUrl')
- duration = int_or_none(playlist.get('duration'))
-
- formats = [{
- 'url': f['url'],
- } for f in playlist['video']]
- self._sort_formats(formats)
+ video_id)
- return {
- 'id': video_id,
- 'title': title,
- 'thumbnail': thumbnail,
- 'duration': duration,
- 'formats': formats,
- }
+ return self._extract_spruto(spruto, video_id)
from ..utils import (
ExtractorError,
orderedSet,
+ str_to_int,
unescapeHTML,
unified_strdate,
)
class VKIE(InfoExtractor):
IE_NAME = 'vk.com'
- _VALID_URL = r'https?://(?:m\.)?vk\.com/(?:video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|(?:.+?\?.*?z=)?video(?P<videoid>[^s].*?)(?:\?|%2F|$))'
+ _VALID_URL = r'''(?x)
+ https?://
+ (?:
+ (?:m\.)?vk\.com/video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|
+ (?:
+ (?:m\.)?vk\.com/(?:.+?\?.*?z=)?video|
+ (?:www\.)?biqle\.ru/watch/
+ )
+ (?P<videoid>[^s].*?)(?:\?(?:.*\blist=(?P<list_id>[\da-f]+))?|%2F|$)
+ )
+ '''
_NETRC_MACHINE = 'vk'
_TESTS = [
'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
'duration': 195,
'upload_date': '20120212',
+ 'view_count': int,
},
},
{
'uploader': 'Tom Cruise',
'title': 'No name',
'duration': 9,
- 'upload_date': '20130721'
+ 'upload_date': '20130721',
+ 'view_count': int,
}
},
{
'title': 'Lin Dan',
'duration': 101,
'upload_date': '20120730',
+ 'view_count': int,
}
},
{
'uploader': 'Триллеры',
'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
'duration': 8352,
- 'upload_date': '20121218'
+ 'upload_date': '20121218',
+ 'view_count': int,
},
'skip': 'Requires vk account credentials',
},
'title': 'Книга Илая',
'duration': 6771,
'upload_date': '20140626',
+ 'view_count': int,
},
'skip': 'Only works from Russia',
},
+ {
+ # video (removed?) only available with list id
+ 'url': 'https://vk.com/video30481095_171201961?list=8764ae2d21f14088d4',
+ 'md5': '091287af5402239a1051c37ec7b92913',
+ 'info_dict': {
+ 'id': '171201961',
+ 'ext': 'mp4',
+ 'title': 'ТюменцевВВ_09.07.2015',
+ 'uploader': 'Anton Ivanov',
+ 'duration': 109,
+ 'upload_date': '20150709',
+ 'view_count': int,
+ },
+ },
+ {
+ # youtube embed
+ 'url': 'https://vk.com/video276849682_170681728',
+ 'info_dict': {
+ 'id': 'V3K4mi0SYkc',
+ 'ext': 'mp4',
+ 'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",
+ 'description': 'md5:bf9c26cfa4acdfb146362682edd3827a',
+ 'duration': 179,
+ 'upload_date': '20130116',
+ 'uploader': "Children's Joy Foundation",
+ 'uploader_id': 'thecjf',
+ 'view_count': int,
+ },
+ },
{
# removed video, just testing that we match the pattern
'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
'only_matching': True,
},
+ {
+ # vk wrapper
+ 'url': 'http://www.biqle.ru/watch/847655_160197695',
+ 'only_matching': True,
+ }
]
def _login(self):
if username is None:
return
- login_form = {
- 'act': 'login',
- 'role': 'al_frame',
- 'expire': '1',
- 'email': username,
- 'pass': password,
- }
+ login_page = self._download_webpage(
+ 'https://vk.com', None, 'Downloading login page')
+
+ login_form = self._form_hidden_inputs(login_page)
+
+ login_form.update({
+ 'email': username.encode('cp1251'),
+ 'pass': password.encode('cp1251'),
+ })
- request = compat_urllib_request.Request('https://login.vk.com/?act=login',
- compat_urllib_parse.urlencode(login_form).encode('utf-8'))
- login_page = self._download_webpage(request, None, note='Logging in as %s' % username)
+ request = compat_urllib_request.Request(
+ 'https://login.vk.com/?act=login',
+ compat_urllib_parse.urlencode(login_form).encode('utf-8'))
+ login_page = self._download_webpage(
+ request, None, note='Logging in as %s' % username)
if re.search(r'onLoginFailed', login_page):
- raise ExtractorError('Unable to login, incorrect username and/or password', expected=True)
+ raise ExtractorError(
+ 'Unable to login, incorrect username and/or password', expected=True)
def _real_initialize(self):
self._login()
if not video_id:
video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id'))
- info_url = 'http://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id
+ info_url = 'https://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id
+
+ # Some videos (removed?) can only be downloaded with list id specified
+ list_id = mobj.group('list_id')
+ if list_id:
+ info_url += '&list=%s' % list_id
+
info_page = self._download_webpage(info_url, video_id)
+ if re.search(r'<!>/login\.php\?.*\bact=security_check', info_page):
+ raise ExtractorError(
+ 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.',
+ expected=True)
+
ERRORS = {
r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
'Video %s has been removed from public access due to rightholder complaint.',
r'<!>Видео временно недоступно':
'Video %s is temporarily unavailable.',
+
+ r'<!>Access denied':
+ 'Access denied to video %s.',
}
for error_re, error_msg in ERRORS.items():
if re.search(error_re, info_page):
raise ExtractorError(error_msg % video_id, expected=True)
- m_yt = re.search(r'src="(http://www.youtube.com/.*?)"', info_page)
- if m_yt is not None:
- self.to_screen('Youtube video detected')
- return self.url_result(m_yt.group(1), 'Youtube')
+ youtube_url = self._search_regex(
+ r'<iframe[^>]+src="((?:https?:)?//www.youtube.com/embed/[^"]+)"',
+ info_page, 'youtube iframe', default=None)
+ if youtube_url:
+ return self.url_result(youtube_url, 'Youtube')
m_rutube = re.search(
r'\ssrc="((?:https?:)?//rutube\.ru\\?/video\\?/embed(?:.*?))\\?"', info_page)
m_rutube.group(1).replace('\\', ''))
return self.url_result(rutube_url)
- m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.*?});', info_page)
+ m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page)
if m_opts:
- m_opts_url = re.search(r"url\s*:\s*'([^']+)", m_opts.group(1))
+ m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1))
if m_opts_url:
opts_url = m_opts_url.group(1)
if opts_url.startswith('//'):
opts_url = 'http:' + opts_url
return self.url_result(opts_url)
- data_json = self._search_regex(r'var vars = ({.*?});', info_page, 'vars')
+ data_json = self._search_regex(r'var\s+vars\s*=\s*({.+?});', info_page, 'vars')
data = json.loads(data_json)
# Extract upload date
upload_date = None
- mobj = re.search(r'id="mv_date_wrap".*?Added ([a-zA-Z]+ [0-9]+), ([0-9]+) at', info_page)
+ mobj = re.search(r'id="mv_date(?:_views)?_wrap"[^>]*>([a-zA-Z]+ [0-9]+), ([0-9]+) at', info_page)
if mobj is not None:
mobj.group(1) + ' ' + mobj.group(2)
upload_date = unified_strdate(mobj.group(1) + ' ' + mobj.group(2))
+ view_count = str_to_int(self._search_regex(
+ r'"mv_views_count_number"[^>]*>([\d,.]+) views<',
+ info_page, 'view count', fatal=False))
+
formats = [{
'format_id': k,
'url': v,
'uploader': data.get('md_author'),
'duration': data.get('duration'),
'upload_date': upload_date,
+ 'view_count': view_count,
}
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
- fields = dict(re.findall(r'''(?x)<input\s+
- type="hidden"\s+
- name="([^"]+)"\s+
- (?:id="[^"]+"\s+)?
- value="([^"]*)"
- ''', webpage))
+ fields = self._form_hidden_inputs(webpage)
if fields['op'] == 'download1':
self._sleep(3, video_id) # they do detect when requests happen too fast!
'comment_count': int,
'categories': ['amazing', 'hd', 'best drummer ever', 'william wei', 'bucket drumming', 'street drummer', 'epic street drumming'],
},
+ 'skip': 'Not accessible from Travis CI server',
}, {
'url': 'http://vube.com/Chiara+Grispo+Video+Channel/YL2qNPkqon',
'md5': 'db7aba89d4603dadd627e9d1973946fe',
# coding: utf-8
from __future__ import unicode_literals
+import re
+
from .common import InfoExtractor
from ..utils import int_or_none
'description': description,
'duration': duration,
}
+
+
+class WebOfStoriesPlaylistIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?webofstories\.com/playAll/(?P<id>[^/]+)'
+ _TEST = {
+ 'url': 'http://www.webofstories.com/playAll/donald.knuth',
+ 'info_dict': {
+ 'id': 'donald.knuth',
+ 'title': 'Donald Knuth (Scientist)',
+ },
+ 'playlist_mincount': 97,
+ }
+
+ def _real_extract(self, url):
+ playlist_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, playlist_id)
+
+ entries = [
+ self.url_result('http://www.webofstories.com/play/%s' % video_number, 'WebOfStories')
+ for video_number in set(re.findall('href="/playAll/%s\?sId=(\d+)"' % playlist_id, webpage))
+ ]
+
+ title = self._search_regex(
+ r'<div id="speakerName">\s*<span>([^<]+)</span>',
+ webpage, 'speaker', default=None)
+ if title:
+ field = self._search_regex(
+ r'<span id="primaryField">([^<]+)</span>',
+ webpage, 'field', default=None)
+ if field:
+ title += ' (%s)' % field
+
+ if not title:
+ title = self._search_regex(
+ r'<title>Play\s+all\s+stories\s*-\s*([^<]+)\s*-\s*Web\s+of\s+Stories</title>',
+ webpage, 'title')
+
+ return self.playlist_result(entries, playlist_id, title)
class XHamsterIE(InfoExtractor):
- """Information Extractor for xHamster"""
_VALID_URL = r'(?P<proto>https?)://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
_TESTS = [
{
'age_limit': age_limit,
'formats': formats,
}
+
+
+class XHamsterEmbedIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?xhamster\.com/xembed\.php\?video=(?P<id>\d+)'
+ _TEST = {
+ 'url': 'http://xhamster.com/xembed.php?video=3328539',
+ 'info_dict': {
+ 'id': '3328539',
+ 'ext': 'mp4',
+ 'title': 'Pen Masturbation',
+ 'upload_date': '20140728',
+ 'uploader_id': 'anonymous',
+ 'duration': 5,
+ 'age_limit': 18,
+ }
+ }
+
+ @staticmethod
+ def _extract_urls(webpage):
+ return [url for _, url in re.findall(
+ r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1',
+ webpage)]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, video_id)
+
+ video_url = self._search_regex(
+ r'href="(https?://xhamster\.com/movies/%s/[^"]+\.html[^"]*)"' % video_id,
+ webpage, 'xhamster url')
+
+ return self.url_result(video_url, 'XHamster')
class XuiteIE(InfoExtractor):
+ IE_DESC = '隨意窩Xuite影音'
_REGEX_BASE64 = r'(?:[A-Za-z0-9+/]{4})*(?:[A-Za-z0-9+/]{2}==|[A-Za-z0-9+/]{3}=)?'
_VALID_URL = r'https?://vlog\.xuite\.net/(?:play|embed)/(?P<id>%s)' % _REGEX_BASE64
_TESTS = [{
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
+ compat_urllib_request,
)
from ..utils import (
clean_html,
ExtractorError,
+ determine_ext,
)
}
}
+ _ANDROID_USER_AGENT = 'Mozilla/5.0 (Linux; Android 4.0.4; Galaxy Nexus Build/IMM76B) AppleWebKit/535.19 (KHTML, like Gecko) Chrome/18.0.1025.133 Mobile Safari/535.19'
+
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_thumbnail = self._search_regex(
r'url_bigthumb=(.+?)&', webpage, 'thumbnail', fatal=False)
+ formats = [{
+ 'url': video_url,
+ }]
+
+ android_req = compat_urllib_request.Request(url)
+ android_req.add_header('User-Agent', self._ANDROID_USER_AGENT)
+ android_webpage = self._download_webpage(android_req, video_id, fatal=False)
+
+ if android_webpage is not None:
+ player_params_str = self._search_regex(
+ 'mobileReplacePlayerDivTwoQual\(([^)]+)\)',
+ android_webpage, 'player parameters', default='')
+ player_params = list(map(lambda s: s.strip(' \''), player_params_str.split(',')))
+ if player_params:
+ formats.extend([{
+ 'url': param,
+ 'preference': -10,
+ } for param in player_params if determine_ext(param) == 'mp4'])
+
+ self._sort_formats(formats)
+
return {
'id': video_id,
- 'url': video_url,
+ 'formats': formats,
'title': video_title,
'ext': 'flv',
'thumbnail': video_thumbnail,
class YamIE(InfoExtractor):
+ IE_DESC = '蕃薯藤yam天空部落'
_VALID_URL = r'http://mymedia.yam.com/m/(?P<id>\d+)'
_TESTS = [{
--- /dev/null
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class YinYueTaiIE(InfoExtractor):
+ IE_NAME = 'yinyuetai:video'
+ IE_DESC = '音悦Tai'
+ _VALID_URL = r'https?://v\.yinyuetai\.com/video(?:/h5)?/(?P<id>[0-9]+)'
+ _TESTS = [{
+ 'url': 'http://v.yinyuetai.com/video/2322376',
+ 'md5': '6e3abe28d38e3a54b591f9f040595ce0',
+ 'info_dict': {
+ 'id': '2322376',
+ 'ext': 'mp4',
+ 'title': '少女时代_PARTY_Music Video Teaser',
+ 'creator': '少女时代',
+ 'duration': 25,
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ },
+ }, {
+ 'url': 'http://v.yinyuetai.com/video/h5/2322376',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ info = self._download_json(
+ 'http://ext.yinyuetai.com/main/get-h-mv-info?json=true&videoId=%s' % video_id, video_id,
+ 'Downloading mv info')['videoInfo']['coreVideoInfo']
+
+ if info['error']:
+ raise ExtractorError(info['errorMsg'], expected=True)
+
+ formats = [{
+ 'url': format_info['videoUrl'],
+ 'format_id': format_info['qualityLevel'],
+ 'format': format_info.get('qualityLevelName'),
+ 'filesize': format_info.get('fileSize'),
+ # though URLs ends with .flv, the downloaded files are in fact mp4
+ 'ext': 'mp4',
+ 'tbr': format_info.get('bitrate'),
+ } for format_info in info['videoUrlModels']]
+ self._sort_formats(formats)
+
+ return {
+ 'id': video_id,
+ 'title': info['videoName'],
+ 'thumbnail': info.get('bigHeadImage'),
+ 'creator': info.get('artistNames'),
+ 'duration': info.get('duration'),
+ 'formats': formats,
+ }
# coding: utf-8
-
from __future__ import unicode_literals
-import math
-import random
-import re
-import time
+import base64
from .common import InfoExtractor
-from ..utils import (
- ExtractorError,
+from ..utils import ExtractorError
+
+from ..compat import (
+ compat_urllib_parse,
+ compat_ord,
+ compat_urllib_request,
)
class YoukuIE(InfoExtractor):
+ IE_NAME = 'youku'
+ IE_DESC = '优酷'
_VALID_URL = r'''(?x)
(?:
http://(?:v|player)\.youku\.com/(?:v_show/id_|player\.php/sid/)|
youku:)
(?P<id>[A-Za-z0-9]+)(?:\.html|/v\.swf|)
'''
- _TEST = {
- 'url': 'http://v.youku.com/v_show/id_XNDgyMDQ2NTQw.html',
- 'md5': 'ffe3f2e435663dc2d1eea34faeff5b5b',
- 'params': {
- 'test': False
+
+ _TESTS = [{
+ 'url': 'http://v.youku.com/v_show/id_XMTc1ODE5Njcy.html',
+ 'md5': '5f3af4192eabacc4501508d54a8cabd7',
+ 'info_dict': {
+ 'id': 'XMTc1ODE5Njcy_part1',
+ 'title': '★Smile﹗♡ Git Fresh -Booty Music舞蹈.',
+ 'ext': 'flv'
+ }
+ }, {
+ 'url': 'http://player.youku.com/player.php/sid/XNDgyMDQ2NTQw/v.swf',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://v.youku.com/v_show/id_XODgxNjg1Mzk2_ev_1.html',
+ 'info_dict': {
+ 'id': 'XODgxNjg1Mzk2',
+ 'title': '武媚娘传奇 85',
},
+ 'playlist_count': 11,
+ }, {
+ 'url': 'http://v.youku.com/v_show/id_XMTI1OTczNDM5Mg==.html',
'info_dict': {
- 'id': 'XNDgyMDQ2NTQw_part00',
- 'ext': 'flv',
- 'title': 'youtube-dl test video "\'/\\ä↭𝕐'
+ 'id': 'XMTI1OTczNDM5Mg',
+ 'title': '花千骨 04',
+ },
+ 'playlist_count': 13,
+ 'skip': 'Available in China only',
+ }]
+
+ def construct_video_urls(self, data1, data2):
+ # get sid, token
+ def yk_t(s1, s2):
+ ls = list(range(256))
+ t = 0
+ for i in range(256):
+ t = (t + ls[i] + compat_ord(s1[i % len(s1)])) % 256
+ ls[i], ls[t] = ls[t], ls[i]
+ s = bytearray()
+ x, y = 0, 0
+ for i in range(len(s2)):
+ y = (y + 1) % 256
+ x = (x + ls[y]) % 256
+ ls[x], ls[y] = ls[y], ls[x]
+ s.append(compat_ord(s2[i]) ^ ls[(ls[x] + ls[y]) % 256])
+ return bytes(s)
+
+ sid, token = yk_t(
+ b'becaf9be', base64.b64decode(data2['ep'].encode('ascii'))
+ ).decode('ascii').split('_')
+
+ # get oip
+ oip = data2['ip']
+
+ # get fileid
+ string_ls = list(
+ 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890')
+ shuffled_string_ls = []
+ seed = data1['seed']
+ N = len(string_ls)
+ for ii in range(N):
+ seed = (seed * 0xd3 + 0x754f) % 0x10000
+ idx = seed * len(string_ls) // 0x10000
+ shuffled_string_ls.append(string_ls[idx])
+ del string_ls[idx]
+
+ fileid_dict = {}
+ for format in data1['streamtypes']:
+ streamfileid = [
+ int(i) for i in data1['streamfileids'][format].strip('*').split('*')]
+ fileid = ''.join(
+ [shuffled_string_ls[i] for i in streamfileid])
+ fileid_dict[format] = fileid[:8] + '%s' + fileid[10:]
+
+ def get_fileid(format, n):
+ fileid = fileid_dict[format] % hex(int(n))[2:].upper().zfill(2)
+ return fileid
+
+ # get ep
+ def generate_ep(format, n):
+ fileid = get_fileid(format, n)
+ ep_t = yk_t(
+ b'bf7e5f01',
+ ('%s_%s_%s' % (sid, fileid, token)).encode('ascii')
+ )
+ ep = base64.b64encode(ep_t).decode('ascii')
+ return ep
+
+ # generate video_urls
+ video_urls_dict = {}
+ for format in data1['streamtypes']:
+ video_urls = []
+ for dt in data1['segs'][format]:
+ n = str(int(dt['no']))
+ param = {
+ 'K': dt['k'],
+ 'hd': self.get_hd(format),
+ 'myp': 0,
+ 'ts': dt['seconds'],
+ 'ypp': 0,
+ 'ctype': 12,
+ 'ev': 1,
+ 'token': token,
+ 'oip': oip,
+ 'ep': generate_ep(format, n)
+ }
+ video_url = \
+ 'http://k.youku.com/player/getFlvPath/' + \
+ 'sid/' + sid + \
+ '_' + str(int(n) + 1).zfill(2) + \
+ '/st/' + self.parse_ext_l(format) + \
+ '/fileid/' + get_fileid(format, n) + '?' + \
+ compat_urllib_parse.urlencode(param)
+ video_urls.append(video_url)
+ video_urls_dict[format] = video_urls
+
+ return video_urls_dict
+
+ def get_hd(self, fm):
+ hd_id_dict = {
+ 'flv': '0',
+ 'mp4': '1',
+ 'hd2': '2',
+ 'hd3': '3',
+ '3gp': '0',
+ '3gphd': '1'
}
- }
-
- def _gen_sid(self):
- nowTime = int(time.time() * 1000)
- random1 = random.randint(1000, 1998)
- random2 = random.randint(1000, 9999)
-
- return "%d%d%d" % (nowTime, random1, random2)
-
- def _get_file_ID_mix_string(self, seed):
- mixed = []
- source = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890")
- seed = float(seed)
- for i in range(len(source)):
- seed = (seed * 211 + 30031) % 65536
- index = math.floor(seed / 65536 * len(source))
- mixed.append(source[int(index)])
- source.remove(source[int(index)])
- # return ''.join(mixed)
- return mixed
-
- def _get_file_id(self, fileId, seed):
- mixed = self._get_file_ID_mix_string(seed)
- ids = fileId.split('*')
- realId = []
- for ch in ids:
- if ch:
- realId.append(mixed[int(ch)])
- return ''.join(realId)
+ return hd_id_dict[fm]
+
+ def parse_ext_l(self, fm):
+ ext_dict = {
+ 'flv': 'flv',
+ 'mp4': 'mp4',
+ 'hd2': 'flv',
+ 'hd3': 'flv',
+ '3gp': 'flv',
+ '3gphd': 'mp4'
+ }
+ return ext_dict[fm]
+
+ def get_format_name(self, fm):
+ _dict = {
+ '3gp': 'h6',
+ '3gphd': 'h5',
+ 'flv': 'h4',
+ 'mp4': 'h3',
+ 'hd2': 'h2',
+ 'hd3': 'h1'
+ }
+ return _dict[fm]
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
- info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id
+ video_id = self._match_id(url)
- config = self._download_json(info_url, video_id)
+ def retrieve_data(req_url, note):
+ req = compat_urllib_request.Request(req_url)
- error_code = config['data'][0].get('error_code')
- if error_code:
- # -8 means blocked outside China.
- error = config['data'][0].get('error') # Chinese and English, separated by newline.
- raise ExtractorError(error or 'Server reported error %i' % error_code,
- expected=True)
+ cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
+ if cn_verification_proxy:
+ req.add_header('Ytdl-request-proxy', cn_verification_proxy)
- video_title = config['data'][0]['title']
- seed = config['data'][0]['seed']
+ raw_data = self._download_json(req, video_id, note=note)
+ return raw_data['data'][0]
- format = self._downloader.params.get('format', None)
- supported_format = list(config['data'][0]['streamfileids'].keys())
+ # request basic data
+ data1 = retrieve_data(
+ 'http://v.youku.com/player/getPlayList/VideoIDS/%s' % video_id,
+ 'Downloading JSON metadata 1')
+ data2 = retrieve_data(
+ 'http://v.youku.com/player/getPlayList/VideoIDS/%s/Pf/4/ctype/12/ev/1' % video_id,
+ 'Downloading JSON metadata 2')
- # TODO proper format selection
- if format is None or format == 'best':
- if 'hd2' in supported_format:
- format = 'hd2'
+ error_code = data1.get('error_code')
+ if error_code:
+ error = data1.get('error')
+ if error is not None and '因版权原因无法观看此视频' in error:
+ raise ExtractorError(
+ 'Youku said: Sorry, this video is available in China only', expected=True)
else:
- format = 'flv'
- ext = 'flv'
- elif format == 'worst':
- format = 'mp4'
- ext = 'mp4'
- else:
- format = 'flv'
- ext = 'flv'
-
- fileid = config['data'][0]['streamfileids'][format]
- keys = [s['k'] for s in config['data'][0]['segs'][format]]
- # segs is usually a dictionary, but an empty *list* if an error occured.
-
- files_info = []
- sid = self._gen_sid()
- fileid = self._get_file_id(fileid, seed)
-
- # column 8,9 of fileid represent the segment number
- # fileid[7:9] should be changed
- for index, key in enumerate(keys):
- temp_fileid = '%s%02X%s' % (fileid[0:8], index, fileid[10:])
- download_url = 'http://k.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key)
-
- info = {
- 'id': '%s_part%02d' % (video_id, index),
- 'url': download_url,
- 'uploader': None,
- 'upload_date': None,
- 'title': video_title,
- 'ext': ext,
- }
- files_info.append(info)
-
- return files_info
+ msg = 'Youku server reported error %i' % error_code
+ if error is not None:
+ msg += ': ' + error
+ raise ExtractorError(msg)
+
+ title = data1['title']
+
+ # generate video_urls_dict
+ video_urls_dict = self.construct_video_urls(data1, data2)
+
+ # construct info
+ entries = [{
+ 'id': '%s_part%d' % (video_id, i + 1),
+ 'title': title,
+ 'formats': [],
+ # some formats are not available for all parts, we have to detect
+ # which one has all
+ } for i in range(max(len(v) for v in data1['segs'].values()))]
+ for fm in data1['streamtypes']:
+ video_urls = video_urls_dict[fm]
+ for video_url, seg, entry in zip(video_urls, data1['segs'][fm], entries):
+ entry['formats'].append({
+ 'url': video_url,
+ 'format_id': self.get_format_name(fm),
+ 'ext': self.parse_ext_l(fm),
+ 'filesize': int(seg['size']),
+ })
+
+ return {
+ '_type': 'multi_video',
+ 'id': video_id,
+ 'title': title,
+ 'entries': entries,
+ }
get_element_by_id,
int_or_none,
orderedSet,
+ str_to_int,
unescapeHTML,
unified_strdate,
uppercase_escape,
+ ISO3166Utils,
)
'44': {'ext': 'webm', 'width': 854, 'height': 480},
'45': {'ext': 'webm', 'width': 1280, 'height': 720},
'46': {'ext': 'webm', 'width': 1920, 'height': 1080},
+ '59': {'ext': 'mp4', 'width': 854, 'height': 480},
+ '78': {'ext': 'mp4', 'width': 854, 'height': 480},
# 3d videos
'skip_download': 'requires avconv',
}
},
+ # Extraction from multiple DASH manifests (https://github.com/rg3/youtube-dl/pull/6097)
+ {
+ 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
+ 'info_dict': {
+ 'id': 'FIl7x6_3R5Y',
+ 'ext': 'mp4',
+ 'title': 'md5:7b81415841e02ecd4313668cde88737a',
+ 'description': 'md5:116377fd2963b81ec4ce64b542173306',
+ 'upload_date': '20150625',
+ 'uploader_id': 'dorappi2000',
+ 'uploader': 'dorappi2000',
+ 'formats': 'mincount:33',
+ },
+ }
]
def __init__(self, *args, **kwargs):
return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
def _parse_dash_manifest(
- self, video_id, dash_manifest_url, player_url, age_gate):
+ self, video_id, dash_manifest_url, player_url, age_gate, fatal=True):
def decrypt_sig(mobj):
s = mobj.group(1)
dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
dash_doc = self._download_xml(
dash_manifest_url, video_id,
note='Downloading DASH manifest',
- errnote='Could not download DASH manifest')
+ errnote='Could not download DASH manifest',
+ fatal=fatal)
+
+ if dash_doc is False:
+ return []
formats = []
for a in dash_doc.findall('.//{urn:mpeg:DASH:schema:MPD:2011}AdaptationSet'):
except StopIteration:
full_info = self._formats.get(format_id, {}).copy()
full_info.update(f)
+ codecs = r.attrib.get('codecs')
+ if codecs:
+ if full_info.get('acodec') == 'none' and 'vcodec' not in full_info:
+ full_info['vcodec'] = codecs
+ elif full_info.get('vcodec') == 'none' and 'acodec' not in full_info:
+ full_info['acodec'] = codecs
formats.append(full_info)
else:
existing_format.update(f)
else:
player_url = None
+ dash_mpds = []
+
+ def add_dash_mpd(video_info):
+ dash_mpd = video_info.get('dashmpd')
+ if dash_mpd and dash_mpd[0] not in dash_mpds:
+ dash_mpds.append(dash_mpd[0])
+
# Get video info
embed_webpage = None
if re.search(r'player-age-gate-content">', video_webpage) is not None:
note='Refetching age-gated info webpage',
errnote='unable to download video info webpage')
video_info = compat_parse_qs(video_info_webpage)
+ add_dash_mpd(video_info)
else:
age_gate = False
- try:
- # Try looking directly into the video webpage
- mobj = re.search(r';ytplayer\.config\s*=\s*({.*?});', video_webpage)
- if not mobj:
- raise ValueError('Could not find ytplayer.config') # caught below
+ video_info = None
+ # Try looking directly into the video webpage
+ mobj = re.search(r';ytplayer\.config\s*=\s*({.*?});', video_webpage)
+ if mobj:
json_code = uppercase_escape(mobj.group(1))
ytplayer_config = json.loads(json_code)
args = ytplayer_config['args']
- # Convert to the same format returned by compat_parse_qs
- video_info = dict((k, [v]) for k, v in args.items())
- if not args.get('url_encoded_fmt_stream_map'):
- raise ValueError('No stream_map present') # caught below
- except ValueError:
- # We fallback to the get_video_info pages (used by the embed page)
+ if args.get('url_encoded_fmt_stream_map'):
+ # Convert to the same format returned by compat_parse_qs
+ video_info = dict((k, [v]) for k, v in args.items())
+ add_dash_mpd(video_info)
+ if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True):
+ # We also try looking in get_video_info since it may contain different dashmpd
+ # URL that points to a DASH manifest with possibly different itag set (some itags
+ # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
+ # manifest pointed by get_video_info's dashmpd).
+ # The general idea is to take a union of itags of both DASH manifests (for example
+ # video with such 'manifest behavior' see https://github.com/rg3/youtube-dl/issues/6093)
self.report_video_info_webpage_download(video_id)
- for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
+ for el_type in ['&el=info', '&el=embedded', '&el=detailpage', '&el=vevo', '']:
video_info_url = (
'%s://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
% (proto, video_id, el_type))
video_info_url,
video_id, note=False,
errnote='unable to download video info webpage')
- video_info = compat_parse_qs(video_info_webpage)
- if 'token' in video_info:
+ get_video_info = compat_parse_qs(video_info_webpage)
+ add_dash_mpd(get_video_info)
+ if not video_info:
+ video_info = get_video_info
+ if 'token' in get_video_info:
break
if 'token' not in video_info:
if 'reason' in video_info:
+ if 'The uploader has not made this video available in your country.' in video_info['reason']:
+ regions_allowed = self._html_search_meta('regionsAllowed', video_webpage, default=None)
+ if regions_allowed is not None:
+ raise ExtractorError('YouTube said: This video is available in %s only' % (
+ ', '.join(map(ISO3166Utils.short2full, regions_allowed.split(',')))),
+ expected=True)
raise ExtractorError(
'YouTube said: %s' % video_info['reason'][0],
expected=True, video_id=video_id)
video_thumbnail = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0])
# upload date
- upload_date = None
- mobj = re.search(r'(?s)id="eow-date.*?>(.*?)</span>', video_webpage)
- if mobj is None:
- mobj = re.search(
- r'(?s)id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live) on (.*?)</strong>',
- video_webpage)
- if mobj is not None:
- upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
- upload_date = unified_strdate(upload_date)
+ upload_date = self._html_search_meta(
+ 'datePublished', video_webpage, 'upload date', default=None)
+ if not upload_date:
+ upload_date = self._search_regex(
+ [r'(?s)id="eow-date.*?>(.*?)</span>',
+ r'id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live|Started) on (.+?)</strong>'],
+ video_webpage, 'upload date', default=None)
+ if upload_date:
+ upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
+ upload_date = unified_strdate(upload_date)
m_cat_container = self._search_regex(
r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
video_description = ''
def _extract_count(count_name):
- count = self._search_regex(
- r'id="watch-%s"[^>]*>.*?([\d,]+)\s*</span>' % re.escape(count_name),
- video_webpage, count_name, default=None)
- if count is not None:
- return int(count.replace(',', ''))
- return None
+ return str_to_int(self._search_regex(
+ r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
+ % re.escape(count_name),
+ video_webpage, count_name, default=None))
+
like_count = _extract_count('like')
dislike_count = _extract_count('dislike')
# Look for the DASH manifest
if self._downloader.params.get('youtube_include_dash_manifest', True):
- dash_mpd = video_info.get('dashmpd')
- if dash_mpd:
- dash_manifest_url = dash_mpd[0]
+ dash_mpd_fatal = True
+ for dash_manifest_url in dash_mpds:
+ dash_formats = {}
try:
- dash_formats = self._parse_dash_manifest(
- video_id, dash_manifest_url, player_url, age_gate)
+ for df in self._parse_dash_manifest(
+ video_id, dash_manifest_url, player_url, age_gate, dash_mpd_fatal):
+ # Do not overwrite DASH format found in some previous DASH manifest
+ if df['format_id'] not in dash_formats:
+ dash_formats[df['format_id']] = df
+ # Additional DASH manifests may end up in HTTP Error 403 therefore
+ # allow them to fail without bug report message if we already have
+ # some DASH manifest succeeded. This is temporary workaround to reduce
+ # burst of bug reports until we figure out the reason and whether it
+ # can be fixed at all.
+ dash_mpd_fatal = False
except (ExtractorError, KeyError) as e:
self.report_warning(
'Skipping DASH manifest: %r' % e, video_id)
- else:
+ if dash_formats:
# Remove the formats we found through non-DASH, they
# contain less info and it can be wrong, because we use
# fixed values (for example the resolution). See
# https://github.com/rg3/youtube-dl/issues/5774 for an
# example.
- dash_keys = set(df['format_id'] for df in dash_formats)
- formats = [f for f in formats if f['format_id'] not in dash_keys]
- formats.extend(dash_formats)
+ formats = [f for f in formats if f['format_id'] not in dash_formats.keys()]
+ formats.extend(dash_formats.values())
# Check for malformed aspect ratio
stretched_m = re.search(
for pagenum in itertools.count(1):
url_query = {
- 'search_query': query,
+ 'search_query': query.encode('utf-8'),
'page': pagenum,
'spf': 'navigate',
}
'--extractor-descriptions',
action='store_true', dest='list_extractor_descriptions', default=False,
help='Output descriptions of all supported extractors')
+ general.add_option(
+ '--force-generic-extractor',
+ action='store_true', dest='force_generic_extractor', default=False,
+ help='Force extraction to use the generic extractor')
general.add_option(
'--default-search',
dest='default_search', metavar='PREFIX',
video_format.add_option(
'--youtube-skip-dash-manifest',
action='store_false', dest='youtube_include_dash_manifest',
- help='Do not download the DASH manifest on YouTube videos')
+ help='Do not download the DASH manifests and related data on YouTube videos')
video_format.add_option(
'--merge-output-format',
action='store', dest='merge_output_format', metavar='FORMAT', default=None,
help=(
- 'If a merge is required (e.g. bestvideo+bestaudio), output to given container format. One of mkv, mp4, ogg, webm, flv.'
+ 'If a merge is required (e.g. bestvideo+bestaudio), '
+ 'output to given container format. One of mkv, mp4, ogg, webm, flv. '
'Ignored if no merge is required'))
subtitles = optparse.OptionGroup(parser, 'Subtitle Options')
metavar='POLICY', dest='fixup', default='detect_or_warn',
help='Automatically correct known faults of the file. '
'One of never (do nothing), warn (only emit a warning), '
- 'detect_or_warn(the default; fix file if we can, warn otherwise)')
+ 'detect_or_warn (the default; fix file if we can, warn otherwise)')
postproc.add_option(
'--prefer-avconv',
action='store_false', dest='prefer_ffmpeg',
thumbnail_filename = info['thumbnails'][-1]['filename']
+ if not os.path.exists(encodeFilename(thumbnail_filename)):
+ self._downloader.report_warning(
+ 'Skipping embedding the thumbnail because the file is missing.')
+ return [], info
+
if info['ext'] == 'mp3':
options = [
'-c', 'copy', '-map', '0', '-map', '1',
shell_quote,
subtitles_filename,
dfxp2srt,
+ ISO639Utils,
)
class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
- # See http://www.loc.gov/standards/iso639-2/ISO-639-2_utf-8.txt
- _lang_map = {
- 'aa': 'aar',
- 'ab': 'abk',
- 'ae': 'ave',
- 'af': 'afr',
- 'ak': 'aka',
- 'am': 'amh',
- 'an': 'arg',
- 'ar': 'ara',
- 'as': 'asm',
- 'av': 'ava',
- 'ay': 'aym',
- 'az': 'aze',
- 'ba': 'bak',
- 'be': 'bel',
- 'bg': 'bul',
- 'bh': 'bih',
- 'bi': 'bis',
- 'bm': 'bam',
- 'bn': 'ben',
- 'bo': 'bod',
- 'br': 'bre',
- 'bs': 'bos',
- 'ca': 'cat',
- 'ce': 'che',
- 'ch': 'cha',
- 'co': 'cos',
- 'cr': 'cre',
- 'cs': 'ces',
- 'cu': 'chu',
- 'cv': 'chv',
- 'cy': 'cym',
- 'da': 'dan',
- 'de': 'deu',
- 'dv': 'div',
- 'dz': 'dzo',
- 'ee': 'ewe',
- 'el': 'ell',
- 'en': 'eng',
- 'eo': 'epo',
- 'es': 'spa',
- 'et': 'est',
- 'eu': 'eus',
- 'fa': 'fas',
- 'ff': 'ful',
- 'fi': 'fin',
- 'fj': 'fij',
- 'fo': 'fao',
- 'fr': 'fra',
- 'fy': 'fry',
- 'ga': 'gle',
- 'gd': 'gla',
- 'gl': 'glg',
- 'gn': 'grn',
- 'gu': 'guj',
- 'gv': 'glv',
- 'ha': 'hau',
- 'he': 'heb',
- 'hi': 'hin',
- 'ho': 'hmo',
- 'hr': 'hrv',
- 'ht': 'hat',
- 'hu': 'hun',
- 'hy': 'hye',
- 'hz': 'her',
- 'ia': 'ina',
- 'id': 'ind',
- 'ie': 'ile',
- 'ig': 'ibo',
- 'ii': 'iii',
- 'ik': 'ipk',
- 'io': 'ido',
- 'is': 'isl',
- 'it': 'ita',
- 'iu': 'iku',
- 'ja': 'jpn',
- 'jv': 'jav',
- 'ka': 'kat',
- 'kg': 'kon',
- 'ki': 'kik',
- 'kj': 'kua',
- 'kk': 'kaz',
- 'kl': 'kal',
- 'km': 'khm',
- 'kn': 'kan',
- 'ko': 'kor',
- 'kr': 'kau',
- 'ks': 'kas',
- 'ku': 'kur',
- 'kv': 'kom',
- 'kw': 'cor',
- 'ky': 'kir',
- 'la': 'lat',
- 'lb': 'ltz',
- 'lg': 'lug',
- 'li': 'lim',
- 'ln': 'lin',
- 'lo': 'lao',
- 'lt': 'lit',
- 'lu': 'lub',
- 'lv': 'lav',
- 'mg': 'mlg',
- 'mh': 'mah',
- 'mi': 'mri',
- 'mk': 'mkd',
- 'ml': 'mal',
- 'mn': 'mon',
- 'mr': 'mar',
- 'ms': 'msa',
- 'mt': 'mlt',
- 'my': 'mya',
- 'na': 'nau',
- 'nb': 'nob',
- 'nd': 'nde',
- 'ne': 'nep',
- 'ng': 'ndo',
- 'nl': 'nld',
- 'nn': 'nno',
- 'no': 'nor',
- 'nr': 'nbl',
- 'nv': 'nav',
- 'ny': 'nya',
- 'oc': 'oci',
- 'oj': 'oji',
- 'om': 'orm',
- 'or': 'ori',
- 'os': 'oss',
- 'pa': 'pan',
- 'pi': 'pli',
- 'pl': 'pol',
- 'ps': 'pus',
- 'pt': 'por',
- 'qu': 'que',
- 'rm': 'roh',
- 'rn': 'run',
- 'ro': 'ron',
- 'ru': 'rus',
- 'rw': 'kin',
- 'sa': 'san',
- 'sc': 'srd',
- 'sd': 'snd',
- 'se': 'sme',
- 'sg': 'sag',
- 'si': 'sin',
- 'sk': 'slk',
- 'sl': 'slv',
- 'sm': 'smo',
- 'sn': 'sna',
- 'so': 'som',
- 'sq': 'sqi',
- 'sr': 'srp',
- 'ss': 'ssw',
- 'st': 'sot',
- 'su': 'sun',
- 'sv': 'swe',
- 'sw': 'swa',
- 'ta': 'tam',
- 'te': 'tel',
- 'tg': 'tgk',
- 'th': 'tha',
- 'ti': 'tir',
- 'tk': 'tuk',
- 'tl': 'tgl',
- 'tn': 'tsn',
- 'to': 'ton',
- 'tr': 'tur',
- 'ts': 'tso',
- 'tt': 'tat',
- 'tw': 'twi',
- 'ty': 'tah',
- 'ug': 'uig',
- 'uk': 'ukr',
- 'ur': 'urd',
- 'uz': 'uzb',
- 've': 'ven',
- 'vi': 'vie',
- 'vo': 'vol',
- 'wa': 'wln',
- 'wo': 'wol',
- 'xh': 'xho',
- 'yi': 'yid',
- 'yo': 'yor',
- 'za': 'zha',
- 'zh': 'zho',
- 'zu': 'zul',
- }
-
- @classmethod
- def _conver_lang_code(cls, code):
- """Convert language code from ISO 639-1 to ISO 639-2/T"""
- return cls._lang_map.get(code[:2])
-
def run(self, information):
if information['ext'] not in ['mp4', 'mkv']:
self._downloader.to_screen('[ffmpeg] Subtitles can only be embedded in mp4 or mkv files')
opts += ['-c:s', 'mov_text']
for (i, lang) in enumerate(sub_langs):
opts.extend(['-map', '%d:0' % (i + 1)])
- lang_code = self._conver_lang_code(lang)
+ lang_code = ISO639Utils.short2long(lang)
if lang_code is not None:
opts.extend(['-metadata:s:s:%d' % i, 'language=%s' % lang_code])
}
+NO_DEFAULT = object()
+
ENGLISH_MONTH_NAMES = [
'January', 'February', 'March', 'April', 'May', 'June',
'July', 'August', 'September', 'October', 'November', 'December']
return '/'.join(replaced)
-def xpath_text(node, xpath, name=None, fatal=False):
+def xpath_text(node, xpath, name=None, fatal=False, default=NO_DEFAULT):
if sys.version_info < (2, 7): # Crazy 2.6
xpath = xpath.encode('ascii')
n = node.find(xpath)
if n is None or n.text is None:
- if fatal:
+ if default is not NO_DEFAULT:
+ return default
+ elif fatal:
name = xpath if name is None else name
raise ExtractorError('Could not find XML element %s' % name)
else:
def dfxp2srt(dfxp_data):
- _x = functools.partial(xpath_with_ns, ns_map={'ttml': 'http://www.w3.org/ns/ttml'})
+ _x = functools.partial(xpath_with_ns, ns_map={
+ 'ttml': 'http://www.w3.org/ns/ttml',
+ 'ttaf1': 'http://www.w3.org/2006/10/ttaf1',
+ })
def parse_node(node):
str_or_empty = functools.partial(str_or_none, default='')
out = str_or_empty(node.text)
for child in node:
- if child.tag in (_x('ttml:br'), 'br'):
+ if child.tag in (_x('ttml:br'), _x('ttaf1:br'), 'br'):
out += '\n' + str_or_empty(child.tail)
- elif child.tag in (_x('ttml:span'), 'span'):
+ elif child.tag in (_x('ttml:span'), _x('ttaf1:span'), 'span'):
out += str_or_empty(parse_node(child))
else:
out += str_or_empty(xml.etree.ElementTree.tostring(child))
dfxp = xml.etree.ElementTree.fromstring(dfxp_data.encode('utf-8'))
out = []
- paras = dfxp.findall(_x('.//ttml:p')) or dfxp.findall('.//p')
+ paras = dfxp.findall(_x('.//ttml:p')) or dfxp.findall(_x('.//ttaf1:p')) or dfxp.findall('.//p')
if not paras:
raise ValueError('Invalid dfxp/TTML subtitle')
return ''.join(out)
+class ISO639Utils(object):
+ # See http://www.loc.gov/standards/iso639-2/ISO-639-2_utf-8.txt
+ _lang_map = {
+ 'aa': 'aar',
+ 'ab': 'abk',
+ 'ae': 'ave',
+ 'af': 'afr',
+ 'ak': 'aka',
+ 'am': 'amh',
+ 'an': 'arg',
+ 'ar': 'ara',
+ 'as': 'asm',
+ 'av': 'ava',
+ 'ay': 'aym',
+ 'az': 'aze',
+ 'ba': 'bak',
+ 'be': 'bel',
+ 'bg': 'bul',
+ 'bh': 'bih',
+ 'bi': 'bis',
+ 'bm': 'bam',
+ 'bn': 'ben',
+ 'bo': 'bod',
+ 'br': 'bre',
+ 'bs': 'bos',
+ 'ca': 'cat',
+ 'ce': 'che',
+ 'ch': 'cha',
+ 'co': 'cos',
+ 'cr': 'cre',
+ 'cs': 'ces',
+ 'cu': 'chu',
+ 'cv': 'chv',
+ 'cy': 'cym',
+ 'da': 'dan',
+ 'de': 'deu',
+ 'dv': 'div',
+ 'dz': 'dzo',
+ 'ee': 'ewe',
+ 'el': 'ell',
+ 'en': 'eng',
+ 'eo': 'epo',
+ 'es': 'spa',
+ 'et': 'est',
+ 'eu': 'eus',
+ 'fa': 'fas',
+ 'ff': 'ful',
+ 'fi': 'fin',
+ 'fj': 'fij',
+ 'fo': 'fao',
+ 'fr': 'fra',
+ 'fy': 'fry',
+ 'ga': 'gle',
+ 'gd': 'gla',
+ 'gl': 'glg',
+ 'gn': 'grn',
+ 'gu': 'guj',
+ 'gv': 'glv',
+ 'ha': 'hau',
+ 'he': 'heb',
+ 'hi': 'hin',
+ 'ho': 'hmo',
+ 'hr': 'hrv',
+ 'ht': 'hat',
+ 'hu': 'hun',
+ 'hy': 'hye',
+ 'hz': 'her',
+ 'ia': 'ina',
+ 'id': 'ind',
+ 'ie': 'ile',
+ 'ig': 'ibo',
+ 'ii': 'iii',
+ 'ik': 'ipk',
+ 'io': 'ido',
+ 'is': 'isl',
+ 'it': 'ita',
+ 'iu': 'iku',
+ 'ja': 'jpn',
+ 'jv': 'jav',
+ 'ka': 'kat',
+ 'kg': 'kon',
+ 'ki': 'kik',
+ 'kj': 'kua',
+ 'kk': 'kaz',
+ 'kl': 'kal',
+ 'km': 'khm',
+ 'kn': 'kan',
+ 'ko': 'kor',
+ 'kr': 'kau',
+ 'ks': 'kas',
+ 'ku': 'kur',
+ 'kv': 'kom',
+ 'kw': 'cor',
+ 'ky': 'kir',
+ 'la': 'lat',
+ 'lb': 'ltz',
+ 'lg': 'lug',
+ 'li': 'lim',
+ 'ln': 'lin',
+ 'lo': 'lao',
+ 'lt': 'lit',
+ 'lu': 'lub',
+ 'lv': 'lav',
+ 'mg': 'mlg',
+ 'mh': 'mah',
+ 'mi': 'mri',
+ 'mk': 'mkd',
+ 'ml': 'mal',
+ 'mn': 'mon',
+ 'mr': 'mar',
+ 'ms': 'msa',
+ 'mt': 'mlt',
+ 'my': 'mya',
+ 'na': 'nau',
+ 'nb': 'nob',
+ 'nd': 'nde',
+ 'ne': 'nep',
+ 'ng': 'ndo',
+ 'nl': 'nld',
+ 'nn': 'nno',
+ 'no': 'nor',
+ 'nr': 'nbl',
+ 'nv': 'nav',
+ 'ny': 'nya',
+ 'oc': 'oci',
+ 'oj': 'oji',
+ 'om': 'orm',
+ 'or': 'ori',
+ 'os': 'oss',
+ 'pa': 'pan',
+ 'pi': 'pli',
+ 'pl': 'pol',
+ 'ps': 'pus',
+ 'pt': 'por',
+ 'qu': 'que',
+ 'rm': 'roh',
+ 'rn': 'run',
+ 'ro': 'ron',
+ 'ru': 'rus',
+ 'rw': 'kin',
+ 'sa': 'san',
+ 'sc': 'srd',
+ 'sd': 'snd',
+ 'se': 'sme',
+ 'sg': 'sag',
+ 'si': 'sin',
+ 'sk': 'slk',
+ 'sl': 'slv',
+ 'sm': 'smo',
+ 'sn': 'sna',
+ 'so': 'som',
+ 'sq': 'sqi',
+ 'sr': 'srp',
+ 'ss': 'ssw',
+ 'st': 'sot',
+ 'su': 'sun',
+ 'sv': 'swe',
+ 'sw': 'swa',
+ 'ta': 'tam',
+ 'te': 'tel',
+ 'tg': 'tgk',
+ 'th': 'tha',
+ 'ti': 'tir',
+ 'tk': 'tuk',
+ 'tl': 'tgl',
+ 'tn': 'tsn',
+ 'to': 'ton',
+ 'tr': 'tur',
+ 'ts': 'tso',
+ 'tt': 'tat',
+ 'tw': 'twi',
+ 'ty': 'tah',
+ 'ug': 'uig',
+ 'uk': 'ukr',
+ 'ur': 'urd',
+ 'uz': 'uzb',
+ 've': 'ven',
+ 'vi': 'vie',
+ 'vo': 'vol',
+ 'wa': 'wln',
+ 'wo': 'wol',
+ 'xh': 'xho',
+ 'yi': 'yid',
+ 'yo': 'yor',
+ 'za': 'zha',
+ 'zh': 'zho',
+ 'zu': 'zul',
+ }
+
+ @classmethod
+ def short2long(cls, code):
+ """Convert language code from ISO 639-1 to ISO 639-2/T"""
+ return cls._lang_map.get(code[:2])
+
+ @classmethod
+ def long2short(cls, code):
+ """Convert language code from ISO 639-2/T to ISO 639-1"""
+ for short_name, long_name in cls._lang_map.items():
+ if long_name == code:
+ return short_name
+
+
+class ISO3166Utils(object):
+ # From http://data.okfn.org/data/core/country-list
+ _country_map = {
+ 'AF': 'Afghanistan',
+ 'AX': 'Åland Islands',
+ 'AL': 'Albania',
+ 'DZ': 'Algeria',
+ 'AS': 'American Samoa',
+ 'AD': 'Andorra',
+ 'AO': 'Angola',
+ 'AI': 'Anguilla',
+ 'AQ': 'Antarctica',
+ 'AG': 'Antigua and Barbuda',
+ 'AR': 'Argentina',
+ 'AM': 'Armenia',
+ 'AW': 'Aruba',
+ 'AU': 'Australia',
+ 'AT': 'Austria',
+ 'AZ': 'Azerbaijan',
+ 'BS': 'Bahamas',
+ 'BH': 'Bahrain',
+ 'BD': 'Bangladesh',
+ 'BB': 'Barbados',
+ 'BY': 'Belarus',
+ 'BE': 'Belgium',
+ 'BZ': 'Belize',
+ 'BJ': 'Benin',
+ 'BM': 'Bermuda',
+ 'BT': 'Bhutan',
+ 'BO': 'Bolivia, Plurinational State of',
+ 'BQ': 'Bonaire, Sint Eustatius and Saba',
+ 'BA': 'Bosnia and Herzegovina',
+ 'BW': 'Botswana',
+ 'BV': 'Bouvet Island',
+ 'BR': 'Brazil',
+ 'IO': 'British Indian Ocean Territory',
+ 'BN': 'Brunei Darussalam',
+ 'BG': 'Bulgaria',
+ 'BF': 'Burkina Faso',
+ 'BI': 'Burundi',
+ 'KH': 'Cambodia',
+ 'CM': 'Cameroon',
+ 'CA': 'Canada',
+ 'CV': 'Cape Verde',
+ 'KY': 'Cayman Islands',
+ 'CF': 'Central African Republic',
+ 'TD': 'Chad',
+ 'CL': 'Chile',
+ 'CN': 'China',
+ 'CX': 'Christmas Island',
+ 'CC': 'Cocos (Keeling) Islands',
+ 'CO': 'Colombia',
+ 'KM': 'Comoros',
+ 'CG': 'Congo',
+ 'CD': 'Congo, the Democratic Republic of the',
+ 'CK': 'Cook Islands',
+ 'CR': 'Costa Rica',
+ 'CI': 'Côte d\'Ivoire',
+ 'HR': 'Croatia',
+ 'CU': 'Cuba',
+ 'CW': 'Curaçao',
+ 'CY': 'Cyprus',
+ 'CZ': 'Czech Republic',
+ 'DK': 'Denmark',
+ 'DJ': 'Djibouti',
+ 'DM': 'Dominica',
+ 'DO': 'Dominican Republic',
+ 'EC': 'Ecuador',
+ 'EG': 'Egypt',
+ 'SV': 'El Salvador',
+ 'GQ': 'Equatorial Guinea',
+ 'ER': 'Eritrea',
+ 'EE': 'Estonia',
+ 'ET': 'Ethiopia',
+ 'FK': 'Falkland Islands (Malvinas)',
+ 'FO': 'Faroe Islands',
+ 'FJ': 'Fiji',
+ 'FI': 'Finland',
+ 'FR': 'France',
+ 'GF': 'French Guiana',
+ 'PF': 'French Polynesia',
+ 'TF': 'French Southern Territories',
+ 'GA': 'Gabon',
+ 'GM': 'Gambia',
+ 'GE': 'Georgia',
+ 'DE': 'Germany',
+ 'GH': 'Ghana',
+ 'GI': 'Gibraltar',
+ 'GR': 'Greece',
+ 'GL': 'Greenland',
+ 'GD': 'Grenada',
+ 'GP': 'Guadeloupe',
+ 'GU': 'Guam',
+ 'GT': 'Guatemala',
+ 'GG': 'Guernsey',
+ 'GN': 'Guinea',
+ 'GW': 'Guinea-Bissau',
+ 'GY': 'Guyana',
+ 'HT': 'Haiti',
+ 'HM': 'Heard Island and McDonald Islands',
+ 'VA': 'Holy See (Vatican City State)',
+ 'HN': 'Honduras',
+ 'HK': 'Hong Kong',
+ 'HU': 'Hungary',
+ 'IS': 'Iceland',
+ 'IN': 'India',
+ 'ID': 'Indonesia',
+ 'IR': 'Iran, Islamic Republic of',
+ 'IQ': 'Iraq',
+ 'IE': 'Ireland',
+ 'IM': 'Isle of Man',
+ 'IL': 'Israel',
+ 'IT': 'Italy',
+ 'JM': 'Jamaica',
+ 'JP': 'Japan',
+ 'JE': 'Jersey',
+ 'JO': 'Jordan',
+ 'KZ': 'Kazakhstan',
+ 'KE': 'Kenya',
+ 'KI': 'Kiribati',
+ 'KP': 'Korea, Democratic People\'s Republic of',
+ 'KR': 'Korea, Republic of',
+ 'KW': 'Kuwait',
+ 'KG': 'Kyrgyzstan',
+ 'LA': 'Lao People\'s Democratic Republic',
+ 'LV': 'Latvia',
+ 'LB': 'Lebanon',
+ 'LS': 'Lesotho',
+ 'LR': 'Liberia',
+ 'LY': 'Libya',
+ 'LI': 'Liechtenstein',
+ 'LT': 'Lithuania',
+ 'LU': 'Luxembourg',
+ 'MO': 'Macao',
+ 'MK': 'Macedonia, the Former Yugoslav Republic of',
+ 'MG': 'Madagascar',
+ 'MW': 'Malawi',
+ 'MY': 'Malaysia',
+ 'MV': 'Maldives',
+ 'ML': 'Mali',
+ 'MT': 'Malta',
+ 'MH': 'Marshall Islands',
+ 'MQ': 'Martinique',
+ 'MR': 'Mauritania',
+ 'MU': 'Mauritius',
+ 'YT': 'Mayotte',
+ 'MX': 'Mexico',
+ 'FM': 'Micronesia, Federated States of',
+ 'MD': 'Moldova, Republic of',
+ 'MC': 'Monaco',
+ 'MN': 'Mongolia',
+ 'ME': 'Montenegro',
+ 'MS': 'Montserrat',
+ 'MA': 'Morocco',
+ 'MZ': 'Mozambique',
+ 'MM': 'Myanmar',
+ 'NA': 'Namibia',
+ 'NR': 'Nauru',
+ 'NP': 'Nepal',
+ 'NL': 'Netherlands',
+ 'NC': 'New Caledonia',
+ 'NZ': 'New Zealand',
+ 'NI': 'Nicaragua',
+ 'NE': 'Niger',
+ 'NG': 'Nigeria',
+ 'NU': 'Niue',
+ 'NF': 'Norfolk Island',
+ 'MP': 'Northern Mariana Islands',
+ 'NO': 'Norway',
+ 'OM': 'Oman',
+ 'PK': 'Pakistan',
+ 'PW': 'Palau',
+ 'PS': 'Palestine, State of',
+ 'PA': 'Panama',
+ 'PG': 'Papua New Guinea',
+ 'PY': 'Paraguay',
+ 'PE': 'Peru',
+ 'PH': 'Philippines',
+ 'PN': 'Pitcairn',
+ 'PL': 'Poland',
+ 'PT': 'Portugal',
+ 'PR': 'Puerto Rico',
+ 'QA': 'Qatar',
+ 'RE': 'Réunion',
+ 'RO': 'Romania',
+ 'RU': 'Russian Federation',
+ 'RW': 'Rwanda',
+ 'BL': 'Saint Barthélemy',
+ 'SH': 'Saint Helena, Ascension and Tristan da Cunha',
+ 'KN': 'Saint Kitts and Nevis',
+ 'LC': 'Saint Lucia',
+ 'MF': 'Saint Martin (French part)',
+ 'PM': 'Saint Pierre and Miquelon',
+ 'VC': 'Saint Vincent and the Grenadines',
+ 'WS': 'Samoa',
+ 'SM': 'San Marino',
+ 'ST': 'Sao Tome and Principe',
+ 'SA': 'Saudi Arabia',
+ 'SN': 'Senegal',
+ 'RS': 'Serbia',
+ 'SC': 'Seychelles',
+ 'SL': 'Sierra Leone',
+ 'SG': 'Singapore',
+ 'SX': 'Sint Maarten (Dutch part)',
+ 'SK': 'Slovakia',
+ 'SI': 'Slovenia',
+ 'SB': 'Solomon Islands',
+ 'SO': 'Somalia',
+ 'ZA': 'South Africa',
+ 'GS': 'South Georgia and the South Sandwich Islands',
+ 'SS': 'South Sudan',
+ 'ES': 'Spain',
+ 'LK': 'Sri Lanka',
+ 'SD': 'Sudan',
+ 'SR': 'Suriname',
+ 'SJ': 'Svalbard and Jan Mayen',
+ 'SZ': 'Swaziland',
+ 'SE': 'Sweden',
+ 'CH': 'Switzerland',
+ 'SY': 'Syrian Arab Republic',
+ 'TW': 'Taiwan, Province of China',
+ 'TJ': 'Tajikistan',
+ 'TZ': 'Tanzania, United Republic of',
+ 'TH': 'Thailand',
+ 'TL': 'Timor-Leste',
+ 'TG': 'Togo',
+ 'TK': 'Tokelau',
+ 'TO': 'Tonga',
+ 'TT': 'Trinidad and Tobago',
+ 'TN': 'Tunisia',
+ 'TR': 'Turkey',
+ 'TM': 'Turkmenistan',
+ 'TC': 'Turks and Caicos Islands',
+ 'TV': 'Tuvalu',
+ 'UG': 'Uganda',
+ 'UA': 'Ukraine',
+ 'AE': 'United Arab Emirates',
+ 'GB': 'United Kingdom',
+ 'US': 'United States',
+ 'UM': 'United States Minor Outlying Islands',
+ 'UY': 'Uruguay',
+ 'UZ': 'Uzbekistan',
+ 'VU': 'Vanuatu',
+ 'VE': 'Venezuela, Bolivarian Republic of',
+ 'VN': 'Viet Nam',
+ 'VG': 'Virgin Islands, British',
+ 'VI': 'Virgin Islands, U.S.',
+ 'WF': 'Wallis and Futuna',
+ 'EH': 'Western Sahara',
+ 'YE': 'Yemen',
+ 'ZM': 'Zambia',
+ 'ZW': 'Zimbabwe',
+ }
+
+ @classmethod
+ def short2full(cls, code):
+ """Convert an ISO 3166-2 country code to the corresponding full name"""
+ return cls._country_map.get(code.upper())
+
+
class PerRequestProxyHandler(compat_urllib_request.ProxyHandler):
def __init__(self, proxies=None):
# Set default handlers
from __future__ import unicode_literals
-__version__ = '2015.06.04.1'
+__version__ = '2015.07.07'