Tithen-Firion
Zack Fernandes
cryptonaut
+Adrian Kretz
all: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish
clean:
- rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish *.dump *.part
+ rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish *.dump *.part *.info.json
cleanall: clean
rm -f youtube-dl youtube-dl.exe
self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
self.assertEqual(unified_strdate('1968-12-10'), '19681210')
self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
+ self.assertEqual(
+ unified_strdate('11/26/2014 11:30:00 AM PST', day_first=False),
+ '20141126')
def test_find_xpath_attr(self):
testxml = '''<root>
ie_result['url'], ie_key=ie_result.get('ie_key'),
extra_info=extra_info, download=False, process=False)
- def make_result(embedded_info):
- new_result = ie_result.copy()
- for f in ('_type', 'url', 'ext', 'player_url', 'formats',
- 'entries', 'ie_key', 'duration',
- 'subtitles', 'annotations', 'format',
- 'thumbnail', 'thumbnails'):
- if f in new_result:
- del new_result[f]
- if f in embedded_info:
- new_result[f] = embedded_info[f]
- return new_result
- new_result = make_result(info)
+ new_result = ie_result.copy()
+ for f in ('_type', 'id', 'url', 'ext', 'player_url', 'formats',
+ 'entries', 'ie_key', 'duration',
+ 'subtitles', 'annotations', 'format',
+ 'thumbnail', 'thumbnails'):
+ if f in new_result:
+ del new_result[f]
+ if f in info:
+ new_result[f] = info[f]
assert new_result.get('_type') != 'url_transparent'
- if new_result.get('_type') == 'compat_list':
- new_result['entries'] = [
- make_result(e) for e in new_result['entries']]
return self.process_ie_result(
new_result, download=download, extra_info=extra_info)
if self.params.get('forceid', False):
self.to_stdout(info_dict['id'])
if self.params.get('forceurl', False):
- # For RTMP URLs, also include the playpath
- self.to_stdout(info_dict['url'] + info_dict.get('play_path', ''))
+ if info_dict.get('requested_formats') is not None:
+ for f in info_dict['requested_formats']:
+ self.to_stdout(f['url'] + f.get('play_path', ''))
+ else:
+ # For RTMP URLs, also include the playpath
+ self.to_stdout(info_dict['url'] + info_dict.get('play_path', ''))
if self.params.get('forcethumbnail', False) and info_dict.get('thumbnail') is not None:
self.to_stdout(info_dict['thumbnail'])
if self.params.get('forcedescription', False) and info_dict.get('description') is not None:
userhome = compat_getenv('HOME')
elif 'USERPROFILE' in os.environ:
userhome = compat_getenv('USERPROFILE')
- elif not 'HOMEPATH' in os.environ:
+ elif 'HOMEPATH' not in os.environ:
return path
else:
try:
from .bbccouk import BBCCoUkIE
from .beeg import BeegIE
from .behindkink import BehindKinkIE
+from .bet import BetIE
from .bild import BildIE
from .bilibili import BiliBiliIE
from .blinkx import BlinkxIE
from .ceskatelevize import CeskaTelevizeIE
from .channel9 import Channel9IE
from .chilloutzone import ChilloutzoneIE
-from .cinemassacre import CinemassacreIE
+from .cinchcast import CinchcastIE
from .clipfish import ClipfishIE
from .cliphunter import CliphunterIE
from .clipsyndicate import ClipsyndicateIE
from .prosiebensat1 import ProSiebenSat1IE
from .pyvideo import PyvideoIE
from .quickvid import QuickVidIE
+from .radiode import RadioDeIE
from .radiofrance import RadioFranceIE
from .rai import RaiIE
from .rbmaradio import RBMARadioIE
from .sbs import SBSIE
from .scivee import SciVeeIE
from .screencast import ScreencastIE
+from .screenwavemedia import CinemassacreIE, ScreenwaveMediaIE, TeamFourIE
from .servingsys import ServingSysIE
from .sexu import SexuIE
from .sexykarma import SexyKarmaIE
YoutubeUserIE,
YoutubeWatchLaterIE,
)
-from .zdf import ZDFIE
+from .zdf import ZDFIE, ZDFChannelIE
from .zingmp3 import (
ZingMp3SongIE,
ZingMp3AlbumIE,
class BehindKinkIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?behindkink\.com/(?P<year>[0-9]{4})/(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<id>[^/#?_]+)'
_TEST = {
- 'url': 'http://www.behindkink.com/2014/08/14/ab1576-performers-voice-finally-heard-the-bill-is-killed/',
- 'md5': '41ad01222b8442089a55528fec43ec01',
+ 'url': 'http://www.behindkink.com/2014/12/05/what-are-you-passionate-about-marley-blaze/',
+ 'md5': '507b57d8fdcd75a41a9a7bdb7989c762',
'info_dict': {
- 'id': '36370',
+ 'id': '37127',
'ext': 'mp4',
- 'title': 'AB1576 - PERFORMERS VOICE FINALLY HEARD - THE BILL IS KILLED!',
- 'description': 'The adult industry voice was finally heard as Assembly Bill 1576 remained\xa0 in suspense today at the Senate Appropriations Hearing. AB1576 was, among other industry damaging issues, a condom mandate...',
- 'upload_date': '20140814',
- 'thumbnail': 'http://www.behindkink.com/wp-content/uploads/2014/08/36370_AB1576_Win.jpg',
+ 'title': 'What are you passionate about – Marley Blaze',
+ 'description': 'md5:aee8e9611b4ff70186f752975d9b94b4',
+ 'upload_date': '20141205',
+ 'thumbnail': 'http://www.behindkink.com/wp-content/uploads/2014/12/blaze-1.jpg',
'age_limit': 18,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('id')
- year = mobj.group('year')
- month = mobj.group('month')
- day = mobj.group('day')
- upload_date = year + month + day
webpage = self._download_webpage(url, display_id)
video_url = self._search_regex(
- r"'file':\s*'([^']+)'",
- webpage, 'URL base')
-
- video_id = url_basename(video_url)
- video_id = video_id.split('_')[0]
+ r'<source src="([^"]+)"', webpage, 'video URL')
+ video_id = url_basename(video_url).split('_')[0]
+ upload_date = mobj.group('year') + mobj.group('month') + mobj.group('day')
return {
'id': video_id,
+ 'display_id': display_id,
'url': video_url,
- 'ext': 'mp4',
'title': self._og_search_title(webpage),
- 'display_id': display_id,
'thumbnail': self._og_search_thumbnail(webpage),
'description': self._og_search_description(webpage),
'upload_date': upload_date,
--- /dev/null
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_urllib_parse,
+ xpath_text,
+ xpath_with_ns,
+ int_or_none,
+ parse_iso8601,
+)
+
+
+class BetIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?bet\.com/(?:[^/]+/)+(?P<id>.+?)\.html'
+ _TESTS = [
+ {
+ 'url': 'http://www.bet.com/news/politics/2014/12/08/in-bet-exclusive-obama-talks-race-and-racism.html',
+ 'info_dict': {
+ 'id': '417cd61c-c793-4e8e-b006-e445ecc45add',
+ 'display_id': 'in-bet-exclusive-obama-talks-race-and-racism',
+ 'ext': 'flv',
+ 'title': 'BET News Presents: A Conversation With President Obama',
+ 'description': 'md5:5a88d8ae912c1b33e090290af7ec33c6',
+ 'duration': 1534,
+ 'timestamp': 1418075340,
+ 'upload_date': '20141208',
+ 'uploader': 'admin',
+ 'thumbnail': 're:(?i)^https?://.*\.jpg$',
+ },
+ 'params': {
+ # rtmp download
+ 'skip_download': True,
+ },
+ },
+ {
+ 'url': 'http://www.bet.com/video/news/national/2014/justice-for-ferguson-a-community-reacts.html',
+ 'info_dict': {
+ 'id': '4160e53b-ad41-43b1-980f-8d85f63121f4',
+ 'display_id': 'justice-for-ferguson-a-community-reacts',
+ 'ext': 'flv',
+ 'title': 'Justice for Ferguson: A Community Reacts',
+ 'description': 'A BET News special.',
+ 'duration': 1696,
+ 'timestamp': 1416942360,
+ 'upload_date': '20141125',
+ 'uploader': 'admin',
+ 'thumbnail': 're:(?i)^https?://.*\.jpg$',
+ },
+ 'params': {
+ # rtmp download
+ 'skip_download': True,
+ },
+ }
+ ]
+
+ def _real_extract(self, url):
+ display_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, display_id)
+
+ media_url = compat_urllib_parse.unquote(self._search_regex(
+ [r'mediaURL\s*:\s*"([^"]+)"', r"var\s+mrssMediaUrl\s*=\s*'([^']+)'"],
+ webpage, 'media URL'))
+
+ mrss = self._download_xml(media_url, display_id)
+
+ item = mrss.find('./channel/item')
+
+ NS_MAP = {
+ 'dc': 'http://purl.org/dc/elements/1.1/',
+ 'media': 'http://search.yahoo.com/mrss/',
+ 'ka': 'http://kickapps.com/karss',
+ }
+
+ title = xpath_text(item, './title', 'title')
+ description = xpath_text(
+ item, './description', 'description', fatal=False)
+
+ video_id = xpath_text(item, './guid', 'video id', fatal=False)
+
+ timestamp = parse_iso8601(xpath_text(
+ item, xpath_with_ns('./dc:date', NS_MAP),
+ 'upload date', fatal=False))
+ uploader = xpath_text(
+ item, xpath_with_ns('./dc:creator', NS_MAP),
+ 'uploader', fatal=False)
+
+ media_content = item.find(
+ xpath_with_ns('./media:content', NS_MAP))
+ duration = int_or_none(media_content.get('duration'))
+ smil_url = media_content.get('url')
+
+ thumbnail = media_content.find(
+ xpath_with_ns('./media:thumbnail', NS_MAP)).get('url')
+
+ formats = self._extract_smil_formats(smil_url, display_id)
+
+ return {
+ 'id': video_id,
+ 'display_id': display_id,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'timestamp': timestamp,
+ 'uploader': uploader,
+ 'duration': duration,
+ 'formats': formats,
+ }
from .common import InfoExtractor
from .subtitles import SubtitlesInfoExtractor
-from ..utils import (
+
+from ..compat import (
+ compat_str,
compat_urllib_request,
- unescapeHTML,
- parse_iso8601,
compat_urlparse,
+)
+from ..utils import (
clean_html,
- compat_str,
+ int_or_none,
+ parse_iso8601,
+ unescapeHTML,
)
'uploader': 'NostalgiaCritic',
'uploader_id': '246467',
}
- }
+ },
+ {
+ # https://github.com/rg3/youtube-dl/pull/4404
+ 'note': 'Audio only',
+ 'url': 'http://blip.tv/hilarios-productions/weekly-manga-recap-kingdom-7119982',
+ 'md5': '76c0a56f24e769ceaab21fbb6416a351',
+ 'info_dict': {
+ 'id': '7103299',
+ 'ext': 'flv',
+ 'title': 'Weekly Manga Recap: Kingdom',
+ 'description': 'And then Shin breaks the enemy line, and he's all like HWAH! And then he slices a guy and it's all like FWASHING! And... it's really hard to describe the best parts of this series without breaking down into sound effects, okay?',
+ 'timestamp': 1417660321,
+ 'upload_date': '20141204',
+ 'uploader': 'The Rollo T',
+ 'uploader_id': '407429',
+ 'duration': 7251,
+ 'vcodec': 'none',
+ }
+ },
]
def _real_extract(self, url):
'url': real_url,
'format_id': role,
'format_note': media_type,
- 'vcodec': media_content.get(blip('vcodec')),
+ 'vcodec': media_content.get(blip('vcodec')) or 'none',
'acodec': media_content.get(blip('acodec')),
'filesize': media_content.get('filesize'),
- 'width': int(media_content.get('width')),
- 'height': int(media_content.get('height')),
+ 'width': int_or_none(media_content.get('width')),
+ 'height': int_or_none(media_content.get('height')),
})
self._sort_formats(formats)
--- /dev/null
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+ unified_strdate,
+ xpath_text,
+)
+
+
+class CinchcastIE(InfoExtractor):
+ _VALID_URL = r'https?://player\.cinchcast\.com/.*?assetId=(?P<id>[0-9]+)'
+ _TEST = {
+ # Actual test is run in generic, look for undergroundwellness
+ 'url': 'http://player.cinchcast.com/?platformId=1&assetType=single&assetId=7141703',
+ 'only_matching': True,
+ }
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ doc = self._download_xml(
+ 'http://www.blogtalkradio.com/playerasset/mrss?assetType=single&assetId=%s' % video_id,
+ video_id)
+
+ item = doc.find('.//item')
+ title = xpath_text(item, './title', fatal=True)
+ date_str = xpath_text(
+ item, './{http://developer.longtailvideo.com/trac/}date')
+ upload_date = unified_strdate(date_str, day_first=False)
+ # duration is present but wrong
+ formats = []
+ formats.append({
+ 'format_id': 'main',
+ 'url': item.find(
+ './{http://search.yahoo.com/mrss/}content').attrib['url'],
+ })
+ backup_url = xpath_text(
+ item, './{http://developer.longtailvideo.com/trac/}backupContent')
+ if backup_url:
+ formats.append({
+ 'preference': 2, # seems to be more reliable
+ 'format_id': 'backup',
+ 'url': backup_url,
+ })
+ self._sort_formats(formats)
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'upload_date': upload_date,
+ 'formats': formats,
+ }
+++ /dev/null
-# encoding: utf-8
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..utils import (
- ExtractorError,
- int_or_none,
-)
-
-
-class CinemassacreIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?cinemassacre\.com/(?P<date_Y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/(?P<display_id>[^?#/]+)'
- _TESTS = [
- {
- 'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
- 'md5': 'fde81fbafaee331785f58cd6c0d46190',
- 'info_dict': {
- 'id': '19911',
- 'ext': 'mp4',
- 'upload_date': '20121110',
- 'title': '“Angry Video Game Nerd: The Movie” – Trailer',
- 'description': 'md5:fb87405fcb42a331742a0dce2708560b',
- },
- },
- {
- 'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
- 'md5': 'd72f10cd39eac4215048f62ab477a511',
- 'info_dict': {
- 'id': '521be8ef82b16',
- 'ext': 'mp4',
- 'upload_date': '20131002',
- 'title': 'The Mummy’s Hand (1940)',
- },
- }
- ]
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- display_id = mobj.group('display_id')
-
- webpage = self._download_webpage(url, display_id)
- video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d')
- mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=(?P<full_video_id>(?:Cinemassacre-)?(?P<video_id>.+?)))"', webpage)
- if not mobj:
- raise ExtractorError('Can\'t extract embed url and video id')
- playerdata_url = mobj.group('embed_url')
- video_id = mobj.group('video_id')
- full_video_id = mobj.group('full_video_id')
-
- video_title = self._html_search_regex(
- r'<title>(?P<title>.+?)\|', webpage, 'title')
- video_description = self._html_search_regex(
- r'<div class="entry-content">(?P<description>.+?)</div>',
- webpage, 'description', flags=re.DOTALL, fatal=False)
- video_thumbnail = self._og_search_thumbnail(webpage)
-
- playerdata = self._download_webpage(playerdata_url, video_id, 'Downloading player webpage')
-
- vidurl = self._search_regex(
- r'\'vidurl\'\s*:\s*"([^\']+)"', playerdata, 'vidurl').replace('\\/', '/')
-
- videolist_url = None
-
- mobj = re.search(r"'videoserver'\s*:\s*'(?P<videoserver>[^']+)'", playerdata)
- if mobj:
- videoserver = mobj.group('videoserver')
- mobj = re.search(r'\'vidid\'\s*:\s*"(?P<vidid>[^\']+)"', playerdata)
- vidid = mobj.group('vidid') if mobj else full_video_id
- videolist_url = 'http://%s/vod/smil:%s.smil/jwplayer.smil' % (videoserver, vidid)
- else:
- mobj = re.search(r"file\s*:\s*'(?P<smil>http.+?/jwplayer\.smil)'", playerdata)
- if mobj:
- videolist_url = mobj.group('smil')
-
- if videolist_url:
- videolist = self._download_xml(videolist_url, video_id, 'Downloading videolist XML')
- formats = []
- baseurl = vidurl[:vidurl.rfind('/') + 1]
- for video in videolist.findall('.//video'):
- src = video.get('src')
- if not src:
- continue
- file_ = src.partition(':')[-1]
- width = int_or_none(video.get('width'))
- height = int_or_none(video.get('height'))
- bitrate = int_or_none(video.get('system-bitrate'))
- format = {
- 'url': baseurl + file_,
- 'format_id': src.rpartition('.')[0].rpartition('_')[-1],
- }
- if width or height:
- format.update({
- 'tbr': bitrate // 1000 if bitrate else None,
- 'width': width,
- 'height': height,
- })
- else:
- format.update({
- 'abr': bitrate // 1000 if bitrate else None,
- 'vcodec': 'none',
- })
- formats.append(format)
- self._sort_formats(formats)
- else:
- formats = [{
- 'url': vidurl,
- }]
-
- return {
- 'id': video_id,
- 'title': video_title,
- 'formats': formats,
- 'description': video_description,
- 'upload_date': video_date,
- 'thumbnail': video_thumbnail,
- }
The following fields are optional:
+ alt_title: A secondary title of the video.
display_id An alternative identifier for the video, not necessarily
unique, but available before title. Typically, id is
something like "4234987", title "Dancing naked mole rats",
* "resolution" (optional, string "{width}x{height"},
deprecated)
thumbnail: Full URL to a video thumbnail image.
- description: One-line video description.
+ description: Full video description.
uploader: Full name of the video uploader.
timestamp: UNIX timestamp of the moment the video became available.
upload_date: Video upload date (YYYYMMDD).
_type "url" indicates that the video must be extracted from another
location, possibly by a different extractor. Its only required key is:
"url" - the next URL to extract.
-
- Additionally, it may have properties believed to be identical to the
- resolved entity, for example "title" if the title of the referred video is
+ The key "ie_key" can be set to the class name (minus the trailing "IE",
+ e.g. "Youtube") if the extractor class is known in advance.
+ Additionally, the dictionary may have any properties of the resolved entity
+ known in advance, for example "title" if the title of the referred video is
known ahead of time.
url_or_request, video_id, note, errnote, fatal=fatal)
if (not fatal) and json_string is False:
return None
+ return self._parse_json(
+ json_string, video_id, transform_source=transform_source, fatal=fatal)
+
+ def _parse_json(self, json_string, video_id, transform_source=None, fatal=True):
if transform_source:
json_string = transform_source(json_string)
try:
return video_info
@staticmethod
- def playlist_result(entries, playlist_id=None, playlist_title=None):
+ def playlist_result(entries, playlist_id=None, playlist_title=None, playlist_description=None):
"""Returns a playlist"""
video_info = {'_type': 'playlist',
'entries': entries}
video_info['id'] = playlist_id
if playlist_title:
video_info['title'] = playlist_title
+ if playlist_description:
+ video_info['description'] = playlist_description
return video_info
def _search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None):
self._sort_formats(formats)
return formats
+ # TODO: improve extraction
+ def _extract_smil_formats(self, smil_url, video_id):
+ smil = self._download_xml(
+ smil_url, video_id, 'Downloading SMIL file',
+ 'Unable to download SMIL file')
+
+ base = smil.find('./head/meta').get('base')
+
+ formats = []
+ rtmp_count = 0
+ for video in smil.findall('./body/switch/video'):
+ src = video.get('src')
+ if not src:
+ continue
+ bitrate = int_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000)
+ width = int_or_none(video.get('width'))
+ height = int_or_none(video.get('height'))
+ proto = video.get('proto')
+ if not proto:
+ if base:
+ if base.startswith('rtmp'):
+ proto = 'rtmp'
+ elif base.startswith('http'):
+ proto = 'http'
+ ext = video.get('ext')
+ if proto == 'm3u8':
+ formats.extend(self._extract_m3u8_formats(src, video_id, ext))
+ elif proto == 'rtmp':
+ rtmp_count += 1
+ streamer = video.get('streamer') or base
+ formats.append({
+ 'url': streamer,
+ 'play_path': src,
+ 'ext': 'flv',
+ 'format_id': 'rtmp-%d' % (rtmp_count if bitrate is None else bitrate),
+ 'tbr': bitrate,
+ 'width': width,
+ 'height': height,
+ })
+ self._sort_formats(formats)
+
+ return formats
+
def _live_title(self, name):
""" Generate the title for a live video """
now = datetime.datetime.now()
compat_urllib_request,
)
from ..utils import (
- urlencode_postdata,
ExtractorError,
+ int_or_none,
limit_length,
+ urlencode_postdata,
)
'info_dict': {
'id': '637842556329505',
'ext': 'mp4',
- 'duration': 38,
'title': 're:Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam',
}
}, {
self._login()
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
+ video_id = self._match_id(url)
url = 'https://www.facebook.com/video/video.php?v=%s' % video_id
webpage = self._download_webpage(url, video_id)
'id': video_id,
'title': video_title,
'url': video_url,
- 'duration': int(video_data['video_duration']),
- 'thumbnail': video_data['thumbnail_src'],
+ 'duration': int_or_none(video_data.get('video_duration')),
+ 'thumbnail': video_data.get('thumbnail_src'),
}
'expected_warnings': [
'URL could be a direct video link, returning it as such.'
]
- }
-
+ },
+ # Cinchcast embed
+ {
+ 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
+ 'info_dict': {
+ 'id': '7141703',
+ 'ext': 'mp3',
+ 'upload_date': '20141126',
+ 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
+ }
+ },
]
def report_following_redirect(self, new_url):
if mobj is not None:
return self.url_result(mobj.group('url'), 'SBS')
+ # Look for embedded Cinchcast player
+ mobj = re.search(
+ r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
+ webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'), 'Cinchcast')
+
mobj = re.search(
r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
webpage)
from __future__ import unicode_literals
-import re
-import json
-import random
-import string
-
from .common import InfoExtractor
-from ..utils import find_xpath_attr
+from ..utils import (
+ find_xpath_attr,
+ int_or_none,
+ js_to_json,
+ unescapeHTML,
+)
class HowStuffWorksIE(InfoExtractor):
'url': 'http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm',
'info_dict': {
'id': '450221',
- 'display_id': 'cool-jobs-iditarod-musher',
'ext': 'flv',
'title': 'Cool Jobs - Iditarod Musher',
- 'description': 'md5:82bb58438a88027b8186a1fccb365f90',
+ 'description': 'Cold sleds, freezing temps and warm dog breath... an Iditarod musher\'s dream. Kasey-Dee Gardner jumps on a sled to find out what the big deal is.',
+ 'display_id': 'cool-jobs-iditarod-musher',
'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 161,
},
- 'params': {
- # md5 is not consistent
- 'skip_download': True
- }
},
{
'url': 'http://adventure.howstuffworks.com/7199-survival-zone-food-and-water-in-the-savanna-video.htm',
'info_dict': {
'id': '453464',
- 'display_id': 'survival-zone-food-and-water-in-the-savanna',
'ext': 'mp4',
'title': 'Survival Zone: Food and Water In the Savanna',
- 'description': 'md5:7e1c89f6411434970c15fa094170c371',
+ 'description': 'Learn how to find both food and water while trekking in the African savannah. In this video from the Discovery Channel.',
+ 'display_id': 'survival-zone-food-and-water-in-the-savanna',
'thumbnail': 're:^https?://.*\.jpg$',
},
- 'params': {
- # md5 is not consistent
- 'skip_download': True
- }
},
{
'url': 'http://entertainment.howstuffworks.com/arts/2706-sword-swallowing-1-by-dan-meyer-video.htm',
'info_dict': {
'id': '440011',
- 'display_id': 'sword-swallowing-1-by-dan-meyer',
'ext': 'flv',
'title': 'Sword Swallowing #1 by Dan Meyer',
- 'description': 'md5:b2409e88172913e2e7d3d1159b0ef735',
+ 'description': 'Video footage (1 of 3) used by permission of the owner Dan Meyer through Sword Swallowers Association International <www.swordswallow.org>',
+ 'display_id': 'sword-swallowing-1-by-dan-meyer',
'thumbnail': 're:^https?://.*\.jpg$',
},
- 'params': {
- # md5 is not consistent
- 'skip_download': True
- }
},
]
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- display_id = mobj.group('id')
+ display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
+ clip_js = self._search_regex(
+ r'(?s)var clip = ({.*?});', webpage, 'clip info')
+ clip_info = self._parse_json(
+ clip_js, display_id, transform_source=js_to_json)
- content_id = self._search_regex(r'var siteSectionId="(\d+)";', webpage, 'content id')
-
- mp4 = self._search_regex(
- r'''(?xs)var\s+clip\s*=\s*{\s*
- .+?\s*
- content_id\s*:\s*%s\s*,\s*
- .+?\s*
- mp4\s*:\s*\[(.*?),?\]\s*
- };\s*
- videoData\.push\(clip\);''' % content_id,
- webpage, 'mp4', fatal=False, default=None)
-
- smil = self._download_xml(
- 'http://services.media.howstuffworks.com/videos/%s/smil-service.smil' % content_id,
- content_id, 'Downloading video SMIL')
-
- http_base = find_xpath_attr(
- smil,
- './{0}head/{0}meta'.format('{http://www.w3.org/2001/SMIL20/Language}'),
- 'name',
- 'httpBase').get('content')
-
- def random_string(str_len=0):
- return ''.join([random.choice(string.ascii_uppercase) for _ in range(str_len)])
-
- URL_SUFFIX = '?v=2.11.3&fp=LNX 11,2,202,356&r=%s&g=%s' % (random_string(5), random_string(12))
-
+ video_id = clip_info['content_id']
formats = []
+ m3u8_url = clip_info.get('m3u8')
+ if m3u8_url:
+ formats += self._extract_m3u8_formats(m3u8_url, video_id, 'mp4')
+ for video in clip_info.get('mp4', []):
+ formats.append({
+ 'url': video['src'],
+ 'format_id': video['bitrate'],
+ 'vbr': int(video['bitrate'].rstrip('k')),
+ })
+
+ if not formats:
+ smil = self._download_xml(
+ 'http://services.media.howstuffworks.com/videos/%s/smil-service.smil' % video_id,
+ video_id, 'Downloading video SMIL')
+
+ http_base = find_xpath_attr(
+ smil,
+ './{0}head/{0}meta'.format('{http://www.w3.org/2001/SMIL20/Language}'),
+ 'name',
+ 'httpBase').get('content')
+
+ URL_SUFFIX = '?v=2.11.3&fp=LNX 11,2,202,356&r=A&g=A'
- if mp4:
- for video in json.loads('[%s]' % mp4):
- bitrate = video['bitrate']
- fmt = {
- 'url': video['src'].replace('http://pmd.video.howstuffworks.com', http_base) + URL_SUFFIX,
- 'format_id': bitrate,
- }
- m = re.search(r'(?P<vbr>\d+)[Kk]', bitrate)
- if m:
- fmt['vbr'] = int(m.group('vbr'))
- formats.append(fmt)
- else:
for video in smil.findall(
- './/{0}body/{0}switch/{0}video'.format('{http://www.w3.org/2001/SMIL20/Language}')):
- vbr = int(video.attrib['system-bitrate']) / 1000
+ './{0}body/{0}switch/{0}video'.format('{http://www.w3.org/2001/SMIL20/Language}')):
+ vbr = int_or_none(video.attrib['system-bitrate'], scale=1000)
formats.append({
'url': '%s/%s%s' % (http_base, video.attrib['src'], URL_SUFFIX),
'format_id': '%dk' % vbr,
self._sort_formats(formats)
- title = self._og_search_title(webpage)
- TITLE_SUFFIX = ' : HowStuffWorks'
- if title.endswith(TITLE_SUFFIX):
- title = title[:-len(TITLE_SUFFIX)]
-
- description = self._og_search_description(webpage)
- thumbnail = self._og_search_thumbnail(webpage)
-
return {
- 'id': content_id,
+ 'id': '%s' % video_id,
'display_id': display_id,
- 'title': title,
- 'description': description,
- 'thumbnail': thumbnail,
+ 'title': unescapeHTML(clip_info['clip_title']),
+ 'description': unescapeHTML(clip_info.get('caption')),
+ 'thumbnail': clip_info.get('video_still_url'),
+ 'duration': clip_info.get('duration'),
'formats': formats,
}
raise ExtractorError('Unable to extract track url')
PREFIX = (
- r'<div class="cloudcast-play-button-container[^"]*?"'
+ r'<span class="play-button[^"]*?"'
r'(?:\s+[a-zA-Z0-9-]+(?:="[^"]+")?)*?\s+')
title = self._html_search_regex(
PREFIX + r'm-title="([^"]+)"', webpage, 'title')
import re
import json
+import os
from .common import InfoExtractor
from ..compat import (
initial_video_url = info['publishPoint']
if info['formats'] == '1':
parsed_url = compat_urllib_parse_urlparse(initial_video_url)
- path = parsed_url.path.replace('.', '_sd.', 1)
+ filename, ext = os.path.splitext(parsed_url.path)
+ path = '%s_sd%s' % (filename, ext)
data = compat_urllib_parse.urlencode({
'type': 'fvod',
'path': compat_urlparse.urlunparse(parsed_url[:2] + (path,) + parsed_url[3:])
'rtmp_conn': 'B:1',
'player_url': 'http://www.ntv.ru/swf/vps1.swf?update=20131128',
'page_url': 'http://www.ntv.ru',
- 'flash_ver': 'LNX 11,2,202,341',
+ 'flash_version': 'LNX 11,2,202,341',
'rtmp_live': True,
'ext': 'flv',
'filesize': int(size.text),
int_or_none,
js_to_json,
qualities,
- determine_ext,
)
thumbnail = self._search_regex(
r"'poster'\s*:\s*'([^']+)'", webpage, 'thumbnail', fatal=False)
- quality = qualities(['SD', 'HD'])
- formats = [{
- 'url': source['file'],
- 'format_id': '%s-%s' % (source['label'], determine_ext(source['file'])),
- 'quality': quality(source['label']),
- } for source in json.loads(js_to_json(self._search_regex(
- r"(?s)'sources'\s*:\s*(\[.+?\])", webpage, 'sources')))]
+ quality = qualities(['sd', 'hd'])
+ sources = json.loads(js_to_json(self._search_regex(
+ r"(?s)'sources'\s*:\s*(\{.+?\})\s*\}\);", webpage, 'sources')))
+ formats = []
+ for container, s in sources.items():
+ for qname, video_url in s.items():
+ formats.append({
+ 'url': video_url,
+ 'container': container,
+ 'format_id': '%s-%s' % (container, qname),
+ 'quality': quality(qname),
+ })
self._sort_formats(formats)
return {
'ext': 'mp4',
'title': 'Im Interview: Kai Wiesinger',
'description': 'md5:e4e5370652ec63b95023e914190b4eb9',
- 'upload_date': '20140225',
+ 'upload_date': '20140203',
'duration': 522.56,
},
'params': {
'ext': 'mp4',
'title': 'Jagd auf Fertigkost im Elsthal - Teil 2',
'description': 'md5:2669cde3febe9bce13904f701e774eb6',
- 'upload_date': '20140225',
+ 'upload_date': '20141014',
'duration': 2410.44,
},
'params': {
'skip_download': True,
},
},
+ {
+ 'url': 'http://www.prosieben.de/tv/joko-gegen-klaas/videos/playlists/episode-8-ganze-folge-playlist',
+ 'info_dict': {
+ 'id': '439664',
+ 'title': 'Episode 8 - Ganze Folge - Playlist',
+ 'description': 'md5:63b8963e71f481782aeea877658dec84',
+ },
+ 'playlist_count': 2,
+ },
]
_CLIPID_REGEXES = [
r'"clip_id"\s*:\s+"(\d+)"',
r'clipid: "(\d+)"',
r'clip[iI]d=(\d+)',
+ r"'itemImageUrl'\s*:\s*'/dynamic/thumbnails/full/\d+/(\d+)",
]
_TITLE_REGEXES = [
r'<h2 class="subtitle" itemprop="name">\s*(.+?)</h2>',
r'<span style="padding-left: 4px;line-height:20px; color:#404040">(\d{2}\.\d{2}\.\d{4})</span>',
r'(\d{2}\.\d{2}\.\d{4}) \| \d{2}:\d{2} Min<br/>',
]
+ _PAGE_TYPE_REGEXES = [
+ r'<meta name="page_type" content="([^"]+)">',
+ r"'itemType'\s*:\s*'([^']*)'",
+ ]
+ _PLAYLIST_ID_REGEXES = [
+ r'content[iI]d=(\d+)',
+ r"'itemId'\s*:\s*'([^']*)'",
+ ]
+ _PLAYLIST_CLIP_REGEXES = [
+ r'(?s)data-qvt=.+?<a href="([^"]+)"',
+ ]
- def _real_extract(self, url):
- video_id = self._match_id(url)
- webpage = self._download_webpage(url, video_id)
-
+ def _extract_clip(self, url, webpage):
clip_id = self._html_search_regex(self._CLIPID_REGEXES, webpage, 'clip id')
access_token = 'testclient'
'duration': duration,
'formats': formats,
}
+
+ def _extract_playlist(self, url, webpage):
+ playlist_id = self._html_search_regex(
+ self._PLAYLIST_ID_REGEXES, webpage, 'playlist id')
+ for regex in self._PLAYLIST_CLIP_REGEXES:
+ playlist_clips = re.findall(regex, webpage)
+ if playlist_clips:
+ title = self._html_search_regex(
+ self._TITLE_REGEXES, webpage, 'title')
+ description = self._html_search_regex(
+ self._DESCRIPTION_REGEXES, webpage, 'description', fatal=False)
+ entries = [
+ self.url_result(
+ re.match('(.+?//.+?)/', url).group(1) + clip_path,
+ 'ProSiebenSat1')
+ for clip_path in playlist_clips]
+ return self.playlist_result(entries, playlist_id, title, description)
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_id)
+ page_type = self._search_regex(
+ self._PAGE_TYPE_REGEXES, webpage,
+ 'page type', default='clip').lower()
+ if page_type == 'clip':
+ return self._extract_clip(url, webpage)
+ elif page_type == 'playlist':
+ return self._extract_playlist(url, webpage)
--- /dev/null
+from __future__ import unicode_literals
+
+import json
+
+from .common import InfoExtractor
+
+
+class RadioDeIE(InfoExtractor):
+ IE_NAME = 'radio.de'
+ _VALID_URL = r'https?://(?P<id>.+?)\.(?:radio\.(?:de|at|fr|pt|es|pl|it)|rad\.io)'
+ _TEST = {
+ 'url': 'http://ndr2.radio.de/',
+ 'md5': '3b4cdd011bc59174596b6145cda474a4',
+ 'info_dict': {
+ 'id': 'ndr2',
+ 'ext': 'mp3',
+ 'title': 're:^NDR 2 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+ 'description': 'md5:591c49c702db1a33751625ebfb67f273',
+ 'thumbnail': 're:^https?://.*\.png',
+ },
+ 'params': {
+ 'skip_download': True,
+ }
+ }
+
+ def _real_extract(self, url):
+ radio_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, radio_id)
+
+ broadcast = json.loads(self._search_regex(
+ r'_getBroadcast\s*=\s*function\(\s*\)\s*{\s*return\s+({.+?})\s*;\s*}',
+ webpage, 'broadcast'))
+
+ title = self._live_title(broadcast['name'])
+ description = broadcast.get('description') or broadcast.get('shortDescription')
+ thumbnail = broadcast.get('picture4Url') or broadcast.get('picture4TransUrl')
+
+ formats = [{
+ 'url': stream['streamUrl'],
+ 'ext': stream['streamContentFormat'].lower(),
+ 'acodec': stream['streamContentFormat'],
+ 'abr': stream['bitRate'],
+ 'asr': stream['sampleRate']
+ } for stream in broadcast['streamUrls']]
+ self._sort_formats(formats)
+
+ return {
+ 'id': radio_id,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'is_live': True,
+ 'formats': formats,
+ }
--- /dev/null
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ int_or_none,
+ unified_strdate,
+)
+
+
+class ScreenwaveMediaIE(InfoExtractor):
+ _VALID_URL = r'http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=(?P<id>.+)'
+
+ _TESTS = [{
+ 'url': 'http://player.screenwavemedia.com/play/play.php?playerdiv=videoarea&companiondiv=squareAd&id=Cinemassacre-19911',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ playerdata = self._download_webpage(url, video_id, 'Downloading player webpage')
+
+ vidtitle = self._search_regex(
+ r'\'vidtitle\'\s*:\s*"([^"]+)"', playerdata, 'vidtitle').replace('\\/', '/')
+ vidurl = self._search_regex(
+ r'\'vidurl\'\s*:\s*"([^"]+)"', playerdata, 'vidurl').replace('\\/', '/')
+
+ videolist_url = None
+
+ mobj = re.search(r"'videoserver'\s*:\s*'(?P<videoserver>[^']+)'", playerdata)
+ if mobj:
+ videoserver = mobj.group('videoserver')
+ mobj = re.search(r'\'vidid\'\s*:\s*"(?P<vidid>[^\']+)"', playerdata)
+ vidid = mobj.group('vidid') if mobj else video_id
+ videolist_url = 'http://%s/vod/smil:%s.smil/jwplayer.smil' % (videoserver, vidid)
+ else:
+ mobj = re.search(r"file\s*:\s*'(?P<smil>http.+?/jwplayer\.smil)'", playerdata)
+ if mobj:
+ videolist_url = mobj.group('smil')
+
+ if videolist_url:
+ videolist = self._download_xml(videolist_url, video_id, 'Downloading videolist XML')
+ formats = []
+ baseurl = vidurl[:vidurl.rfind('/') + 1]
+ for video in videolist.findall('.//video'):
+ src = video.get('src')
+ if not src:
+ continue
+ file_ = src.partition(':')[-1]
+ width = int_or_none(video.get('width'))
+ height = int_or_none(video.get('height'))
+ bitrate = int_or_none(video.get('system-bitrate'), scale=1000)
+ format = {
+ 'url': baseurl + file_,
+ 'format_id': src.rpartition('.')[0].rpartition('_')[-1],
+ }
+ if width or height:
+ format.update({
+ 'tbr': bitrate,
+ 'width': width,
+ 'height': height,
+ })
+ else:
+ format.update({
+ 'abr': bitrate,
+ 'vcodec': 'none',
+ })
+ formats.append(format)
+ else:
+ formats = [{
+ 'url': vidurl,
+ }]
+ self._sort_formats(formats)
+
+ return {
+ 'id': video_id,
+ 'title': vidtitle,
+ 'formats': formats,
+ }
+
+
+class CinemassacreIE(InfoExtractor):
+ _VALID_URL = 'https?://(?:www\.)?cinemassacre\.com/(?P<date_y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/(?P<display_id>[^?#/]+)'
+ _TESTS = [
+ {
+ 'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
+ 'md5': 'fde81fbafaee331785f58cd6c0d46190',
+ 'info_dict': {
+ 'id': 'Cinemassacre-19911',
+ 'ext': 'mp4',
+ 'upload_date': '20121110',
+ 'title': '“Angry Video Game Nerd: The Movie” – Trailer',
+ 'description': 'md5:fb87405fcb42a331742a0dce2708560b',
+ },
+ },
+ {
+ 'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
+ 'md5': 'd72f10cd39eac4215048f62ab477a511',
+ 'info_dict': {
+ 'id': 'Cinemassacre-521be8ef82b16',
+ 'ext': 'mp4',
+ 'upload_date': '20131002',
+ 'title': 'The Mummy’s Hand (1940)',
+ },
+ }
+ ]
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ display_id = mobj.group('display_id')
+ video_date = mobj.group('date_y') + mobj.group('date_m') + mobj.group('date_d')
+
+ webpage = self._download_webpage(url, display_id)
+
+ playerdata_url = self._search_regex(
+ r'src="(http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"',
+ webpage, 'player data URL')
+ video_title = self._html_search_regex(
+ r'<title>(?P<title>.+?)\|', webpage, 'title')
+ video_description = self._html_search_regex(
+ r'<div class="entry-content">(?P<description>.+?)</div>',
+ webpage, 'description', flags=re.DOTALL, fatal=False)
+ video_thumbnail = self._og_search_thumbnail(webpage)
+
+ return {
+ '_type': 'url_transparent',
+ 'display_id': display_id,
+ 'title': video_title,
+ 'description': video_description,
+ 'upload_date': video_date,
+ 'thumbnail': video_thumbnail,
+ 'url': playerdata_url,
+ }
+
+
+class TeamFourIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?teamfourstar\.com/video/(?P<id>[a-z0-9\-]+)/?'
+ _TEST = {
+ 'url': 'http://teamfourstar.com/video/a-moment-with-tfs-episode-4/',
+ 'info_dict': {
+ 'id': 'TeamFourStar-5292a02f20bfa',
+ 'ext': 'mp4',
+ 'upload_date': '20130401',
+ 'description': 'Check out this and more on our website: http://teamfourstar.com\nTFS Store: http://sharkrobot.com/team-four-star\nFollow on Twitter: http://twitter.com/teamfourstar\nLike on FB: http://facebook.com/teamfourstar',
+ 'title': 'A Moment With TFS Episode 4',
+ }
+ }
+
+ def _real_extract(self, url):
+ display_id = self._match_id(url)
+ webpage = self._download_webpage(url, display_id)
+
+ playerdata_url = self._search_regex(
+ r'src="(http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"',
+ webpage, 'player data URL')
+
+ video_title = self._html_search_regex(
+ r'<div class="heroheadingtitle">(?P<title>.+?)</div>',
+ webpage, 'title')
+ video_date = unified_strdate(self._html_search_regex(
+ r'<div class="heroheadingdate">(?P<date>.+?)</div>',
+ webpage, 'date', fatal=False))
+ video_description = self._html_search_regex(
+ r'(?s)<div class="postcontent">(?P<description>.+?)</div>',
+ webpage, 'description', fatal=False)
+ video_thumbnail = self._og_search_thumbnail(webpage)
+
+ return {
+ '_type': 'url_transparent',
+ 'display_id': display_id,
+ 'title': video_title,
+ 'description': video_description,
+ 'upload_date': video_date,
+ 'thumbnail': video_thumbnail,
+ 'url': playerdata_url,
+ }
broadcast_page = self._download_webpage(broadcast_url, broadcast_id, 'Downloading broadcast page')
if re.search('>Режиссер с логином <br/>"%s"<br/> <span>не существует<' % broadcast_id, broadcast_page) is not None:
- raise ExtractorError('Broadcast %s does not exist' % broadcast_id, expected=True)
+ raise ExtractorError(
+ 'Broadcast %s does not exist' % broadcast_id, expected=True)
# Adult content
if re.search('EroConfirmText">', broadcast_page) is not None:
(username, password) = self._get_login_info()
if username is None:
- raise ExtractorError('Erotic broadcasts allowed only for registered users, '
- 'use --username and --password options to provide account credentials.', expected=True)
+ raise ExtractorError(
+ 'Erotic broadcasts allowed only for registered users, '
+ 'use --username and --password options to provide account credentials.',
+ expected=True)
login_form = {
'login-hint53': '1',
'password': password,
}
- request = compat_urllib_request.Request(broadcast_url + '/?no_redirect=1', compat_urllib_parse.urlencode(login_form))
+ request = compat_urllib_request.Request(
+ broadcast_url + '/?no_redirect=1', compat_urllib_parse.urlencode(login_form))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
- broadcast_page = self._download_webpage(request, broadcast_id, 'Logging in and confirming age')
+ broadcast_page = self._download_webpage(
+ request, broadcast_id, 'Logging in and confirming age')
if re.search('>Неверный логин или пароль<', broadcast_page) is not None:
raise ExtractorError('Unable to log in: bad username or password', expected=True)
adult_content = False
ticket = self._html_search_regex(
- 'window\.broadcast_control\.addFlashVar\\(\'file\', \'([^\']+)\'\\);',
+ r"window\.broadcast_control\.addFlashVar\('file'\s*,\s*'([^']+)'\)",
broadcast_page, 'broadcast ticket')
url = 'http://smotri.com/broadcast/view/url/?ticket=%s' % ticket
if broadcast_password:
url += '&pass=%s' % hashlib.md5(broadcast_password.encode('utf-8')).hexdigest()
- broadcast_json_page = self._download_webpage(url, broadcast_id, 'Downloading broadcast JSON')
+ broadcast_json_page = self._download_webpage(
+ url, broadcast_id, 'Downloading broadcast JSON')
try:
broadcast_json = json.loads(broadcast_json_page)
protected_broadcast = broadcast_json['_pass_protected'] == 1
if protected_broadcast and not broadcast_password:
- raise ExtractorError('This broadcast is protected by a password, use the --video-password option', expected=True)
+ raise ExtractorError(
+ 'This broadcast is protected by a password, use the --video-password option',
+ expected=True)
broadcast_offline = broadcast_json['is_play'] == 0
if broadcast_offline:
raise ExtractorError('Broadcast %s is offline' % broadcast_id, expected=True)
rtmp_url = broadcast_json['_server']
- if not rtmp_url.startswith('rtmp://'):
+ mobj = re.search(r'^rtmp://[^/]+/(?P<app>.+)/?$', rtmp_url)
+ if not mobj:
raise ExtractorError('Unexpected broadcast rtmp URL')
broadcast_playpath = broadcast_json['_streamName']
+ broadcast_app = '%s/%s' % (mobj.group('app'), broadcast_json['_vidURL'])
broadcast_thumbnail = broadcast_json['_imgURL']
- broadcast_title = broadcast_json['title']
+ broadcast_title = self._live_title(broadcast_json['title'])
broadcast_description = broadcast_json['description']
broadcaster_nick = broadcast_json['nick']
broadcaster_login = broadcast_json['login']
'age_limit': 18 if adult_content else 0,
'ext': 'flv',
'play_path': broadcast_playpath,
+ 'player_url': 'http://pics.smotri.com/broadcast_play.swf',
+ 'app': broadcast_app,
'rtmp_live': True,
- 'rtmp_conn': rtmp_conn
+ 'rtmp_conn': rtmp_conn,
+ 'is_live': True,
}
# encoding: utf-8
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
from ..utils import (
float_or_none,
- str_to_int,
+ parse_age_limit,
)
class TvigleIE(InfoExtractor):
IE_NAME = 'tvigle'
IE_DESC = 'Интернет-телевидение Tvigle.ru'
- _VALID_URL = r'http://(?:www\.)?tvigle\.ru/(?:[^/]+/)+(?P<display_id>[^/]+)/$'
+ _VALID_URL = r'http://(?:www\.)?tvigle\.ru/(?:[^/]+/)+(?P<id>[^/]+)/$'
_TESTS = [
{
- 'url': 'http://www.tvigle.ru/video/brat/',
- 'md5': 'ff4344a4894b0524441fb6f8218dc716',
+ 'url': 'http://www.tvigle.ru/video/sokrat/',
+ 'md5': '36514aed3657d4f70b4b2cef8eb520cd',
'info_dict': {
- 'id': '5118490',
- 'display_id': 'brat',
- 'ext': 'mp4',
- 'title': 'Ð\91рат',
- 'description': 'md5:d16ac7c0b47052ea51fddb92c4e413eb',
- 'duration': 5722.6,
- 'age_limit': 16,
+ 'id': '1848932',
+ 'display_id': 'sokrat',
+ 'ext': 'flv',
+ 'title': 'Сократ',
+ 'description': 'md5:a05bd01be310074d5833efc6743be95e',
+ 'duration': 6586,
+ 'age_limit': 0,
},
},
{
]
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- display_id = mobj.group('display_id')
+ display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
title = item['title']
description = item['description']
thumbnail = item['thumbnail']
- duration = float_or_none(item['durationMilliseconds'], 1000)
- age_limit = str_to_int(item['ageRestrictions'])
+ duration = float_or_none(item.get('durationMilliseconds'), 1000)
+ age_limit = parse_age_limit(item.get('ageRestrictions'))
formats = []
for vcodec, fmts in item['videos'].items():
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
- ExtractorError,
parse_iso8601,
qualities,
)
'http://playapi.mtgx.tv/v1/videos/%s' % video_id, video_id, 'Downloading video JSON')
if video['is_geo_blocked']:
- raise ExtractorError(
- 'This content is not available in your country due to copyright reasons', expected=True)
+ self.report_warning(
+ 'This content might not be available in your country due to copyright reasons')
streams = self._download_json(
'http://playapi.mtgx.tv/v1/videos/stream/%s' % video_id, video_id, 'Downloading streams JSON')
+# coding: utf-8
from __future__ import unicode_literals
import itertools
from .common import InfoExtractor
from ..utils import (
+ compat_urllib_parse,
+ compat_urllib_request,
ExtractorError,
parse_iso8601,
)
"""
_PAGE_LIMIT = 100
_API_BASE = 'https://api.twitch.tv'
+ _LOGIN_URL = 'https://secure.twitch.tv/user/login'
_TESTS = [{
'url': 'http://www.twitch.tv/riotgames/b/577357806',
'info_dict': {
'view_count': info['views'],
}
+ def _real_initialize(self):
+ self._login()
+
+ def _login(self):
+ (username, password) = self._get_login_info()
+ if username is None:
+ return
+
+ 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': '',
+ 'follow': '',
+ 'user[login]': username,
+ 'user[password]': password,
+ }
+
+ request = compat_urllib_request.Request(
+ self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
+ request.add_header('Referer', self._LOGIN_URL)
+ 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:
+ raise ExtractorError(
+ 'Unable to login: %s' % m.group('msg').strip(), expected=True)
+
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj.group('chapterid'):
'id': 'b9KOOWX7HUx',
'ext': 'mp4',
'title': 'Chicken.',
+ 'alt_title': 'Vine by Jack Dorsey',
'description': 'Chicken.',
'upload_date': '20130519',
'uploader': 'Jack Dorsey',
}
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('https://vine.co/v/' + video_id, video_id)
data = json.loads(self._html_search_regex(
r'window\.POST_DATA = { %s: ({.+?}) }' % video_id, webpage, 'vine data'))
- formats = [
- {
- 'url': data['videoLowURL'],
- 'ext': 'mp4',
- 'format_id': 'low',
- },
- {
- 'url': data['videoUrl'],
- 'ext': 'mp4',
- 'format_id': 'standard',
- }
- ]
+ formats = [{
+ 'url': data['videoLowURL'],
+ 'ext': 'mp4',
+ 'format_id': 'low',
+ }, {
+ 'url': data['videoUrl'],
+ 'ext': 'mp4',
+ 'format_id': 'standard',
+ }]
return {
'id': video_id,
'title': self._og_search_title(webpage),
+ 'alt_title': self._og_search_description(webpage),
'description': data['description'],
'thumbnail': data['thumbnailUrl'],
'upload_date': unified_strdate(data['created']),
from .subtitles import SubtitlesInfoExtractor
from ..jsinterp import JSInterpreter
from ..swfinterp import SWFInterpreter
-from ..utils import (
+from ..compat import (
compat_chr,
compat_parse_qs,
compat_urllib_parse,
compat_urllib_request,
compat_urlparse,
compat_str,
-
+)
+from ..utils import (
clean_html,
- get_element_by_id,
- get_element_by_attribute,
ExtractorError,
+ get_element_by_attribute,
+ get_element_by_id,
int_or_none,
OnDemandPagedList,
+ orderedSet,
unescapeHTML,
unified_strdate,
- orderedSet,
uppercase_escape,
)
'upload_date': '20140605',
},
},
+ # video_info is None (https://github.com/rg3/youtube-dl/issues/4421)
+ {
+ 'url': '__2ABJjxzNo',
+ 'info_dict': {
+ 'id': '__2ABJjxzNo',
+ 'ext': 'mp4',
+ 'upload_date': '20100430',
+ 'uploader_id': 'deadmau5',
+ 'description': 'md5:12c56784b8032162bb936a5f76d55360',
+ 'uploader': 'deadmau5',
+ 'title': 'Deadmau5 - Some Chords (HD)',
+ },
+ 'expected_warnings': [
+ 'DASH manifest missing',
+ ]
+ },
+ # Olympics (https://github.com/rg3/youtube-dl/issues/4431)
+ {
+ 'url': 'lqQg6PlCWgI',
+ 'info_dict': {
+ 'id': 'lqQg6PlCWgI',
+ 'ext': 'mp4',
+ 'upload_date': '20120731',
+ 'uploader_id': 'olympic',
+ 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
+ 'uploader': 'Olympics',
+ 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
+ },
+ 'params': {
+ 'skip_download': 'requires avconv',
+ }
+ },
]
def __init__(self, *args, **kwargs):
url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
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):
+ def decrypt_sig(mobj):
+ s = mobj.group(1)
+ dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
+ return '/signature/%s' % dec_s
+ dash_manifest_url = re.sub(r'/s/([\w\.]+)', decrypt_sig, dash_manifest_url)
+ dash_doc = self._download_xml(
+ dash_manifest_url, video_id,
+ note='Downloading DASH manifest',
+ errnote='Could not download DASH manifest')
+
+ formats = []
+ for r in dash_doc.findall('.//{urn:mpeg:DASH:schema:MPD:2011}Representation'):
+ url_el = r.find('{urn:mpeg:DASH:schema:MPD:2011}BaseURL')
+ if url_el is None:
+ continue
+ format_id = r.attrib['id']
+ video_url = url_el.text
+ filesize = int_or_none(url_el.attrib.get('{http://youtube.com/yt/2012/10/10}contentLength'))
+ f = {
+ 'format_id': format_id,
+ 'url': video_url,
+ 'width': int_or_none(r.attrib.get('width')),
+ 'tbr': int_or_none(r.attrib.get('bandwidth'), 1000),
+ 'asr': int_or_none(r.attrib.get('audioSamplingRate')),
+ 'filesize': filesize,
+ 'fps': int_or_none(r.attrib.get('frameRate')),
+ }
+ try:
+ existing_format = next(
+ fo for fo in formats
+ if fo['format_id'] == format_id)
+ except StopIteration:
+ f.update(self._formats.get(format_id, {}))
+ formats.append(f)
+ else:
+ existing_format.update(f)
+ return formats
+
def _real_extract(self, url):
proto = (
'http' if self._downloader.params.get('prefer_insecure', False)
m_cat_container = self._search_regex(
r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
- video_webpage, 'categories', fatal=False)
+ video_webpage, 'categories', default=None)
if m_cat_container:
category = self._html_search_regex(
r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
'url': video_info['conn'][0],
'player_url': player_url,
}]
- elif len(video_info.get('url_encoded_fmt_stream_map', [])) >= 1 or len(video_info.get('adaptive_fmts', [])) >= 1:
+ elif len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1:
encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0]
if 'rtmpe%3Dyes' in encoded_url_map:
raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True)
# Look for the DASH manifest
if self._downloader.params.get('youtube_include_dash_manifest', True):
- try:
- # The DASH manifest used needs to be the one from the original video_webpage.
- # The one found in get_video_info seems to be using different signatures.
- # However, in the case of an age restriction there won't be any embedded dashmpd in the video_webpage.
- # Luckily, it seems, this case uses some kind of default signature (len == 86), so the
- # combination of get_video_info and the _static_decrypt_signature() decryption fallback will work here.
- dash_manifest_url = video_info.get('dashmpd')[0]
-
- def decrypt_sig(mobj):
- s = mobj.group(1)
- dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
- return '/signature/%s' % dec_s
- dash_manifest_url = re.sub(r'/s/([\w\.]+)', decrypt_sig, dash_manifest_url)
- dash_doc = self._download_xml(
- dash_manifest_url, video_id,
- note='Downloading DASH manifest',
- errnote='Could not download DASH manifest')
- for r in dash_doc.findall('.//{urn:mpeg:DASH:schema:MPD:2011}Representation'):
- url_el = r.find('{urn:mpeg:DASH:schema:MPD:2011}BaseURL')
- if url_el is None:
- continue
- format_id = r.attrib['id']
- video_url = url_el.text
- filesize = int_or_none(url_el.attrib.get('{http://youtube.com/yt/2012/10/10}contentLength'))
- f = {
- 'format_id': format_id,
- 'url': video_url,
- 'width': int_or_none(r.attrib.get('width')),
- 'tbr': int_or_none(r.attrib.get('bandwidth'), 1000),
- 'asr': int_or_none(r.attrib.get('audioSamplingRate')),
- 'filesize': filesize,
- 'fps': int_or_none(r.attrib.get('frameRate')),
- }
- try:
- existing_format = next(
- fo for fo in formats
- if fo['format_id'] == format_id)
- except StopIteration:
- f.update(self._formats.get(format_id, {}))
- formats.append(f)
- else:
- existing_format.update(f)
-
- except (ExtractorError, KeyError) as e:
- self.report_warning('Skipping DASH manifest: %r' % e, video_id)
+ dash_mpd = video_info.get('dashmpd')
+ if dash_mpd:
+ dash_manifest_url = dash_mpd[0]
+ try:
+ dash_formats = self._parse_dash_manifest(
+ video_id, dash_manifest_url, player_url, age_gate)
+ except (ExtractorError, KeyError) as e:
+ self.report_warning(
+ 'Skipping DASH manifest: %r' % e, video_id)
+ else:
+ formats.extend(dash_formats)
self._sort_formats(formats)
# coding: utf-8
from __future__ import unicode_literals
+import functools
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
unified_strdate,
+ OnDemandPagedList,
)
class ZDFIE(InfoExtractor):
- _VALID_URL = r'^https?://www\.zdf\.de/ZDFmediathek(?P<hash>#)?/(.*beitrag/(?:video/)?)(?P<id>[0-9]+)(?:/[^/?]+)?(?:\?.*)?'
+ _VALID_URL = r'(?:zdf:|zdf:video:|https?://www\.zdf\.de/ZDFmediathek(?:#)?/(.*beitrag/(?:video/)?))(?P<id>[0-9]+)(?:/[^/?]+)?(?:\?.*)?'
_TEST = {
'url': 'http://www.zdf.de/ZDFmediathek/beitrag/video/2037704/ZDFspezial---Ende-des-Machtpokers--?bc=sts;stt',
def _real_extract(self, url):
video_id = self._match_id(url)
-
xml_url = 'http://www.zdf.de/ZDFmediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id
return extract_from_xml_url(self, video_id, xml_url)
+
+
+class ZDFChannelIE(InfoExtractor):
+ _VALID_URL = r'(?:zdf:topic:|https?://www\.zdf\.de/ZDFmediathek(?:#)?/.*kanaluebersicht/)(?P<id>[0-9]+)'
+ _TEST = {
+ 'url': 'http://www.zdf.de/ZDFmediathek#/kanaluebersicht/1586442/sendung/Titanic',
+ 'info_dict': {
+ 'id': '1586442',
+ },
+ 'playlist_count': 4,
+ }
+ _PAGE_SIZE = 50
+
+ def _fetch_page(self, channel_id, page):
+ offset = page * self._PAGE_SIZE
+ xml_url = (
+ 'http://www.zdf.de/ZDFmediathek/xmlservice/web/aktuellste?ak=web&offset=%d&maxLength=%d&id=%s'
+ % (offset, self._PAGE_SIZE, channel_id))
+ doc = self._download_xml(
+ xml_url, channel_id,
+ note='Downloading channel info',
+ errnote='Failed to download channel info')
+
+ title = doc.find('.//information/title').text
+ description = doc.find('.//information/detail').text
+ for asset in doc.findall('.//teasers/teaser'):
+ a_type = asset.find('./type').text
+ a_id = asset.find('./details/assetId').text
+ if a_type not in ('video', 'topic'):
+ continue
+ yield {
+ '_type': 'url',
+ 'playlist_title': title,
+ 'playlist_description': description,
+ 'url': 'zdf:%s:%s' % (a_type, a_id),
+ }
+
+ def _real_extract(self, url):
+ channel_id = self._match_id(url)
+ entries = OnDemandPagedList(
+ functools.partial(self._fetch_page, channel_id), self._PAGE_SIZE)
+
+ return {
+ '_type': 'playlist',
+ 'id': channel_id,
+ 'entries': entries,
+ }
def run(self, information):
cmd = self.exec_cmd
- if not '{}' in cmd:
+ if '{}' not in cmd:
cmd += ' {}'
cmd = cmd.replace('{}', shlex_quote(information['filepath']))
to_screen(compat_str(traceback.format_exc()))
to_screen('ERROR: can\'t obtain versions info. Please try again later.')
return
- if not 'signature' in versions_info:
+ if 'signature' not in versions_info:
to_screen('ERROR: the versions file is not signed or corrupted. Aborting.')
return
signature = versions_info['signature']
xpath = xpath.encode('ascii')
n = node.find(xpath)
- if n is None:
+ if n is None or n.text is None:
if fatal:
name = xpath if name is None else name
raise ExtractorError('Could not find XML element %s' % name)
return calendar.timegm(dt.timetuple())
-def unified_strdate(date_str):
+def unified_strdate(date_str, day_first=True):
"""Return a string with the date in the format YYYYMMDD"""
if date_str is None:
return None
-
upload_date = None
# Replace commas
date_str = date_str.replace(',', ' ')
# %z (UTC offset) is only supported in python>=3.2
date_str = re.sub(r' ?(\+|-)[0-9]{2}:?[0-9]{2}$', '', date_str)
+ # Remove AM/PM + timezone
+ date_str = re.sub(r'(?i)\s*(?:AM|PM)\s+[A-Z]+', '', date_str)
+
format_expressions = [
'%d %B %Y',
'%d %b %Y',
'%d/%m/%Y',
'%d/%m/%y',
'%Y/%m/%d %H:%M:%S',
- '%d/%m/%Y %H:%M:%S',
'%Y-%m-%d %H:%M:%S',
'%Y-%m-%d %H:%M:%S.%f',
'%d.%m.%Y %H:%M',
'%Y-%m-%dT%H:%M:%S.%f',
'%Y-%m-%dT%H:%M',
]
+ if day_first:
+ format_expressions.extend([
+ '%d/%m/%Y %H:%M:%S',
+ ])
+ else:
+ format_expressions.extend([
+ '%m/%d/%Y %H:%M:%S',
+ ])
for expression in format_expressions:
try:
upload_date = datetime.datetime.strptime(date_str, expression).strftime('%Y%m%d')
Return a datetime object from a string in the format YYYYMMDD or
(now|today)[+-][0-9](day|week|month|year)(s)?"""
today = datetime.date.today()
- if date_str == 'now'or date_str == 'today':
+ if date_str in ('now', 'today'):
return today
+ if date_str == 'yesterday':
+ return today - datetime.timedelta(days=1)
match = re.match('(now|today)(?P<sign>[+-])(?P<time>\d+)(?P<unit>day|week|month|year)(s)?', date_str)
if match is not None:
sign = match.group('sign')
def unsmuggle_url(smug_url, default=None):
- if not '#__youtubedl_smuggle' in smug_url:
+ if '#__youtubedl_smuggle' not in smug_url:
return smug_url, default
url, _, sdata = smug_url.rpartition('#')
jsond = compat_parse_qs(sdata)['__youtubedl_smuggle'][0]
from __future__ import unicode_literals
-__version__ = '2014.12.06.1'
+__version__ = '2014.12.12.1'
projects / youtube-dl / commitdiff