from __future__ import absolute_import
+import base64
import datetime
+import itertools
import netrc
import os
import re
import xml.etree.ElementTree
import random
import math
+import operator
from .utils import *
url: Final video URL.
title: Video title, unescaped.
ext: Video filename extension.
- uploader: Full name of the video uploader.
- upload_date: Video upload date (YYYYMMDD).
The following fields are optional:
format: The video format, defaults to ext (used for --get-format)
thumbnail: Full URL to a video thumbnail image.
description: One-line video description.
+ uploader: Full name of the video uploader.
+ upload_date: Video upload date (YYYYMMDD).
uploader_id: Nickname or id of the video uploader.
+ location: Physical location of the video.
player_url: SWF Player URL (used for rtmpdump).
subtitles: The .srt file contents.
urlhandle: [internal] The urlHandle to be used to download the file,
self._ready = False
self.set_downloader(downloader)
- def suitable(self, url):
+ @classmethod
+ def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE."""
- return re.match(self._VALID_URL, url) is not None
+ return re.match(cls._VALID_URL, url) is not None
- def working(self):
+ @classmethod
+ def working(cls):
"""Getter method for _WORKING."""
- return self._WORKING
+ return cls._WORKING
def initialize(self):
"""Initializes an instance (authentication, etc)."""
def IE_NAME(self):
return type(self).__name__[:-2]
+ def _request_webpage(self, url_or_request, video_id, note=None, errnote=None):
+ """ Returns the response handle """
+ if note is None:
+ note = u'Downloading video webpage'
+ self._downloader.to_screen(u'[%s] %s: %s' % (self.IE_NAME, video_id, note))
+ try:
+ return compat_urllib_request.urlopen(url_or_request)
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ if errnote is None:
+ errnote = u'Unable to download webpage'
+ raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2])
+
+ def _download_webpage(self, url_or_request, video_id, note=None, errnote=None):
+ """ Returns the data of the page as a string """
+ urlh = self._request_webpage(url_or_request, video_id, note, errnote)
+ webpage_bytes = urlh.read()
+ return webpage_bytes.decode('utf-8', 'replace')
+
+
class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com."""
(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|
tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains
(?:.*?\#/)? # handle anchor (#/) redirect urls
- (?!view_play_list|my_playlists|artist|playlist) # ignore playlist URLs
(?: # the various things that can precede the ID:
(?:(?:v|embed|e)/) # v/ or embed/ or e/
|(?: # or the v= param in all its forms
(?(1).+)? # if we found the ID, everything can follow
$"""
_LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
- _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'
+ _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
_NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
_NETRC_MACHINE = 'youtube'
}
IE_NAME = u'youtube'
- def suitable(self, url):
+ @classmethod
+ def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE."""
- return re.match(self._VALID_URL, url, re.VERBOSE) is not None
+ if YoutubePlaylistIE.suitable(url): return False
+ return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
def report_lang(self):
"""Report attempt to set language."""
srt_lang = list(srt_lang_list.keys())[0]
if not srt_lang in srt_lang_list:
return (u'WARNING: no closed captions found in the specified language', None)
- request = compat_urllib_request.Request('http://www.youtube.com/api/timedtext?lang=%s&name=%s&v=%s' % (srt_lang, srt_lang_list[srt_lang], video_id))
+ params = compat_urllib_parse.urlencode({
+ 'lang': srt_lang,
+ 'name': srt_lang_list[srt_lang].encode('utf-8'),
+ 'v': video_id,
+ })
+ url = 'http://www.youtube.com/api/timedtext?' + params
try:
- srt_xml = compat_urllib_request.urlopen(request).read().decode('utf-8')
+ srt_xml = compat_urllib_request.urlopen(url).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
return (u'WARNING: unable to download video subtitles: %s' % compat_str(err), None)
if not srt_xml:
- return (u'WARNING: unable to download video subtitles', None)
+ return (u'WARNING: Did not fetch video subtitles', None)
return (None, self._closed_captions_xml_to_srt(srt_xml))
def _print_formats(self, formats):
else:
raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
except (IOError, netrc.NetrcParseError) as err:
- self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % compat_str(err))
+ self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err))
return
# Set language
self.report_lang()
compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.to_stderr(u'WARNING: unable to set language: %s' % compat_str(err))
+ self._downloader.report_warning(u'unable to set language: %s' % compat_str(err))
return
# No authentication to be performed
if username is None:
return
+ request = compat_urllib_request.Request(self._LOGIN_URL)
+ try:
+ login_page = compat_urllib_request.urlopen(request).read().decode('utf-8')
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ self._downloader.report_warning(u'unable to fetch login page: %s' % compat_str(err))
+ return
+
+ galx = None
+ dsh = None
+ match = re.search(re.compile(r'<input.+?name="GALX".+?value="(.+?)"', re.DOTALL), login_page)
+ if match:
+ galx = match.group(1)
+
+ match = re.search(re.compile(r'<input.+?name="dsh".+?value="(.+?)"', re.DOTALL), login_page)
+ if match:
+ dsh = match.group(1)
+
# Log in
- login_form = {
- 'current_form': 'loginForm',
- 'next': '/',
- 'action_login': 'Log In',
- 'username': username,
- 'password': password,
- }
- request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form))
+ login_form_strs = {
+ u'continue': u'http://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1',
+ u'Email': username,
+ u'GALX': galx,
+ u'Passwd': password,
+ u'PersistentCookie': u'yes',
+ u'_utf8': u'霱',
+ u'bgresponse': u'js_disabled',
+ u'checkConnection': u'',
+ u'checkedDomains': u'youtube',
+ u'dnConn': u'',
+ u'dsh': dsh,
+ u'pstMsg': u'0',
+ u'rmShown': u'1',
+ u'secTok': u'',
+ u'signIn': u'Sign in',
+ u'timeStmp': u'',
+ u'service': u'youtube',
+ u'uilel': u'3',
+ u'hl': u'en_US',
+ }
+ # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode
+ # chokes on unicode
+ login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in login_form_strs.items())
+ login_data = compat_urllib_parse.urlencode(login_form).encode('ascii')
+ request = compat_urllib_request.Request(self._LOGIN_URL, login_data)
try:
self.report_login()
login_results = compat_urllib_request.urlopen(request).read().decode('utf-8')
- if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None:
- self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password')
+ if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None:
+ self._downloader.report_warning(u'unable to log in: bad username or password')
return
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.to_stderr(u'WARNING: unable to log in: %s' % compat_str(err))
+ self._downloader.report_warning(u'unable to log in: %s' % compat_str(err))
return
# Confirm age
# uploader_id
video_uploader_id = None
- mobj = re.search(r'<link itemprop="url" href="http://www.youtube.com/user/([^"]+)">', video_webpage)
+ mobj = re.search(r'<link itemprop="url" href="http://www.youtube.com/(?:user|channel)/([^"]+)">', video_webpage)
if mobj is not None:
video_uploader_id = mobj.group(1)
else:
_VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)'
IE_NAME = u'dailymotion'
+ _WORKING = False
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id)
-
def report_extraction(self, video_id):
"""Report information extraction."""
self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)
# Retrieve video webpage to extract further information
request = compat_urllib_request.Request(url)
request.add_header('Cookie', 'family_filter=off')
- try:
- self.report_download_webpage(video_id)
- webpage_bytes = compat_urllib_request.urlopen(request).read()
- webpage = webpage_bytes.decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % compat_str(err))
- return
+ webpage = self._download_webpage(request, video_id)
# Extract URL, uploader and title from webpage
self.report_extraction(video_id)
"""Information extractor for vimeo.com."""
# _VALID_URL matches Vimeo URLs
- _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:(?:groups|album)/[^/]+/)?(?:videos?/)?([0-9]+)'
+ _VALID_URL = r'(?P<proto>https?://)?(?:(?:www|player)\.)?vimeo\.com/(?:(?:groups|album)/[^/]+/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)'
IE_NAME = u'vimeo'
def __init__(self, downloader=None):
self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
return
- video_id = mobj.group(1)
+ video_id = mobj.group('id')
+ if not mobj.group('proto'):
+ url = 'https://' + url
+ if mobj.group('direct_link'):
+ url = 'https://vimeo.com/' + video_id
# Retrieve video webpage to extract further information
request = compat_urllib_request.Request(url, None, std_headers)
opener = compat_urllib_request.OpenerDirector()
for handler in [compat_urllib_request.HTTPHandler, compat_urllib_request.HTTPDefaultErrorHandler,
HTTPMethodFallback, HEADRedirectHandler,
- compat_urllib_error.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]:
+ compat_urllib_request.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]:
opener.add_handler(handler())
response = opener.open(HeadRequest(url))
if mobj is None:
# Broaden the search a little bit
mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
+ if mobj is None:
+ # Broaden the search a little bit: JWPlayer JS loader
+ mobj = re.search(r'[^A-Za-z0-9]?file:\s*["\'](http[^\'"&]*)', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
return
self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
return
elif n > self._max_youtube_results:
- self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
+ self._downloader.report_warning(u'ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
n = self._max_youtube_results
self._download_n_results(query, n)
return
result_url = self._API_URL % (compat_urllib_parse.quote_plus(query), (50*pagenum)+1)
request = compat_urllib_request.Request(result_url)
try:
- data = compat_urllib_request.urlopen(request).read()
+ data = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.trouble(u'ERROR: unable to download API page: %s' % compat_str(err))
return
api_response = json.loads(data)['data']
+ if not 'items' in api_response:
+ self._downloader.trouble(u'[youtube] No video results')
+ return
+
new_ids = list(video['id'] for video in api_response['items'])
video_ids += new_ids
self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
return
elif n > self._max_google_results:
- self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n))
+ self._downloader.report_warning(u'gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n))
n = self._max_google_results
self._download_n_results(query, n)
return
if re.search(self._MORE_PAGES_INDICATOR, page) is None:
for id in video_ids:
- self._downloader#!/usr/bin/env python
-# -*- coding: utf-8 -*-
+ self._downloader.download(['http://video.google.com/videoplay?docid=%s' % id])
+ return
-from __future__ import absolute_import
+ pagenum = pagenum + 1
-import datetime
-import netrc
-import os
-import re
-import socket
-import time
-import email.utils
-import xml.etree.ElementTree
-import random
-import math
-from .utils import *
+class YahooSearchIE(InfoExtractor):
+ """Information Extractor for Yahoo! Video search queries."""
+ _WORKING = False
+ _VALID_URL = r'yvsearch(\d+|all)?:[\s\S]+'
+ _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s'
+ _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"'
+ _MORE_PAGES_INDICATOR = r'\s*Next'
+ _max_yahoo_results = 1000
+ IE_NAME = u'video.yahoo:search'
-class InfoExtractor(object):
- """Information Extractor class.
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
- Information extractors are the classes that, given a URL, extract
- information about the video (or videos) the URL refers to. This
- information includes the real video URL, the video title, author and
- others. The information is stored in a dictionary which is then
- passed to the FileDownloader. The FileDownloader processes this
- information possibly downloading the video to the file system, among
- other possible outcomes.
+ def report_download_page(self, query, pagenum):
+ """Report attempt to download playlist page with given number."""
+ query = query.decode(preferredencoding())
+ self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum))
- The dictionaries must include the following fields:
+ def _real_extract(self, query):
+ mobj = re.match(self._VALID_URL, query)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
+ return
- id: Video identifier.
- url: Final video URL.
- title: Video title, unescaped.
- ext: Video filename extension.
- uploader: Full name of the video uploader.
- upload_date: Video upload date (YYYYMMDD).
+ prefix, query = query.split(':')
+ prefix = prefix[8:]
+ query = query.encode('utf-8')
+ if prefix == '':
+ self._download_n_results(query, 1)
+ return
+ elif prefix == 'all':
+ self._download_n_results(query, self._max_yahoo_results)
+ return
+ else:
+ try:
+ n = int(prefix)
+ if n <= 0:
+ self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
+ return
+ elif n > self._max_yahoo_results:
+ self._downloader.report_warning(u'yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n))
+ n = self._max_yahoo_results
+ self._download_n_results(query, n)
+ return
+ except ValueError: # parsing prefix as integer fails
+ self._download_n_results(query, 1)
+ return
- The following fields are optional:
+ def _download_n_results(self, query, n):
+ """Downloads a specified number of results for a query"""
- format: The video format, defaults to ext (used for --get-format)
- thumbnail: Full URL to a video thumbnail image.
- description: One-line video description.
- uploader_id: Nickname or id of the video uploader.
- player_url: SWF Player URL (used for rtmpdump).
- subtitles: The .srt file contents.
- urlhandle: [internal] The urlHandle to be used to download the file,
- like returned by urllib.request.urlopen
+ video_ids = []
+ already_seen = set()
+ pagenum = 1
- The fields should all be Unicode strings.
+ while True:
+ self.report_download_page(query, pagenum)
+ result_url = self._TEMPLATE_URL % (compat_urllib_parse.quote_plus(query), pagenum)
+ request = compat_urllib_request.Request(result_url)
+ try:
+ page = compat_urllib_request.urlopen(request).read()
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
+ return
- Subclasses of this one should re-define the _real_initialize() and
- _real_extract() methods and define a _VALID_URL regexp.
- Probably, they should also be added to the list of extractors.
+ # Extract video identifiers
+ for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+ video_id = mobj.group(1)
+ if video_id not in already_seen:
+ video_ids.append(video_id)
+ already_seen.add(video_id)
+ if len(video_ids) == n:
+ # Specified n videos reached
+ for id in video_ids:
+ self._downloader.download(['http://video.yahoo.com/watch/%s' % id])
+ return
- _real_extract() must return a *list* of information dictionaries as
- described above.
+ if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+ for id in video_ids:
+ self._downloader.download(['http://video.yahoo.com/watch/%s' % id])
+ return
- Finally, the _WORKING attribute should be set to False for broken IEs
- in order to warn the users and skip the tests.
- """
+ pagenum = pagenum + 1
- _ready = False
- _downloader = None
- _WORKING = True
+
+class YoutubePlaylistIE(InfoExtractor):
+ """Information Extractor for YouTube playlists."""
+
+ _VALID_URL = r"""(?:
+ (?:https?://)?
+ (?:\w+\.)?
+ youtube\.com/
+ (?:
+ (?:course|view_play_list|my_playlists|artist|playlist|watch)
+ \? (?:.*?&)*? (?:p|a|list)=
+ | user/.*?/user/
+ | p/
+ | user/.*?#[pg]/c/
+ )
+ ((?:PL|EC|UU)?[0-9A-Za-z-_]{10,})
+ .*
+ |
+ ((?:PL|EC|UU)[0-9A-Za-z-_]{10,})
+ )"""
+ _TEMPLATE_URL = 'https://gdata.youtube.com/feeds/api/playlists/%s?max-results=%i&start-index=%i&v=2&alt=json'
+ _MAX_RESULTS = 50
+ IE_NAME = u'youtube:playlist'
def __init__(self, downloader=None):
- """Constructor. Receives an optional downloader."""
- self._ready = False
- self.set_downloader(downloader)
+ InfoExtractor.__init__(self, downloader)
- def suitable(self, url):
+ @classmethod
+ def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE."""
- return re.match(self._VALID_URL, url) is not None
+ return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
- def working(self):
- """Getter method for _WORKING."""
- return self._WORKING
+ def report_download_page(self, playlist_id, pagenum):
+ """Report attempt to download playlist page with given number."""
+ self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
- def initialize(self):
- """Initializes an instance (authentication, etc)."""
- if not self._ready:
- self._real_initialize()
- self._ready = True
+ def _real_extract(self, url):
+ # Extract playlist id
+ mobj = re.match(self._VALID_URL, url, re.VERBOSE)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+ return
- def extract(self, url):
- """Extracts URL information and returns it in list of dicts."""
- self.initialize()
- return self._real_extract(url)
+ # Download playlist videos from API
+ playlist_id = mobj.group(1) or mobj.group(2)
+ page_num = 1
+ videos = []
- def set_downloader(self, downloader):
- """Sets the downloader for this IE."""
- self._downloader = downloader
+ while True:
+ self.report_download_page(playlist_id, page_num)
- def _real_initialize(self):
- """Real initialization process. Redefine in subclasses."""
- pass
+ url = self._TEMPLATE_URL % (playlist_id, self._MAX_RESULTS, self._MAX_RESULTS * (page_num - 1) + 1)
+ try:
+ page = compat_urllib_request.urlopen(url).read().decode('utf8')
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
+ return
+
+ try:
+ response = json.loads(page)
+ except ValueError as err:
+ self._downloader.trouble(u'ERROR: Invalid JSON in API response: ' + compat_str(err))
+ return
+
+ if not 'feed' in response or not 'entry' in response['feed']:
+ self._downloader.trouble(u'ERROR: Got a malformed response from YouTube API')
+ return
+ videos += [ (entry['yt$position']['$t'], entry['content']['src'])
+ for entry in response['feed']['entry']
+ if 'content' in entry ]
+
+ if len(response['feed']['entry']) < self._MAX_RESULTS:
+ break
+ page_num += 1
+
+ videos = [v[1] for v in sorted(videos)]
+ total = len(videos)
+
+ playliststart = self._downloader.params.get('playliststart', 1) - 1
+ playlistend = self._downloader.params.get('playlistend', -1)
+ if playlistend == -1:
+ videos = videos[playliststart:]
+ else:
+ videos = videos[playliststart:playlistend]
+
+ if len(videos) == total:
+ self._downloader.to_screen(u'[youtube] PL %s: Found %i videos' % (playlist_id, total))
+ else:
+ self._downloader.to_screen(u'[youtube] PL %s: Found %i videos, downloading %i' % (playlist_id, total, len(videos)))
+
+ for video in videos:
+ self._downloader.download([video])
+ return
+
+
+class YoutubeChannelIE(InfoExtractor):
+ """Information Extractor for YouTube channels."""
+
+ _VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)(?:/.*)?$"
+ _TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en'
+ _MORE_PAGES_INDICATOR = u"Next \N{RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK}"
+ IE_NAME = u'youtube:channel'
+
+ def report_download_page(self, channel_id, pagenum):
+ """Report attempt to download channel page with given number."""
+ self._downloader.to_screen(u'[youtube] Channel %s: Downloading page #%s' % (channel_id, pagenum))
def _real_extract(self, url):
- """Real extraction process. Redefine in subclasses."""
- pass
+ # Extract channel id
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+ return
- @property
- def IE_NAME(self):
- return type(self).__name__[:-2]
+ # Download channel pages
+ channel_id = mobj.group(1)
+ video_ids = []
+ pagenum = 1
-class YoutubeIE(InfoExtractor):
- """Information extractor for youtube.com."""
-
- _VALID_URL = r"""^
- (
- (?:https?://)? # http(s):// (optional)
- (?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|
- tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains
- (?:.*?\#/)? # handle anchor (#/) redirect urls
- (?!view_play_list|my_playlists|artist|playlist) # ignore playlist URLs
- (?: # the various things that can precede the ID:
- (?:(?:v|embed|e)/) # v/ or embed/ or e/
- |(?: # or the v= param in all its forms
- (?:watch(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
- (?:\?|\#!?) # the params delimiter ? or # or #!
- (?:.*?&)? # any other preceding param (like /?s=tuff&v=xxxx)
- v=
- )
- )? # optional -> youtube.com/xxxx is OK
- )? # all until now is optional -> you can pass the naked ID
- ([0-9A-Za-z_-]+) # here is it! the YouTube video ID
- (?(1).+)? # if we found the ID, everything can follow
- $"""
- _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
- _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'
- _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
- _NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
- _NETRC_MACHINE = 'youtube'
- # Listed in order of quality
- _available_formats = ['38', '37', '46', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13']
- _available_formats_prefer_free = ['38', '46', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13']
- _video_extensions = {
- '13': '3gp',
- '17': 'mp4',
- '18': 'mp4',
- '22': 'mp4',
- '37': 'mp4',
- '38': 'video', # You actually don't know if this will be MOV, AVI or whatever
- '43': 'webm',
- '44': 'webm',
- '45': 'webm',
- '46': 'webm',
- }
- _video_dimensions = {
- '5': '240x400',
- '6': '???',
- '13': '???',
- '17': '144x176',
- '18': '360x640',
- '22': '720x1280',
- '34': '360x640',
- '35': '480x854',
- '37': '1080x1920',
- '38': '3072x4096',
- '43': '360x640',
- '44': '480x854',
- '45': '720x1280',
- '46': '1080x1920',
- }
- IE_NAME = u'youtube'
-
- def suitable(self, url):
- """Receives a URL and returns True if suitable for this IE."""
- return re.match(self._VALID_URL, url, re.VERBOSE) is not None
-
- def report_lang(self):
- """Report attempt to set language."""
- self._downloader.to_screen(u'[youtube] Setting language')
-
- def report_login(self):
- """Report attempt to log in."""
- self._downloader.to_screen(u'[youtube] Logging in')
-
- def report_age_confirmation(self):
- """Report attempt to confirm age."""
- self._downloader.to_screen(u'[youtube] Confirming age')
-
- def report_video_webpage_download(self, video_id):
- """Report attempt to download video webpage."""
- self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id)
-
- def report_video_info_webpage_download(self, video_id):
- """Report attempt to download video info webpage."""
- self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id)
-
- def report_video_subtitles_download(self, video_id):
- """Report attempt to download video info webpage."""
- self._downloader.to_screen(u'[youtube] %s: Downloading video subtitles' % video_id)
-
- def report_information_extraction(self, video_id):
- """Report attempt to extract video information."""
- self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id)
-
- def report_unavailable_format(self, video_id, format):
- """Report extracted video URL."""
- self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format))
-
- def report_rtmp_download(self):
- """Indicate the download will use the RTMP protocol."""
- self._downloader.to_screen(u'[youtube] RTMP download detected')
-
- def _closed_captions_xml_to_srt(self, xml_string):
- srt = ''
- texts = re.findall(r'<text start="([\d\.]+)"( dur="([\d\.]+)")?>([^<]+)</text>', xml_string, re.MULTILINE)
- # TODO parse xml instead of regex
- for n, (start, dur_tag, dur, caption) in enumerate(texts):
- if not dur: dur = '4'
- start = float(start)
- end = start + float(dur)
- start = "%02i:%02i:%02i,%03i" %(start/(60*60), start/60%60, start%60, start%1*1000)
- end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000)
- caption = unescapeHTML(caption)
- caption = unescapeHTML(caption) # double cycle, intentional
- srt += str(n+1) + '\n'
- srt += start + ' --> ' + end + '\n'
- srt += caption + '\n\n'
- return srt
-
- def _extract_subtitles(self, video_id):
- self.report_video_subtitles_download(video_id)
- request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id)
- try:
- srt_list = compat_urllib_request.urlopen(request).read().decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- return (u'WARNING: unable to download video subtitles: %s' % compat_str(err), None)
- srt_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', srt_list)
- srt_lang_list = dict((l[1], l[0]) for l in srt_lang_list)
- if not srt_lang_list:
- return (u'WARNING: video has no closed captions', None)
- if self._downloader.params.get('subtitleslang', False):
- srt_lang = self._downloader.params.get('subtitleslang')
- elif 'en' in srt_lang_list:
- srt_lang = 'en'
- else:
- srt_lang = list(srt_lang_list.keys())[0]
- if not srt_lang in srt_lang_list:
- return (u'WARNING: no closed captions found in the specified language', None)
- request = compat_urllib_request.Request('http://www.youtube.com/api/timedtext?lang=%s&name=%s&v=%s' % (srt_lang, srt_lang_list[srt_lang], video_id))
- try:
- srt_xml = compat_urllib_request.urlopen(request).read().decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- return (u'WARNING: unable to download video subtitles: %s' % compat_str(err), None)
- if not srt_xml:
- return (u'WARNING: unable to download video subtitles', None)
- return (None, self._closed_captions_xml_to_srt(srt_xml))
-
- def _print_formats(self, formats):
- print('Available formats:')
- for x in formats:
- print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???')))
-
- def _real_initialize(self):
- if self._downloader is None:
- return
-
- username = None
- password = None
- downloader_params = self._downloader.params
-
- # Attempt to use provided username and password or .netrc data
- if downloader_params.get('username', None) is not None:
- username = downloader_params['username']
- password = downloader_params['password']
- elif downloader_params.get('usenetrc', False):
- try:
- info = netrc.netrc().authenticators(self._NETRC_MACHINE)
- if info is not None:
- username = info[0]
- password = info[2]
- else:
- raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
- except (IOError, netrc.NetrcParseError) as err:
- self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % compat_str(err))
- return
-
- # Set language
- request = compat_urllib_request.Request(self._LANG_URL)
- try:
- self.report_lang()
- compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.to_stderr(u'WARNING: unable to set language: %s' % compat_str(err))
- return
-
- # No authentication to be performed
- if username is None:
- return
-
- # Log in
- login_form = {
- 'current_form': 'loginForm',
- 'next': '/',
- 'action_login': 'Log In',
- 'username': username,
- 'password': password,
- }
- request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form))
- try:
- self.report_login()
- login_results = compat_urllib_request.urlopen(request).read().decode('utf-8')
- if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None:
- self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password')
- return
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.to_stderr(u'WARNING: unable to log in: %s' % compat_str(err))
- return
-
- # Confirm age
- age_form = {
- 'next_url': '/',
- 'action_confirm': 'Confirm',
- }
- request = compat_urllib_request.Request(self._AGE_URL, compat_urllib_parse.urlencode(age_form))
- try:
- self.report_age_confirmation()
- age_results = compat_urllib_request.urlopen(request).read().decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err))
- return
-
- def _extract_id(self, url):
- mobj = re.match(self._VALID_URL, url, re.VERBOSE)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
- video_id = mobj.group(2)
- return video_id
-
- def _real_extract(self, url):
- # Extract original video URL from URL with redirection, like age verification, using next_url parameter
- mobj = re.search(self._NEXT_URL_RE, url)
- if mobj:
- url = 'http://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/')
- video_id = self._extract_id(url)
-
- # Get video webpage
- self.report_video_webpage_download(video_id)
- url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id
- request = compat_urllib_request.Request(url)
- try:
- video_webpage_bytes = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
- return
-
- video_webpage = video_webpage_bytes.decode('utf-8', 'ignore')
-
- # Attempt to extract SWF player URL
- mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
- if mobj is not None:
- player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
- else:
- player_url = None
-
- # Get video info
- self.report_video_info_webpage_download(video_id)
- for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
- video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
- % (video_id, el_type))
- request = compat_urllib_request.Request(video_info_url)
- try:
- video_info_webpage_bytes = compat_urllib_request.urlopen(request).read()
- video_info_webpage = video_info_webpage_bytes.decode('utf-8', 'ignore')
- video_info = compat_parse_qs(video_info_webpage)
- if 'token' in video_info:
- break
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % compat_str(err))
- return
- if 'token' not in video_info:
- if 'reason' in video_info:
- self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0])
- else:
- self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason')
- return
-
- # Check for "rental" videos
- if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
- self._downloader.trouble(u'ERROR: "rental" videos not supported')
- return
-
- # Start extracting information
- self.report_information_extraction(video_id)
-
- # uploader
- if 'author' not in video_info:
- self._downloader.trouble(u'ERROR: unable to extract uploader name')
- return
- video_uploader = compat_urllib_parse.unquote_plus(video_info['author'][0])
-
- # uploader_id
- video_uploader_id = None
- mobj = re.search(r'<link itemprop="url" href="http://www.youtube.com/user/([^"]+)">', video_webpage)
- if mobj is not None:
- video_uploader_id = mobj.group(1)
- else:
- self._downloader.trouble(u'WARNING: unable to extract uploader nickname')
-
- # title
- if 'title' not in video_info:
- self._downloader.trouble(u'ERROR: unable to extract video title')
- return
- video_title = compat_urllib_parse.unquote_plus(video_info['title'][0])
-
- # thumbnail image
- if 'thumbnail_url' not in video_info:
- self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
- video_thumbnail = ''
- else: # don't panic if we can't find it
- video_thumbnail = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0])
-
- # upload date
- upload_date = None
- mobj = re.search(r'id="eow-date.*?>(.*?)</span>', video_webpage, re.DOTALL)
- if mobj is not None:
- upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
- format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y']
- for expression in format_expressions:
- try:
- upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d')
- except:
- pass
-
- # description
- video_description = get_element_by_id("eow-description", video_webpage)
- if video_description:
- video_description = clean_html(video_description)
- else:
- video_description = ''
-
- # closed captions
- video_subtitles = None
- if self._downloader.params.get('writesubtitles', False):
- (srt_error, video_subtitles) = self._extract_subtitles(video_id)
- if srt_error:
- self._downloader.trouble(srt_error)
-
- if 'length_seconds' not in video_info:
- self._downloader.trouble(u'WARNING: unable to extract video duration')
- video_duration = ''
- else:
- video_duration = compat_urllib_parse.unquote_plus(video_info['length_seconds'][0])
-
- # token
- video_token = compat_urllib_parse.unquote_plus(video_info['token'][0])
-
- # Decide which formats to download
- req_format = self._downloader.params.get('format', None)
-
- if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
- self.report_rtmp_download()
- video_url_list = [(None, video_info['conn'][0])]
- elif 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1:
- url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',')
- url_data = [compat_parse_qs(uds) for uds in url_data_strs]
- url_data = [ud for ud in url_data if 'itag' in ud and 'url' in ud]
- url_map = dict((ud['itag'][0], ud['url'][0] + '&signature=' + ud['sig'][0]) for ud in url_data)
-
- format_limit = self._downloader.params.get('format_limit', None)
- available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats
- if format_limit is not None and format_limit in available_formats:
- format_list = available_formats[available_formats.index(format_limit):]
- else:
- format_list = available_formats
- existing_formats = [x for x in format_list if x in url_map]
- if len(existing_formats) == 0:
- self._downloader.trouble(u'ERROR: no known formats available for video')
- return
- if self._downloader.params.get('listformats', None):
- self._print_formats(existing_formats)
- return
- if req_format is None or req_format == 'best':
- video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
- elif req_format == 'worst':
- video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality
- elif req_format in ('-1', 'all'):
- video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
- else:
- # Specific formats. We pick the first in a slash-delimeted sequence.
- # For example, if '1/2/3/4' is requested and '2' and '4' are available, we pick '2'.
- req_formats = req_format.split('/')
- video_url_list = None
- for rf in req_formats:
- if rf in url_map:
- video_url_list = [(rf, url_map[rf])]
- break
- if video_url_list is None:
- self._downloader.trouble(u'ERROR: requested format not available')
- return
- else:
- self._downloader.trouble(u'ERROR: no conn or url_encoded_fmt_stream_map information found in video info')
- return
-
- results = []
- for format_param, video_real_url in video_url_list:
- # Extension
- video_extension = self._video_extensions.get(format_param, 'flv')
-
- video_format = '{0} - {1}'.format(format_param if format_param else video_extension,
- self._video_dimensions.get(format_param, '???'))
-
- results.append({
- 'id': video_id,
- 'url': video_real_url,
- 'uploader': video_uploader,
- 'uploader_id': video_uploader_id,
- 'upload_date': upload_date,
- 'title': video_title,
- 'ext': video_extension,
- 'format': video_format,
- 'thumbnail': video_thumbnail,
- 'description': video_description,
- 'player_url': player_url,
- 'subtitles': video_subtitles,
- 'duration': video_duration
- })
- return results
-
-
-class MetacafeIE(InfoExtractor):
- """Information Extractor for metacafe.com."""
-
- _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
- _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
- _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
- IE_NAME = u'metacafe'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_disclaimer(self):
- """Report disclaimer retrieval."""
- self._downloader.to_screen(u'[metacafe] Retrieving disclaimer')
-
- def report_age_confirmation(self):
- """Report attempt to confirm age."""
- self._downloader.to_screen(u'[metacafe] Confirming age')
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id)
-
- def _real_initialize(self):
- # Retrieve disclaimer
- request = compat_urllib_request.Request(self._DISCLAIMER)
- try:
- self.report_disclaimer()
- disclaimer = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % compat_str(err))
- return
-
- # Confirm age
- disclaimer_form = {
- 'filters': '0',
- 'submit': "Continue - I'm over 18",
- }
- request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form))
- try:
- self.report_age_confirmation()
- disclaimer = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err))
- return
-
- def _real_extract(self, url):
- # Extract id and simplified title from URL
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
-
- video_id = mobj.group(1)
-
- # Check if video comes from YouTube
- mobj2 = re.match(r'^yt-(.*)$', video_id)
- if mobj2 is not None:
- self._downloader.download(['http://www.youtube.com/watch?v=%s' % mobj2.group(1)])
- return
-
- # Retrieve video webpage to extract further information
- request = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id)
- try:
- self.report_download_webpage(video_id)
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % compat_str(err))
- return
-
- # Extract URL, uploader and title from webpage
- self.report_extraction(video_id)
- mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
- if mobj is not None:
- mediaURL = compat_urllib_parse.unquote(mobj.group(1))
- video_extension = mediaURL[-3:]
-
- # Extract gdaKey if available
- mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
- if mobj is None:
- video_url = mediaURL
- else:
- gdaKey = mobj.group(1)
- video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
- else:
- mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
- vardict = compat_parse_qs(mobj.group(1))
- if 'mediaData' not in vardict:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
- mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0])
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
- mediaURL = mobj.group(1).replace('\\/', '/')
- video_extension = mediaURL[-3:]
- video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2))
-
- mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
- return
- video_title = mobj.group(1).decode('utf-8')
-
- mobj = re.search(r'submitter=(.*?);', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
- return
- video_uploader = mobj.group(1)
-
- return [{
- 'id': video_id.decode('utf-8'),
- 'url': video_url.decode('utf-8'),
- 'uploader': video_uploader.decode('utf-8'),
- 'upload_date': None,
- 'title': video_title,
- 'ext': video_extension.decode('utf-8'),
- }]
-
-
-class DailymotionIE(InfoExtractor):
- """Information Extractor for Dailymotion"""
-
- _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)'
- IE_NAME = u'dailymotion'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)
-
- def _real_extract(self, url):
- # Extract id and simplified title from URL
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
-
- video_id = mobj.group(1).split('_')[0].split('?')[0]
-
- video_extension = 'mp4'
-
- # Retrieve video webpage to extract further information
- request = compat_urllib_request.Request(url)
- request.add_header('Cookie', 'family_filter=off')
- try:
- self.report_download_webpage(video_id)
- webpage_bytes = compat_urllib_request.urlopen(request).read()
- webpage = webpage_bytes.decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % compat_str(err))
- return
-
- # Extract URL, uploader and title from webpage
- self.report_extraction(video_id)
- mobj = re.search(r'\s*var flashvars = (.*)', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
- flashvars = compat_urllib_parse.unquote(mobj.group(1))
-
- for key in ['hd1080URL', 'hd720URL', 'hqURL', 'sdURL', 'ldURL', 'video_url']:
- if key in flashvars:
- max_quality = key
- self._downloader.to_screen(u'[dailymotion] Using %s' % key)
- break
- else:
- self._downloader.trouble(u'ERROR: unable to extract video URL')
- return
-
- mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video URL')
- return
-
- video_url = compat_urllib_parse.unquote(mobj.group(1)).replace('\\/', '/')
-
- # TODO: support choosing qualities
-
- mobj = re.search(r'<meta property="og:title" content="(?P<title>[^"]*)" />', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
- return
- video_title = unescapeHTML(mobj.group('title'))
-
- video_uploader = None
- mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>', webpage)
- if mobj is None:
- # lookin for official user
- mobj_official = re.search(r'<span rel="author"[^>]+?>([^<]+?)</span>', webpage)
- if mobj_official is None:
- self._downloader.trouble(u'WARNING: unable to extract uploader nickname')
- else:
- video_uploader = mobj_official.group(1)
- else:
- video_uploader = mobj.group(1)
-
- video_upload_date = None
- mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage)
- if mobj is not None:
- video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1)
-
- return [{
- 'id': video_id,
- 'url': video_url,
- 'uploader': video_uploader,
- 'upload_date': video_upload_date,
- 'title': video_title,
- 'ext': video_extension,
- }]
-
-
-class PhotobucketIE(InfoExtractor):
- """Information extractor for photobucket.com."""
-
- _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
- IE_NAME = u'photobucket'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id)
-
- def _real_extract(self, url):
- # Extract id from URL
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
-
- video_id = mobj.group(1)
-
- video_extension = 'flv'
-
- # Retrieve video webpage to extract further information
- request = compat_urllib_request.Request(url)
- try:
- self.report_download_webpage(video_id)
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
- return
-
- # Extract URL, uploader, and title from webpage
- self.report_extraction(video_id)
- mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
- mediaURL = compat_urllib_parse.unquote(mobj.group(1))
-
- video_url = mediaURL
-
- mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
- return
- video_title = mobj.group(1).decode('utf-8')
-
- video_uploader = mobj.group(2).decode('utf-8')
-
- return [{
- 'id': video_id.decode('utf-8'),
- 'url': video_url.decode('utf-8'),
- 'uploader': video_uploader,
- 'upload_date': None,
- 'title': video_title,
- 'ext': video_extension.decode('utf-8'),
- }]
-
-
-class YahooIE(InfoExtractor):
- """Information extractor for video.yahoo.com."""
-
- _WORKING = False
- # _VALID_URL matches all Yahoo! Video URLs
- # _VPAGE_URL matches only the extractable '/watch/' URLs
- _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?'
- _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?'
- IE_NAME = u'video.yahoo'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id)
-
- def _real_extract(self, url, new_video=True):
- # Extract ID from URL
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
-
- video_id = mobj.group(2)
- video_extension = 'flv'
-
- # Rewrite valid but non-extractable URLs as
- # extractable English language /watch/ URLs
- if re.match(self._VPAGE_URL, url) is None:
- request = compat_urllib_request.Request(url)
- try:
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
- return
-
- mobj = re.search(r'\("id", "([0-9]+)"\);', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Unable to extract id field')
- return
- yahoo_id = mobj.group(1)
-
- mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Unable to extract vid field')
- return
- yahoo_vid = mobj.group(1)
-
- url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id)
- return self._real_extract(url, new_video=False)
-
- # Retrieve video webpage to extract further information
- request = compat_urllib_request.Request(url)
- try:
- self.report_download_webpage(video_id)
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
- return
-
- # Extract uploader and title from webpage
- self.report_extraction(video_id)
- mobj = re.search(r'<meta name="title" content="(.*)" />', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video title')
- return
- video_title = mobj.group(1).decode('utf-8')
-
- mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video uploader')
- return
- video_uploader = mobj.group(1).decode('utf-8')
-
- # Extract video thumbnail
- mobj = re.search(r'<link rel="image_src" href="(.*)" />', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
- return
- video_thumbnail = mobj.group(1).decode('utf-8')
-
- # Extract video description
- mobj = re.search(r'<meta name="description" content="(.*)" />', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video description')
- return
- video_description = mobj.group(1).decode('utf-8')
- if not video_description:
- video_description = 'No description available.'
-
- # Extract video height and width
- mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video height')
- return
- yv_video_height = mobj.group(1)
-
- mobj = re.search(r'<meta name="video_width" content="([0-9]+)" />', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video width')
- return
- yv_video_width = mobj.group(1)
-
- # Retrieve video playlist to extract media URL
- # I'm not completely sure what all these options are, but we
- # seem to need most of them, otherwise the server sends a 401.
- yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents
- yv_bitrate = '700' # according to Wikipedia this is hard-coded
- request = compat_urllib_request.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id +
- '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height +
- '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797')
- try:
- self.report_download_webpage(video_id)
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
- return
-
- # Extract media URL from playlist XML
- mobj = re.search(r'<STREAM APP="(http://.*)" FULLPATH="/?(/.*\.flv\?[^"]*)"', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Unable to extract media URL')
- return
- video_url = compat_urllib_parse.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8')
- video_url = unescapeHTML(video_url)
-
- return [{
- 'id': video_id.decode('utf-8'),
- 'url': video_url,
- 'uploader': video_uploader,
- 'upload_date': None,
- 'title': video_title,
- 'ext': video_extension.decode('utf-8'),
- 'thumbnail': video_thumbnail.decode('utf-8'),
- 'description': video_description,
- }]
-
-
-class VimeoIE(InfoExtractor):
- """Information extractor for vimeo.com."""
-
- # _VALID_URL matches Vimeo URLs
- _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:(?:groups|album)/[^/]+/)?(?:videos?/)?([0-9]+)'
- IE_NAME = u'vimeo'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id)
-
- def _real_extract(self, url, new_video=True):
- # Extract ID from URL
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
-
- video_id = mobj.group(1)
-
- # Retrieve video webpage to extract further information
- request = compat_urllib_request.Request(url, None, std_headers)
- try:
- self.report_download_webpage(video_id)
- webpage_bytes = compat_urllib_request.urlopen(request).read()
- webpage = webpage_bytes.decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
- return
-
- # Now we begin extracting as much information as we can from what we
- # retrieved. First we extract the information common to all extractors,
- # and latter we extract those that are Vimeo specific.
- self.report_extraction(video_id)
-
- # Extract the config JSON
- try:
- config = webpage.split(' = {config:')[1].split(',assets:')[0]
- config = json.loads(config)
- except:
- self._downloader.trouble(u'ERROR: unable to extract info section')
- return
-
- # Extract title
- video_title = config["video"]["title"]
-
- # Extract uploader and uploader_id
- video_uploader = config["video"]["owner"]["name"]
- video_uploader_id = config["video"]["owner"]["url"].split('/')[-1]
-
- # Extract video thumbnail
- video_thumbnail = config["video"]["thumbnail"]
-
- # Extract video description
- video_description = get_element_by_attribute("itemprop", "description", webpage)
- if video_description: video_description = clean_html(video_description)
- else: video_description = ''
-
- # Extract upload date
- video_upload_date = None
- mobj = re.search(r'<meta itemprop="dateCreated" content="(\d{4})-(\d{2})-(\d{2})T', webpage)
- if mobj is not None:
- video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3)
-
- # Vimeo specific: extract request signature and timestamp
- sig = config['request']['signature']
- timestamp = config['request']['timestamp']
-
- # Vimeo specific: extract video codec and quality information
- # First consider quality, then codecs, then take everything
- # TODO bind to format param
- codecs = [('h264', 'mp4'), ('vp8', 'flv'), ('vp6', 'flv')]
- files = { 'hd': [], 'sd': [], 'other': []}
- for codec_name, codec_extension in codecs:
- if codec_name in config["video"]["files"]:
- if 'hd' in config["video"]["files"][codec_name]:
- files['hd'].append((codec_name, codec_extension, 'hd'))
- elif 'sd' in config["video"]["files"][codec_name]:
- files['sd'].append((codec_name, codec_extension, 'sd'))
- else:
- files['other'].append((codec_name, codec_extension, config["video"]["files"][codec_name][0]))
-
- for quality in ('hd', 'sd', 'other'):
- if len(files[quality]) > 0:
- video_quality = files[quality][0][2]
- video_codec = files[quality][0][0]
- video_extension = files[quality][0][1]
- self._downloader.to_screen(u'[vimeo] %s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality))
- break
- else:
- self._downloader.trouble(u'ERROR: no known codec found')
- return
-
- video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \
- %(video_id, sig, timestamp, video_quality, video_codec.upper())
-
- return [{
- 'id': video_id,
- 'url': video_url,
- 'uploader': video_uploader,
- 'uploader_id': video_uploader_id,
- 'upload_date': video_upload_date,
- 'title': video_title,
- 'ext': video_extension,
- 'thumbnail': video_thumbnail,
- 'description': video_description,
- }]
-
-
-class ArteTvIE(InfoExtractor):
- """arte.tv information extractor."""
-
- _VALID_URL = r'(?:http://)?videos\.arte\.tv/(?:fr|de)/videos/.*'
- _LIVE_URL = r'index-[0-9]+\.html$'
-
- IE_NAME = u'arte.tv'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[arte.tv] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[arte.tv] %s: Extracting information' % video_id)
-
- def fetch_webpage(self, url):
- self._downloader.incre#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-
-from __future__ import absolute_import
-
-import datetime
-import netrc
-import os
-import re
-import socket
-import time
-import email.utils
-import xml.etree.ElementTree
-import random
-import math
-
-from .utils import *
-
-
-class InfoExtractor(object):
- """Information Extractor class.
-
- Information extractors are the classes that, given a URL, extract
- information about the video (or videos) the URL refers to. This
- information includes the real video URL, the video title, author and
- others. The information is stored in a dictionary which is then
- passed to the FileDownloader. The FileDownloader processes this
- information possibly downloading the video to the file system, among
- other possible outcomes.
-
- The dictionaries must include the following fields:
-
- id: Video identifier.
- url: Final video URL.
- title: Video title, unescaped.
- ext: Video filename extension.
- uploader: Full name of the video uploader.
- upload_date: Video upload date (YYYYMMDD).
-
- The following fields are optional:
-
- format: The video format, defaults to ext (used for --get-format)
- thumbnail: Full URL to a video thumbnail image.
- description: One-line video description.
- uploader_id: Nickname or id of the video uploader.
- player_url: SWF Player URL (used for rtmpdump).
- subtitles: The .srt file contents.
- urlhandle: [internal] The urlHandle to be used to download the file,
- like returned by urllib.request.urlopen
-
- The fields should all be Unicode strings.
-
- Subclasses of this one should re-define the _real_initialize() and
- _real_extract() methods and define a _VALID_URL regexp.
- Probably, they should also be added to the list of extractors.
-
- _real_extract() must return a *list* of information dictionaries as
- described above.
-
- Finally, the _WORKING attribute should be set to False for broken IEs
- in order to warn the users and skip the tests.
- """
-
- _ready = False
- _downloader = None
- _WORKING = True
-
- def __init__(self, downloader=None):
- """Constructor. Receives an optional downloader."""
- self._ready = False
- self.set_downloader(downloader)
-
- def suitable(self, url):
- """Receives a URL and returns True if suitable for this IE."""
- return re.match(self._VALID_URL, url) is not None
-
- def working(self):
- """Getter method for _WORKING."""
- return self._WORKING
-
- def initialize(self):
- """Initializes an instance (authentication, etc)."""
- if not self._ready:
- self._real_initialize()
- self._ready = True
-
- def extract(self, url):
- """Extracts URL information and returns it in list of dicts."""
- self.initialize()
- return self._real_extract(url)
-
- def set_downloader(self, downloader):
- """Sets the downloader for this IE."""
- self._downloader = downloader
-
- def _real_initialize(self):
- """Real initialization process. Redefine in subclasses."""
- pass
-
- def _real_extract(self, url):
- """Real extraction process. Redefine in subclasses."""
- pass
-
- @property
- def IE_NAME(self):
- return type(self).__name__[:-2]
-
-class YoutubeIE(InfoExtractor):
- """Information extractor for youtube.com."""
-
- _VALID_URL = r"""^
- (
- (?:https?://)? # http(s):// (optional)
- (?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|
- tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains
- (?:.*?\#/)? # handle anchor (#/) redirect urls
- (?!view_play_list|my_playlists|artist|playlist) # ignore playlist URLs
- (?: # the various things that can precede the ID:
- (?:(?:v|embed|e)/) # v/ or embed/ or e/
- |(?: # or the v= param in all its forms
- (?:watch(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
- (?:\?|\#!?) # the params delimiter ? or # or #!
- (?:.*?&)? # any other preceding param (like /?s=tuff&v=xxxx)
- v=
- )
- )? # optional -> youtube.com/xxxx is OK
- )? # all until now is optional -> you can pass the naked ID
- ([0-9A-Za-z_-]+) # here is it! the YouTube video ID
- (?(1).+)? # if we found the ID, everything can follow
- $"""
- _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
- _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'
- _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
- _NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
- _NETRC_MACHINE = 'youtube'
- # Listed in order of quality
- _available_formats = ['38', '37', '46', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13']
- _available_formats_prefer_free = ['38', '46', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13']
- _video_extensions = {
- '13': '3gp',
- '17': 'mp4',
- '18': 'mp4',
- '22': 'mp4',
- '37': 'mp4',
- '38': 'video', # You actually don't know if this will be MOV, AVI or whatever
- '43': 'webm',
- '44': 'webm',
- '45': 'webm',
- '46': 'webm',
- }
- _video_dimensions = {
- '5': '240x400',
- '6': '???',
- '13': '???',
- '17': '144x176',
- '18': '360x640',
- '22': '720x1280',
- '34': '360x640',
- '35': '480x854',
- '37': '1080x1920',
- '38': '3072x4096',
- '43': '360x640',
- '44': '480x854',
- '45': '720x1280',
- '46': '1080x1920',
- }
- IE_NAME = u'youtube'
-
- def suitable(self, url):
- """Receives a URL and returns True if suitable for this IE."""
- return re.match(self._VALID_URL, url, re.VERBOSE) is not None
-
- def report_lang(self):
- """Report attempt to set language."""
- self._downloader.to_screen(u'[youtube] Setting language')
-
- def report_login(self):
- """Report attempt to log in."""
- self._downloader.to_screen(u'[youtube] Logging in')
-
- def report_age_confirmation(self):
- """Report attempt to confirm age."""
- self._downloader.to_screen(u'[youtube] Confirming age')
-
- def report_video_webpage_download(self, video_id):
- """Report attempt to download video webpage."""
- self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id)
-
- def report_video_info_webpage_download(self, video_id):
- """Report attempt to download video info webpage."""
- self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id)
-
- def report_video_subtitles_download(self, video_id):
- """Report attempt to download video info webpage."""
- self._downloader.to_screen(u'[youtube] %s: Downloading video subtitles' % video_id)
-
- def report_information_extraction(self, video_id):
- """Report attempt to extract video information."""
- self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id)
-
- def report_unavailable_format(self, video_id, format):
- """Report extracted video URL."""
- self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format))
-
- def report_rtmp_download(self):
- """Indicate the download will use the RTMP protocol."""
- self._downloader.to_screen(u'[youtube] RTMP download detected')
-
- def _closed_captions_xml_to_srt(self, xml_string):
- srt = ''
- texts = re.findall(r'<text start="([\d\.]+)"( dur="([\d\.]+)")?>([^<]+)</text>', xml_string, re.MULTILINE)
- # TODO parse xml instead of regex
- for n, (start, dur_tag, dur, caption) in enumerate(texts):
- if not dur: dur = '4'
- start = float(start)
- end = start + float(dur)
- start = "%02i:%02i:%02i,%03i" %(start/(60*60), start/60%60, start%60, start%1*1000)
- end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000)
- caption = unescapeHTML(caption)
- caption = unescapeHTML(caption) # double cycle, intentional
- srt += str(n+1) + '\n'
- srt += start + ' --> ' + end + '\n'
- srt += caption + '\n\n'
- return srt
-
- def _extract_subtitles(self, video_id):
- self.report_video_subtitles_download(video_id)
- request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id)
- try:
- srt_list = compat_urllib_request.urlopen(request).read().decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- return (u'WARNING: unable to download video subtitles: %s' % compat_str(err), None)
- srt_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', srt_list)
- srt_lang_list = dict((l[1], l[0]) for l in srt_lang_list)
- if not srt_lang_list:
- return (u'WARNING: video has no closed captions', None)
- if self._downloader.params.get('subtitleslang', False):
- srt_lang = self._downloader.params.get('subtitleslang')
- elif 'en' in srt_lang_list:
- srt_lang = 'en'
- else:
- srt_lang = list(srt_lang_list.keys())[0]
- if not srt_lang in srt_lang_list:
- return (u'WARNING: no closed captions found in the specified language', None)
- request = compat_urllib_request.Request('http://www.youtube.com/api/timedtext?lang=%s&name=%s&v=%s' % (srt_lang, srt_lang_list[srt_lang], video_id))
- try:
- srt_xml = compat_urllib_request.urlopen(request).read().decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- return (u'WARNING: unable to download video subtitles: %s' % compat_str(err), None)
- if not srt_xml:
- return (u'WARNING: unable to download video subtitles', None)
- return (None, self._closed_captions_xml_to_srt(srt_xml))
-
- def _print_formats(self, formats):
- print('Available formats:')
- for x in formats:
- print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???')))
-
- def _real_initialize(self):
- if self._downloader is None:
- return
-
- username = None
- password = None
- downloader_params = self._downloader.params
-
- # Attempt to use provided username and password or .netrc data
- if downloader_params.get('username', None) is not None:
- username = downloader_params['username']
- password = downloader_params['password']
- elif downloader_params.get('usenetrc', False):
- try:
- info = netrc.netrc().authenticators(self._NETRC_MACHINE)
- if info is not None:
- username = info[0]
- password = info[2]
- else:
- raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
- except (IOError, netrc.NetrcParseError) as err:
- self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % compat_str(err))
- return
-
- # Set language
- request = compat_urllib_request.Request(self._LANG_URL)
- try:
- self.report_lang()
- compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.to_stderr(u'WARNING: unable to set language: %s' % compat_str(err))
- return
-
- # No authentication to be performed
- if username is None:
- return
-
- # Log in
- login_form = {
- 'current_form': 'loginForm',
- 'next': '/',
- 'action_login': 'Log In',
- 'username': username,
- 'password': password,
- }
- request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form))
- try:
- self.report_login()
- login_results = compat_urllib_request.urlopen(request).read().decode('utf-8')
- if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None:
- self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password')
- return
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.to_stderr(u'WARNING: unable to log in: %s' % compat_str(err))
- return
-
- # Confirm age
- age_form = {
- 'next_url': '/',
- 'action_confirm': 'Confirm',
- }
- request = compat_urllib_request.Request(self._AGE_URL, compat_urllib_parse.urlencode(age_form))
- try:
- self.report_age_confirmation()
- age_results = compat_urllib_request.urlopen(request).read().decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err))
- return
-
- def _extract_id(self, url):
- mobj = re.match(self._VALID_URL, url, re.VERBOSE)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
- video_id = mobj.group(2)
- return video_id
-
- def _real_extract(self, url):
- # Extract original video URL from URL with redirection, like age verification, using next_url parameter
- mobj = re.search(self._NEXT_URL_RE, url)
- if mobj:
- url = 'http://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/')
- video_id = self._extract_id(url)
-
- # Get video webpage
- self.report_video_webpage_download(video_id)
- url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id
- request = compat_urllib_request.Request(url)
- try:
- video_webpage_bytes = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
- return
-
- video_webpage = video_webpage_bytes.decode('utf-8', 'ignore')
-
- # Attempt to extract SWF player URL
- mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
- if mobj is not None:
- player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
- else:
- player_url = None
-
- # Get video info
- self.report_video_info_webpage_download(video_id)
- for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
- video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
- % (video_id, el_type))
- request = compat_urllib_request.Request(video_info_url)
- try:
- video_info_webpage_bytes = compat_urllib_request.urlopen(request).read()
- video_info_webpage = video_info_webpage_bytes.decode('utf-8', 'ignore')
- video_info = compat_parse_qs(video_info_webpage)
- if 'token' in video_info:
- break
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % compat_str(err))
- return
- if 'token' not in video_info:
- if 'reason' in video_info:
- self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0])
- else:
- self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason')
- return
-
- # Check for "rental" videos
- if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
- self._downloader.trouble(u'ERROR: "rental" videos not supported')
- return
-
- # Start extracting information
- self.report_information_extraction(video_id)
-
- # uploader
- if 'author' not in video_info:
- self._downloader.trouble(u'ERROR: unable to extract uploader name')
- return
- video_uploader = compat_urllib_parse.unquote_plus(video_info['author'][0])
-
- # uploader_id
- video_uploader_id = None
- mobj = re.search(r'<link itemprop="url" href="http://www.youtube.com/user/([^"]+)">', video_webpage)
- if mobj is not None:
- video_uploader_id = mobj.group(1)
- else:
- self._downloader.trouble(u'WARNING: unable to extract uploader nickname')
-
- # title
- if 'title' not in video_info:
- self._downloader.trouble(u'ERROR: unable to extract video title')
- return
- video_title = compat_urllib_parse.unquote_plus(video_info['title'][0])
-
- # thumbnail image
- if 'thumbnail_url' not in video_info:
- self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
- video_thumbnail = ''
- else: # don't panic if we can't find it
- video_thumbnail = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0])
-
- # upload date
- upload_date = None
- mobj = re.search(r'id="eow-date.*?>(.*?)</span>', video_webpage, re.DOTALL)
- if mobj is not None:
- upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
- format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y']
- for expression in format_expressions:
- try:
- upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d')
- except:
- pass
-
- # description
- video_description = get_element_by_id("eow-description", video_webpage)
- if video_description:
- video_description = clean_html(video_description)
- else:
- video_description = ''
-
- # closed captions
- video_subtitles = None
- if self._downloader.params.get('writesubtitles', False):
- (srt_error, video_subtitles) = self._extract_subtitles(video_id)
- if srt_error:
- self._downloader.trouble(srt_error)
-
- if 'length_seconds' not in video_info:
- self._downloader.trouble(u'WARNING: unable to extract video duration')
- video_duration = ''
- else:
- video_duration = compat_urllib_parse.unquote_plus(video_info['length_seconds'][0])
-
- # token
- video_token = compat_urllib_parse.unquote_plus(video_info['token'][0])
-
- # Decide which formats to download
- req_format = self._downloader.params.get('format', None)
-
- if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
- self.report_rtmp_download()
- video_url_list = [(None, video_info['conn'][0])]
- elif 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1:
- url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',')
- url_data = [compat_parse_qs(uds) for uds in url_data_strs]
- url_data = [ud for ud in url_data if 'itag' in ud and 'url' in ud]
- url_map = dict((ud['itag'][0], ud['url'][0] + '&signature=' + ud['sig'][0]) for ud in url_data)
-
- format_limit = self._downloader.params.get('format_limit', None)
- available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats
- if format_limit is not None and format_limit in available_formats:
- format_list = available_formats[available_formats.index(format_limit):]
- else:
- format_list = available_formats
- existing_formats = [x for x in format_list if x in url_map]
- if len(existing_formats) == 0:
- self._downloader.trouble(u'ERROR: no known formats available for video')
- return
- if self._downloader.params.get('listformats', None):
- self._print_formats(existing_formats)
- return
- if req_format is None or req_format == 'best':
- video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
- elif req_format == 'worst':
- video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality
- elif req_format in ('-1', 'all'):
- video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
- else:
- # Specific formats. We pick the first in a slash-delimeted sequence.
- # For example, if '1/2/3/4' is requested and '2' and '4' are available, we pick '2'.
- req_formats = req_format.split('/')
- video_url_list = None
- for rf in req_formats:
- if rf in url_map:
- video_url_list = [(rf, url_map[rf])]
- break
- if video_url_list is None:
- self._downloader.trouble(u'ERROR: requested format not available')
- return
- else:
- self._downloader.trouble(u'ERROR: no conn or url_encoded_fmt_stream_map information found in video info')
- return
-
- results = []
- for format_param, video_real_url in video_url_list:
- # Extension
- video_extension = self._video_extensions.get(format_param, 'flv')
-
- video_format = '{0} - {1}'.format(format_param if format_param else video_extension,
- self._video_dimensions.get(format_param, '???'))
-
- results.append({
- 'id': video_id,
- 'url': video_real_url,
- 'uploader': video_uploader,
- 'uploader_id': video_uploader_id,
- 'upload_date': upload_date,
- 'title': video_title,
- 'ext': video_extension,
- 'format': video_format,
- 'thumbnail': video_thumbnail,
- 'description': video_description,
- 'player_url': player_url,
- 'subtitles': video_subtitles,
- 'duration': video_duration
- })
- return results
-
-
-class MetacafeIE(InfoExtractor):
- """Information Extractor for metacafe.com."""
-
- _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
- _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
- _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
- IE_NAME = u'metacafe'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_disclaimer(self):
- """Report disclaimer retrieval."""
- self._downloader.to_screen(u'[metacafe] Retrieving disclaimer')
-
- def report_age_confirmation(self):
- """Report attempt to confirm age."""
- self._downloader.to_screen(u'[metacafe] Confirming age')
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id)
-
- def _real_initialize(self):
- # Retrieve disclaimer
- request = compat_urllib_request.Request(self._DISCLAIMER)
- try:
- self.report_disclaimer()
- disclaimer = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % compat_str(err))
- return
-
- # Confirm age
- disclaimer_form = {
- 'filters': '0',
- 'submit': "Continue - I'm over 18",
- }
- request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form))
- try:
- self.report_age_confirmation()
- disclaimer = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err))
- return
-
- def _real_extract(self, url):
- # Extract id and simplified title from URL
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
-
- video_id = mobj.group(1)
-
- # Check if video comes from YouTube
- mobj2 = re.match(r'^yt-(.*)$', video_id)
- if mobj2 is not None:
- self._downloader.download(['http://www.youtube.com/watch?v=%s' % mobj2.group(1)])
- return
-
- # Retrieve video webpage to extract further information
- request = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id)
- try:
- self.report_download_webpage(video_id)
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % compat_str(err))
- return
-
- # Extract URL, uploader and title from webpage
- self.report_extraction(video_id)
- mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
- if mobj is not None:
- mediaURL = compat_urllib_parse.unquote(mobj.group(1))
- video_extension = mediaURL[-3:]
-
- # Extract gdaKey if available
- mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
- if mobj is None:
- video_url = mediaURL
- else:
- gdaKey = mobj.group(1)
- video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
- else:
- mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
- vardict = compat_parse_qs(mobj.group(1))
- if 'mediaData' not in vardict:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
- mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0])
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
- mediaURL = mobj.group(1).replace('\\/', '/')
- video_extension = mediaURL[-3:]
- video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2))
-
- mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
- return
- video_title = mobj.group(1).decode('utf-8')
-
- mobj = re.search(r'submitter=(.*?);', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
- return
- video_uploader = mobj.group(1)
-
- return [{
- 'id': video_id.decode('utf-8'),
- 'url': video_url.decode('utf-8'),
- 'uploader': video_uploader.decode('utf-8'),
- 'upload_date': None,
- 'title': video_title,
- 'ext': video_extension.decode('utf-8'),
- }]
-
-
-class DailymotionIE(InfoExtractor):
- """Information Extractor for Dailymotion"""
-
- _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)'
- IE_NAME = u'dailymotion'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)
-
- def _real_extract(self, url):
- # Extract id and simplified title from URL
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
-
- video_id = mobj.group(1).split('_')[0].split('?')[0]
-
- video_extension = 'mp4'
-
- # Retrieve video webpage to extract further information
- request = compat_urllib_request.Request(url)
- request.add_header('Cookie', 'family_filter=off')
- try:
- self.report_download_webpage(video_id)
- webpage_bytes = compat_urllib_request.urlopen(request).read()
- webpage = webpage_bytes.decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % compat_str(err))
- return
-
- # Extract URL, uploader and title from webpage
- self.report_extraction(video_id)
- mobj = re.search(r'\s*var flashvars = (.*)', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
- flashvars = compat_urllib_parse.unquote(mobj.group(1))
-
- for key in ['hd1080URL', 'hd720URL', 'hqURL', 'sdURL', 'ldURL', 'video_url']:
- if key in flashvars:
- max_quality = key
- self._downloader.to_screen(u'[dailymotion] Using %s' % key)
- break
- else:
- self._downloader.trouble(u'ERROR: unable to extract video URL')
- return
-
- mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video URL')
- return
-
- video_url = compat_urllib_parse.unquote(mobj.group(1)).replace('\\/', '/')
-
- # TODO: support choosing qualities
-
- mobj = re.search(r'<meta property="og:title" content="(?P<title>[^"]*)" />', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
- return
- video_title = unescapeHTML(mobj.group('title'))
-
- video_uploader = None
- mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>', webpage)
- if mobj is None:
- # lookin for official user
- mobj_official = re.search(r'<span rel="author"[^>]+?>([^<]+?)</span>', webpage)
- if mobj_official is None:
- self._downloader.trouble(u'WARNING: unable to extract uploader nickname')
- else:
- video_uploader = mobj_official.group(1)
- else:
- video_uploader = mobj.group(1)
-
- video_upload_date = None
- mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage)
- if mobj is not None:
- video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1)
-
- return [{
- 'id': video_id,
- 'url': video_url,
- 'uploader': video_uploader,
- 'upload_date': video_upload_date,
- 'title': video_title,
- 'ext': video_extension,
- }]
-
-
-class PhotobucketIE(InfoExtractor):
- """Information extractor for photobucket.com."""
-
- _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
- IE_NAME = u'photobucket'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id)
-
- def _real_extract(self, url):
- # Extract id from URL
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
-
- video_id = mobj.group(1)
-
- video_extension = 'flv'
-
- # Retrieve video webpage to extract further information
- request = compat_urllib_request.Request(url)
- try:
- self.report_download_webpage(video_id)
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
- return
-
- # Extract URL, uploader, and title from webpage
- self.report_extraction(video_id)
- mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
- mediaURL = compat_urllib_parse.unquote(mobj.group(1))
-
- video_url = mediaURL
-
- mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
- return
- video_title = mobj.group(1).decode('utf-8')
-
- video_uploader = mobj.group(2).decode('utf-8')
-
- return [{
- 'id': video_id.decode('utf-8'),
- 'url': video_url.decode('utf-8'),
- 'uploader': video_uploader,
- 'upload_date': None,
- 'title': video_title,
- 'ext': video_extension.decode('utf-8'),
- }]
-
-
-class YahooIE(InfoExtractor):
- """Information extractor for video.yahoo.com."""
-
- _WORKING = False
- # _VALID_URL matches all Yahoo! Video URLs
- # _VPAGE_URL matches only the extractable '/watch/' URLs
- _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?'
- _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?'
- IE_NAME = u'video.yahoo'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id)
-
- def _real_extract(self, url, new_video=True):
- # Extract ID from URL
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
-
- video_id = mobj.group(2)
- video_extension = 'flv'
-
- # Rewrite valid but non-extractable URLs as
- # extractable English language /watch/ URLs
- if re.match(self._VPAGE_URL, url) is None:
- request = compat_urllib_request.Request(url)
- try:
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
- return
-
- mobj = re.search(r'\("id", "([0-9]+)"\);', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Unable to extract id field')
- return
- yahoo_id = mobj.group(1)
-
- mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Unable to extract vid field')
- return
- yahoo_vid = mobj.group(1)
-
- url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id)
- return self._real_extract(url, new_video=False)
-
- # Retrieve video webpage to extract further information
- request = compat_urllib_request.Request(url)
- try:
- self.report_download_webpage(video_id)
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
- return
-
- # Extract uploader and title from webpage
- self.report_extraction(video_id)
- mobj = re.search(r'<meta name="title" content="(.*)" />', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video title')
- return
- video_title = mobj.group(1).decode('utf-8')
-
- mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video uploader')
- return
- video_uploader = mobj.group(1).decode('utf-8')
-
- # Extract video thumbnail
- mobj = re.search(r'<link rel="image_src" href="(.*)" />', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
- return
- video_thumbnail = mobj.group(1).decode('utf-8')
-
- # Extract video description
- mobj = re.search(r'<meta name="description" content="(.*)" />', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video description')
- return
- video_description = mobj.group(1).decode('utf-8')
- if not video_description:
- video_description = 'No description available.'
-
- # Extract video height and width
- mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video height')
- return
- yv_video_height = mobj.group(1)
-
- mobj = re.search(r'<meta name="video_width" content="([0-9]+)" />', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video width')
- return
- yv_video_width = mobj.group(1)
-
- # Retrieve video playlist to extract media URL
- # I'm not completely sure what all these options are, but we
- # seem to need most of them, otherwise the server sends a 401.
- yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents
- yv_bitrate = '700' # according to Wikipedia this is hard-coded
- request = compat_urllib_request.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id +
- '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height +
- '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797')
- try:
- self.report_download_webpage(video_id)
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
- return
-
- # Extract media URL from playlist XML
- mobj = re.search(r'<STREAM APP="(http://.*)" FULLPATH="/?(/.*\.flv\?[^"]*)"', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Unable to extract media URL')
- return
- video_url = compat_urllib_parse.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8')
- video_url = unescapeHTML(video_url)
-
- return [{
- 'id': video_id.decode('utf-8'),
- 'url': video_url,
- 'uploader': video_uploader,
- 'upload_date': None,
- 'title': video_title,
- 'ext': video_extension.decode('utf-8'),
- 'thumbnail': video_thumbnail.decode('utf-8'),
- 'description': video_description,
- }]
-
-
-class VimeoIE(InfoExtractor):
- """Information extractor for vimeo.com."""
-
- # _VALID_URL matches Vimeo URLs
- _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:(?:groups|album)/[^/]+/)?(?:videos?/)?([0-9]+)'
- IE_NAME = u'vimeo'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id)
-
- def _real_extract(self, url, new_video=True):
- # Extract ID from URL
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
-
- video_id = mobj.group(1)
-
- # Retrieve video webpage to extract further information
- request = compat_urllib_request.Request(url, None, std_headers)
- try:
- self.report_download_webpage(video_id)
- webpage_bytes = compat_urllib_request.urlopen(request).read()
- webpage = webpage_bytes.decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
- return
-
- # Now we begin extracting as much information as we can from what we
- # retrieved. First we extract the information common to all extractors,
- # and latter we extract those that are Vimeo specific.
- self.report_extraction(video_id)
-
- # Extract the config JSON
- try:
- config = webpage.split(' = {config:')[1].split(',assets:')[0]
- config = json.loads(config)
- except:
- self._downloader.trouble(u'ERROR: unable to extract info section')
- return
-
- # Extract title
- video_title = config["video"]["title"]
-
- # Extract uploader and uploader_id
- video_uploader = config["video"]["owner"]["name"]
- video_uploader_id = config["video"]["owner"]["url"].split('/')[-1]
-
- # Extract video thumbnail
- video_thumbnail = config["video"]["thumbnail"]
-
- # Extract video description
- video_description = get_element_by_attribute("itemprop", "description", webpage)
- if video_description: video_description = clean_html(video_description)
- else: video_description = ''
-
- # Extract upload date
- video_upload_date = None
- mobj = re.search(r'<meta itemprop="dateCreated" content="(\d{4})-(\d{2})-(\d{2})T', webpage)
- if mobj is not None:
- video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3)
-
- # Vimeo specific: extract request signature and timestamp
- sig = config['request']['signature']
- timestamp = config['request']['timestamp']
-
- # Vimeo specific: extract video codec and quality information
- # First consider quality, then codecs, then take everything
- # TODO bind to format param
- codecs = [('h264', 'mp4'), ('vp8', 'flv'), ('vp6', 'flv')]
- files = { 'hd': [], 'sd': [], 'other': []}
- for codec_name, codec_extension in codecs:
- if codec_name in config["video"]["files"]:
- if 'hd' in config["video"]["files"][codec_name]:
- files['hd'].append((codec_name, codec_extension, 'hd'))
- elif 'sd' in config["video"]["files"][codec_name]:
- files['sd'].append((codec_name, codec_extension, 'sd'))
- else:
- files['other'].append((codec_name, codec_extension, config["video"]["files"][codec_name][0]))
-
- for quality in ('hd', 'sd', 'other'):
- if len(files[quality]) > 0:
- video_quality = files[quality][0][2]
- video_codec = files[quality][0][0]
- video_extension = files[quality][0][1]
- self._downloader.to_screen(u'[vimeo] %s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality))
- break
- else:
- self._downloader.trouble(u'ERROR: no known codec found')
- return
-
- video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \
- %(video_id, sig, timestamp, video_quality, video_codec.upper())
-
- return [{
- 'id': video_id,
- 'url': video_url,
- 'uploader': video_uploader,
- 'uploader_id': video_uploader_id,
- 'upload_date': video_upload_date,
- 'title': video_title,
- 'ext': video_extension,
- 'thumbnail': video_thumbnail,
- 'description': video_description,
- }]
-
-
-class ArteTvIE(InfoExtractor):
- """arte.tv information extractor."""
-
- _VALID_URL = r'(?:http://)?videos\.arte\.tv/(?:fr|de)/videos/.*'
- _LIVE_URL = r'index-[0-9]+\.html$'
-
- IE_NAME = u'arte.tv'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[arte.tv] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[arte.tv] %s: Extracting information' % video_id)
-
- def fetch_webpage(self, url):
- self._downloader.increment_downloads()
- request = compat_urllib_request.Request(url)
- try:
- self.report_download_webpage(url)
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
- return
- except ValueError as err:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
- return webpage
-
- def grep_webpage(self, url, regex, regexFlags, matchTuples):
- page = self.fetch_webpage(url)
- mobj = re.search(regex, page, regexFlags)
- info = {}
-
- if mobj is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
-
- for (i, key, err) in matchTuples:
- if mobj.group(i) is None:
- self._downloader.trouble(err)
- return
- else:
- info[key] = mobj.group(i)
-
- return info
-
- def extractLiveStream(self, url):
- video_lang = url.split('/')[-4]
- info = self.grep_webpage(
- url,
- r'src="(.*?/videothek_js.*?\.js)',
- 0,
- [
- (1, 'url', u'ERROR: Invalid URL: %s' % url)
- ]
- )
- http_host = url.split('/')[2]
- next_url = 'http://%s%s' % (http_host, compat_urllib_parse.unquote(info.get('url')))
- info = self.grep_webpage(
- next_url,
- r'(s_artestras_scst_geoFRDE_' + video_lang + '.*?)\'.*?' +
- '(http://.*?\.swf).*?' +
- '(rtmp://.*?)\'',
- re.DOTALL,
- [
- (1, 'path', u'ERROR: could not extract video path: %s' % url),
- (2, 'player', u'ERROR: could not extract video player: %s' % url),
- (3, 'url', u'ERROR: could not extract video url: %s' % url)
- ]
- )
- video_url = u'%s/%s' % (info.get('url'), info.get('path'))
-
- def extractPlus7Stream(self, url):
- video_lang = url.split('/')[-3]
- info = self.grep_webpage(
- url,
- r'param name="movie".*?videorefFileUrl=(http[^\'"&]*)',
- 0,
- [
- (1, 'url', u'ERROR: Invalid URL: %s' % url)
- ]
- )
- next_url = compat_urllib_parse.unquote(info.get('url'))
- info = self.grep_webpage(
- next_url,
- r'<video lang="%s" ref="(http[^\'"&]*)' % video_lang,
- 0,
- [
- (1, 'url', u'ERROR: Could not find <video> tag: %s' % url)
- ]
- )
- next_url = compat_urllib_parse.unquote(info.get('url'))
-
- info = self.grep_webpage(
- next_url,
- r'<video id="(.*?)".*?>.*?' +
- '<name>(.*?)</name>.*?' +
- '<dateVideo>(.*?)</dateVideo>.*?' +
- '<url quality="hd">(.*?)</url>',
- re.DOTALL,
- [
- (1, 'id', u'ERROR: could not extract video id: %s' % url),
- (2, 'title', u'ERROR: could not extract video title: %s' % url),
- (3, 'date', u'ERROR: could not extract video date: %s' % url),
- (4, 'url', u'ERROR: could not extract video url: %s' % url)
- ]
- )
-
- return {
- 'id': info.get('id'),
- 'url': compat_urllib_parse.unquote(info.get('url')),
- 'uploader': u'arte.tv',
- 'upload_date': info.get('date'),
- 'title': info.get('title').decode('utf-8'),
- 'ext': u'mp4',
- 'format': u'NA',
- 'player_url': None,
- }
-
- def _real_extract(self, url):
- video_id = url.split('/')[-1]
- self.report_extraction(video_id)
-
- if re.search(self._LIVE_URL, video_id) is not None:
- self.extractLiveStream(url)
- return
- else:
- info = self.extractPlus7Stream(url)
-
- return [info]
-
-
-class GenericIE(InfoExtractor):
- """Generic last-resort information extractor."""
-
- _VALID_URL = r'.*'
- IE_NAME = u'generic'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.')
- self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id)
-
- def report_following_redirect(self, new_url):
- """Report information extraction."""
- self._downloader.to_screen(u'[redirect] Following redirect to %s' % new_url)
-
- def _test_redirect(self, url):
- """Check if it is a redirect, like url shorteners, in case restart chain."""
- class HeadRequest(compat_urllib_request.Request):
- def get_method(self):
- return "HEAD"
-
- class HEADRedirectHandler(compat_urllib_request.HTTPRedirectHandler):
- """
- Subclass the HTTPRedirectHandler to make it use our
- HeadRequest also on the redirected URL
- """
- def redirect_request(self, req, fp, code, msg, headers, newurl):
- if code in (301, 302, 303, 307):
- newurl = newurl.replace(' ', '%20')
- newheaders = dict((k,v) for k,v in req.headers.items()
- if k.lower() not in ("content-length", "content-type"))
- return HeadRequest(newurl,
- headers=newheaders,
- origin_req_host=req.get_origin_req_host(),
- unverifiable=True)
- else:
- raise compat_urllib_error.HTTPError(req.get_full_url(), code, msg, headers, fp)
-
- class HTTPMethodFallback(compat_urllib_request.BaseHandler):
- """
- Fallback to GET if HEAD is not allowed (405 HTTP error)
- """
- def http_error_405(self, req, fp, code, msg, headers):
- fp.read()
- fp.close()
-
- newheaders = dict((k,v) for k,v in req.headers.items()
- if k.lower() not in ("content-length", "content-type"))
- return self.parent.open(compat_urllib_request.Request(req.get_full_url(),
- headers=newheaders,
- origin_req_host=req.get_origin_req_host(),
- unverifiable=True))
-
- # Build our opener
- opener = compat_urllib_request.OpenerDirector()
- for handler in [compat_urllib_request.HTTPHandler, compat_urllib_request.HTTPDefaultErrorHandler,
- HTTPMethodFallback, HEADRedirectHandler,
- compat_urllib_error.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]:
- opener.add_handler(handler())
-
- response = opener.open(HeadRequest(url))
- new_url = response.geturl()
-
- if url == new_url:
- return False
-
- self.report_following_redirect(new_url)
- self._downloader.download([new_url])
- return True
-
- def _real_extract(self, url):
- if self._test_redirect(url): return
-
- video_id = url.split('/')[-1]
- request = compat_urllib_request.Request(url)
- try:
- self.report_download_webpage(video_id)
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
- return
- except ValueError as err:
- # since this is the last-resort InfoExtractor, if
- # this error is thrown, it'll be thrown here
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
-
- self.report_extraction(video_id)
- # Start with something easy: JW Player in SWFObject
- mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
- if mobj is None:
- # Broaden the search a little bit
- mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
-
- # It's possible that one of the regexes
- # matched, but returned an empty group:
- if mobj.group(1) is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
-
- video_url = compat_urllib_parse.unquote(mobj.group(1))
- video_id = os.path.basename(video_url)
-
- # here's a fun little line of code for you:
- video_extension = os.path.splitext(video_id)[1][1:]
- video_id = os.path.splitext(video_id)[0]
-
- # it's tempting to parse this further, but you would
- # have to take into account all the variations like
- # Video Title - Site Name
- # Site Name | Video Title
- # Video Title - Tagline | Site Name
- # and so on and so forth; it's just not practical
- mobj = re.search(r'<title>(.*)</title>', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
- return
- video_title = mobj.group(1)
-
- # video uploader is domain name
- mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
- return
- video_uploader = mobj.group(1)
-
- return [{
- 'id': video_id,
- 'url': video_url,
- 'uploader': video_uploader,
- 'upload_date': None,
- 'title': video_title,
- 'ext': video_extension,
- }]
-
-
-class YoutubeSearchIE(InfoExtractor):
- """Information Extractor for YouTube search queries."""
- _VALID_URL = r'ytsearch(\d+|all)?:[\s\S]+'
- _API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc'
- _max_youtube_results = 1000
- IE_NAME = u'youtube:search'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_page(self, query, pagenum):
- """Report attempt to download search page with given number."""
- query = query.decode(preferredencoding())
- self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
-
- def _real_extract(self, query):
- mobj = re.match(self._VALID_URL, query)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
- return
-
- prefix, query = query.split(':')
- prefix = prefix[8:]
- query = query.encode('utf-8')
- if prefix == '':
- self._download_n_results(query, 1)
- return
- elif prefix == 'all':
- self._download_n_results(query, self._max_youtube_results)
- return
- else:
- try:
- n = int(prefix)
- if n <= 0:
- self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
- return
- elif n > self._max_youtube_results:
- self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
- n = self._max_youtube_results
- self._download_n_results(query, n)
- return
- except ValueError: # parsing prefix as integer fails
- self._download_n_results(query, 1)
- return
-
- def _download_n_results(self, query, n):
- """Downloads a specified number of results for a query"""
-
- video_ids = []
- pagenum = 0
- limit = n
-
- while (50 * pagenum) < limit:
- self.report_download_page(query, pagenum+1)
- result_url = self._API_URL % (compat_urllib_parse.quote_plus(query), (50*pagenum)+1)
- request = compat_urllib_request.Request(result_url)
- try:
- data = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download API page: %s' % compat_str(err))
- return
- api_response = json.loads(data)['data']
-
- new_ids = list(video['id'] for video in api_response['items'])
- video_ids += new_ids
-
- limit = min(n, api_response['totalItems'])
- pagenum += 1
-
- if len(video_ids) > n:
- video_ids = video_ids[:n]
- for id in video_ids:
- self._downloader.download(['http://www.youtube.com/watch?v=%s' % id])
- return
-
-
-class GoogleSearchIE(InfoExtractor):
- """Information Extractor for Google Video search queries."""
- _VALID_URL = r'gvsearch(\d+|all)?:[\s\S]+'
- _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en'
- _VIDEO_INDICATOR = r'<a href="http://video\.google\.com/videoplay\?docid=([^"\&]+)'
- _MORE_PAGES_INDICATOR = r'class="pn" id="pnnext"'
- _max_google_results = 1000
- IE_NAME = u'video.google:search'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_page(self, query, pagenum):
- """Report attempt to download playlist page with given number."""
- query = query.decode(preferredencoding())
- self._downloader.to_screen(u'[video.google] query "%s": Downloading page %s' % (query, pagenum))
-
- def _real_extract(self, query):
- mobj = re.match(self._VALID_URL, query)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
- return
-
- prefix, query = query.split(':')
- prefix = prefix[8:]
- query = query.encode('utf-8')
- if prefix == '':
- self._download_n_results(query, 1)
- return
- elif prefix == 'all':
- self._download_n_results(query, self._max_google_results)
- return
- else:
- try:
- n = int(prefix)
- if n <= 0:
- self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
- return
- elif n > self._max_google_results:
- self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n))
- n = self._max_google_results
- self._download_n_results(query, n)
- return
- except ValueError: # parsing prefix as integer fails
- self._download_n_results(query, 1)
- return
-
- def _download_n_results(self, query, n):
- """Downloads a specified number of results for a query"""
-
- video_ids = []
- pagenum = 0
-
- while True:
- self.report_download_page(query, pagenum)
- result_url = self._TEMPLATE_URL % (compat_urllib_parse.quote_plus(query), pagenum*10)
- request = compat_urllib_request.Request(result_url)
- try:
- page = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
- return
-
- # Extract video identifiers
- for mobj in re.finditer(self._VIDEO_INDICATOR, page):
- video_id = mobj.group(1)
- if video_id not in video_ids:
- video_ids.append(video_id)
- if len(video_ids) == n:
- # Specified n videos reached
- for id in video_ids:
- self._downloader.download(['http://video.google.com/videoplay?docid=%s' % id])
- return
-
- if re.search(self._MORE_PAGES_INDICATOR, page) is None:
- for id in video_ids:
- self._downloader.download(['http://video.google.com/videoplay?docid=%s' % id])
- return
-
- pagenum = pagenum + 1
-
-
-class YahooSearchIE(InfoExtractor):
- """Information Extractor for Yahoo! Video search queries."""
-
- _WORKING = False
- _VALID_URL = r'yvsearch(\d+|all)?:[\s\S]+'
- _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s'
- _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"'
- _MORE_PAGES_INDICATOR = r'\s*Next'
- _max_yahoo_results = 1000
- IE_NAME = u'video.yahoo:search'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_page(self, query, pagenum):
- """Report attempt to download playlist page with given number."""
- query = query.decode(preferredencoding())
- self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum))
-
- def _real_extract(self, query):
- mobj = re.match(self._VALID_URL, query)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
- return
-
- prefix, query = query.split(':')
- prefix = prefix[8:]
- query = query.encode('utf-8')
- if prefix == '':
- self._download_n_results(query, 1)
- return
- elif prefix == 'all':
- self._download_n_results(query, self._max_yahoo_results)
- return
- else:
- try:
- n = int(prefix)
- if n <= 0:
- self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
- return
- elif n > self._max_yahoo_results:
- self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n))
- n = self._max_yahoo_results
- self._download_n_results(query, n)
- return
- except ValueError: # parsing prefix as integer fails
- self._download_n_results(query, 1)
- return
-
- def _download_n_results(self, query, n):
- """Downloads a specified number of results for a query"""
-
- video_ids = []
- already_seen = set()
- pagenum = 1
-
- while True:
- self.report_download_page(query, pagenum)
- result_url = self._TEMPLATE_URL % (compat_urllib_parse.quote_plus(query), pagenum)
- request = compat_urllib_request.Request(result_url)
- try:
- page = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
- return
-
- # Extract video identifiers
- for mobj in re.finditer(self._VIDEO_INDICATOR, page):
- video_id = mobj.group(1)
- if video_id not in already_seen:
- video_ids.append(video_id)
- already_seen.add(video_id)
- if len(video_ids) == n:
- # Specified n videos reached
- for id in video_ids:
- self._downloader.download(['http://video.yahoo.com/watch/%s' % id])
- return
-
- if re.search(self._MORE_PAGES_INDICATOR, page) is None:
- for id in video_ids:
- self._downloader.download(['http://video.yahoo.com/watch/%s' % id])
- return
-
- pagenum = pagenum + 1
-
-
-class YoutubePlaylistIE(InfoExtractor):
- """Information Extractor for YouTube playlists."""
-
- _VALID_URL = r'(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL|EC)?|PL|EC)([0-9A-Za-z-_]{10,})(?:/.*?/([0-9A-Za-z_-]+))?.*'
- _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
- _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&([^&"]+&)*list=.*?%s'
- _MORE_PAGES_INDICATOR = u"Next \N{RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK}"
- IE_NAME = u'youtube:playlist'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_page(self, playlist_id, pagenum):
- """Report attempt to download playlist page with given number."""
- self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
-
- def _real_extract(self, url):
- # Extract playlist id
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid url: %s' % url)
- return
-
- # Single video case
- if mobj.group(3) is not None:
- self._downloader.download([mobj.group(3)])
- return
-
- # Download playlist pages
- # prefix is 'p' as default for playlists but there are other types that need extra care
- playlist_prefix = mobj.group(1)
- if playlist_prefix == 'a':
- playlist_access = 'artist'
- else:
- playlist_prefix = 'p'
- playlist_access = 'view_play_list'
- playlist_id = mobj.group(2)
- video_ids = []
- pagenum = 1
-
- while True:
- self.report_download_page(playlist_id, pagenum)
- url = self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum)
- request = compat_urllib_request.Request(url)
- try:
- page = compat_urllib_request.urlopen(request).read().decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
- return
-
- # Extract video identifiers
- ids_in_page = []
- for mobj in re.finditer(self._VIDEO_INDICATOR_TEMPLATE % playlist_id, page):
- if mobj.group(1) not in ids_in_page:
- ids_in_page.append(mobj.group(1))
- video_ids.extend(ids_in_page)
-
- if self._MORE_PAGES_INDICATOR not in page:
- break
- pagenum = pagenum + 1
-
- total = len(video_ids)
-
- playliststart = self._downloader.params.get('playliststart', 1) - 1
- playlistend = self._downloader.params.get('playlistend', -1)
- if playlistend == -1:
- video_ids = video_ids[playliststart:]
- else:
- video_ids = video_ids[playliststart:playlistend]
-
- if len(video_ids) == total:
- self._downloader.to_screen(u'[youtube] PL %s: Found %i videos' % (playlist_id, total))
- else:
- self._downloader.to_screen(u'[youtube] PL %s: Found %i videos, downloading %i' % (playlist_id, total, len(video_ids)))
-
- for id in video_ids:
- self._downloader.download(['http://www.youtube.com/watch?v=%s' % id])
- return
-
-
-class YoutubeChannelIE(InfoExtractor):
- """Information Extractor for YouTube channels."""
-
- _VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)(?:/.*)?$"
- _TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en'
- _MORE_PAGES_INDICATOR = u"Next \N{RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK}"
- IE_NAME = u'youtube:channel'
-
- def report_download_page(self, channel_id, pagenum):
- """Report attempt to download channel page with given number."""
- self._downloader.to_screen(u'[youtube] Channel %s: Downloading page #%s' % (channel_id, pagenum))
-
- def _real_extract(self, url):
- # Extract channel id
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid url: %s' % url)
- return
-
- # Download channel pages
- channel_id = mobj.group(1)
- video_ids = []
- pagenum = 1
-
- while True:
- self.report_download_page(channel_id, pagenum)
- url = self._TEMPLATE_URL % (channel_id, pagenum)
- request = compat_urllib_request.Request(url)
- try:
- page = compat_urllib_request.urlopen(request).read().decode('utf8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
- return
+ while True:
+ self.report_download_page(channel_id, pagenum)
+ url = self._TEMPLATE_URL % (channel_id, pagenum)
+ request = compat_urllib_request.Request(url)
+ try:
+ page = compat_urllib_request.urlopen(request).read().decode('utf8')
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
+ return
# Extract video identifiers
ids_in_page = []
while True:
self.report_download_page(username, pagenum)
-
- request = compat_urllib_request.Request( page_base + "&page=" + str(pagenum) )
-
+ url = page_base + "&page=" + str(pagenum)
+ request = compat_urllib_request.Request( url )
try:
page = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
"""Information extractor for depositfiles.com"""
_VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)'
- IE_NAME = u'DepositFiles'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
def report_download_webpage(self, file_id):
"""Report webpage download."""
class FacebookIE(InfoExtractor):
"""Information Extractor for Facebook"""
- _WORKING = False
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
_LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&'
_NETRC_MACHINE = 'facebook'
- _available_formats = ['video', 'highqual', 'lowqual']
- _video_extensions = {
- 'video': 'mp4',
- 'highqual': 'mp4',
- 'lowqual': 'mp4',
- }
IE_NAME = u'facebook'
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def _reporter(self, message):
- """Add header and report message."""
- self._downloader.to_screen(u'[facebook] %s' % message)
-
def report_login(self):
"""Report attempt to log in."""
- self._reporter(u'Logging in')
-
- def report_video_webpage_download(self, video_id):
- """Report attempt to download video webpage."""
- self._reporter(u'%s: Downloading video webpage' % video_id)
-
- def report_information_extraction(self, video_id):
- """Report attempt to extract video information."""
- self._reporter(u'%s: Extracting video information' % video_id)
-
- def _parse_page(self, video_webpage):
- """Extract video information from page"""
- # General data
- data = {'title': r'\("video_title", "(.*?)"\)',
- 'description': r'<div class="datawrap">(.*?)</div>',
- 'owner': r'\("video_owner_name", "(.*?)"\)',
- 'thumbnail': r'\("thumb_url", "(?P<THUMB>.*?)"\)',
- }
- video_info = {}
- for piece in data.keys():
- mobj = re.search(data[piece], video_webpage)
- if mobj is not None:
- video_info[piece] = compat_urllib_parse.unquote_plus(mobj.group(1).decode("unicode_escape"))
-
- # Video urls
- video_urls = {}
- for fmt in self._available_formats:
- mobj = re.search(r'\("%s_src\", "(.+?)"\)' % fmt, video_webpage)
- if mobj is not None:
- # URL is in a Javascript segment inside an escaped Unicode format within
- # the generally utf-8 page
- video_urls[fmt] = compat_urllib_parse.unquote_plus(mobj.group(1).decode("unicode_escape"))
- video_info['video_urls'] = video_urls
-
- return video_info
+ self._downloader.to_screen(u'[%s] Logging in' % self.IE_NAME)
def _real_initialize(self):
if self._downloader is None:
else:
raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
except (IOError, netrc.NetrcParseError) as err:
- self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % compat_str(err))
+ self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err))
return
if useremail is None:
self.report_login()
login_results = compat_urllib_request.urlopen(request).read()
if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None:
- self._downloader.to_stderr(u'WARNING: unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
+ self._downloader.report_warning(u'unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
return
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.to_stderr(u'WARNING: unable to log in: %s' % compat_str(err))
+ self._downloader.report_warning(u'unable to log in: %s' % compat_str(err))
return
def _real_extract(self, url):
return
video_id = mobj.group('ID')
- # Get video webpage
- self.report_video_webpage_download(video_id)
- request = compat_urllib_request.Request('https://www.facebook.com/video/video.php?v=%s' % video_id)
- try:
- page = compat_urllib_request.urlopen(request)
- video_webpage = page.read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
- return
-
- # Start extracting information
- self.report_information_extraction(video_id)
-
- # Extract information
- video_info = self._parse_page(video_webpage)
-
- # uploader
- if 'owner' not in video_info:
- self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
- return
- video_uploader = video_info['owner']
-
- # title
- if 'title' not in video_info:
- self._downloader.trouble(u'ERROR: unable to extract video title')
- return
- video_title = video_info['title']
- video_title = video_title.decode('utf-8')
-
- # thumbnail image
- if 'thumbnail' not in video_info:
- self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
- video_thumbnail = ''
- else:
- video_thumbnail = video_info['thumbnail']
-
- # upload date
- upload_date = None
- if 'upload_date' in video_info:
- upload_time = video_info['upload_date']
- timetuple = email.utils.parsedate_tz(upload_time)
- if timetuple is not None:
- try:
- upload_date = time.strftime('%Y%m%d', timetuple[0:9])
- except:
- pass
-
- # description
- video_description = video_info.get('description', 'No description available.')
+ url = 'https://www.facebook.com/video/video.php?v=%s' % video_id
+ webpage = self._download_webpage(url, video_id)
- url_map = video_info['video_urls']
- if url_map:
- # Decide which formats to download
- req_format = self._downloader.params.get('format', None)
- format_limit = self._downloader.params.get('format_limit', None)
-
- if format_limit is not None and format_limit in self._available_formats:
- format_list = self._available_formats[self._available_formats.index(format_limit):]
- else:
- format_list = self._available_formats
- existing_formats = [x for x in format_list if x in url_map]
- if len(existing_formats) == 0:
- self._downloader.trouble(u'ERROR: no known formats available for video')
- return
- if req_format is None:
- video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
- elif req_format == 'worst':
- video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality
- elif req_format == '-1':
- video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
- else:
- # Specific format
- if req_format not in url_map:
- self._downloader.trouble(u'ERROR: requested format not available')
- return
- video_url_list = [(req_format, url_map[req_format])] # Specific format
+ BEFORE = '[["allowFullScreen","true"],["allowScriptAccess","always"],["salign","tl"],["scale","noscale"],["wmode","opaque"]].forEach(function(param) {swf.addParam(param[0], param[1]);});\n'
+ AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});'
+ m = re.search(re.escape(BEFORE) + '(.*?)' + re.escape(AFTER), webpage)
+ if not m:
+ raise ExtractorError(u'Cannot parse data')
+ data = dict(json.loads(m.group(1)))
+ params_raw = compat_urllib_parse.unquote(data['params'])
+ params = json.loads(params_raw)
+ video_url = params['hd_src']
+ if not video_url:
+ video_url = params['sd_src']
+ if not video_url:
+ raise ExtractorError(u'Cannot find video URL')
+ video_duration = int(params['video_duration'])
+
+ m = re.search('<h2 class="uiHeaderTitle">([^<]+)</h2>', webpage)
+ if not m:
+ raise ExtractorError(u'Cannot find title in webpage')
+ video_title = unescapeHTML(m.group(1))
- results = []
- for format_param, video_real_url in video_url_list:
- # Extension
- video_extension = self._video_extensions.get(format_param, 'mp4')
+ info = {
+ 'id': video_id,
+ 'title': video_title,
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'duration': video_duration,
+ 'thumbnail': params['thumbnail_src'],
+ }
+ return [info]
- results.append({
- 'id': video_id.decode('utf-8'),
- 'url': video_real_url.decode('utf-8'),
- 'uploader': video_uploader.decode('utf-8'),
- 'upload_date': upload_date,
- 'title': video_title,
- 'ext': video_extension.decode('utf-8'),
- 'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
- 'thumbnail': video_thumbnail.decode('utf-8'),
- 'description': video_description.decode('utf-8'),
- })
- return results
class BlipTVIE(InfoExtractor):
"""Information extractor for blip.tv"""
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return
+ urlp = compat_urllib_parse_urlparse(url)
+ if urlp.path.startswith('/play/'):
+ request = compat_urllib_request.Request(url)
+ response = compat_urllib_request.urlopen(request)
+ redirecturl = response.geturl()
+ rurlp = compat_urllib_parse_urlparse(redirecturl)
+ file_id = compat_parse_qs(rurlp.fragment)['file'][0].rpartition('/')[2]
+ url = 'http://blip.tv/a/a-' + file_id
+ return self._real_extract(url)
+
+
if '?' in url:
cchar = '&'
else:
cchar = '?'
json_url = url + cchar + 'skin=json&version=2&no_wrap=1'
request = compat_urllib_request.Request(json_url)
+ request.add_header('User-Agent', 'iTunes/10.6.1')
self.report_extraction(mobj.group(1))
info = None
try:
'urlhandle': urlh
}
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % compat_str(err))
- return
+ raise ExtractorError(u'ERROR: unable to download video info webpage: %s' % compat_str(err))
if info is None: # Regular URL
try:
json_code_bytes = urlh.read()
'format': data['media']['mimeType'],
'thumbnail': data['thumbnailUrl'],
'description': data['description'],
- 'player_url': data['embedUrl']
+ 'player_url': data['embedUrl'],
+ 'user_agent': 'iTunes/10.6.1',
}
except (ValueError,KeyError) as err:
self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err))
return
- std_headers['User-Agent'] = 'iTunes/10.6.1'
return [info]
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[myvideo] %s: Downloading webpage' % video_id)
-
def report_extraction(self, video_id):
"""Report information extraction."""
self._downloader.to_screen(u'[myvideo] %s: Extracting information' % video_id)
video_id = mobj.group(1)
# Get video webpage
- request = compat_urllib_request.Request('http://www.myvideo.de/watch/%s' % video_id)
- try:
- self.report_download_webpage(video_id)
- webpage = compat_urllib_request.urlopen(request).read().decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
- return
+ webpage_url = 'http://www.myvideo.de/watch/%s' % video_id
+ webpage = self._download_webpage(webpage_url, video_id)
self.report_extraction(video_id)
- mobj = re.search(r'<link rel=\'image_src\' href=\'(http://is[0-9].myvideo\.de/de/movie[0-9]+/[a-f0-9]+)/thumbs/[^.]+\.jpg\' />',
+ mobj = re.search(r'<link rel=\'image_src\' href=\'(http://is[0-9].myvideo\.de/de/movie[0-9]+/[a-f0-9]+)/thumbs/.*?\.jpg\' />',
webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract media URL')
(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
|(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)))))
$"""
- IE_NAME = u'comedycentral'
_available_formats = ['3500', '2200', '1700', '1200', '750', '400']
'400': '384x216',
}
- def suitable(self, url):
+ @classmethod
+ def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE."""
- return re.match(self._VALID_URL, url, re.VERBOSE) is not None
+ return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
def report_extraction(self, episode_id):
self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id)
- def report_config_download(self, episode_id):
- self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration' % episode_id)
+ def report_config_download(self, episode_id, media_id):
+ self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration for %s' % (episode_id, media_id))
def report_index_download(self, episode_id):
self._downloader.to_screen(u'[comedycentral] %s: Downloading show index' % episode_id)
- def report_player_url(self, episode_id):
- self._downloader.to_screen(u'[comedycentral] %s: Determining player URL' % episode_id)
-
-
def _print_formats(self, formats):
print('Available formats:')
for x in formats:
try:
htmlHandle = compat_urllib_request.urlopen(req)
html = htmlHandle.read()
+ webpage = html.decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
return
return
epTitle = mobj.group('episode')
- mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', html)
+ mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage)
if len(mMovieParams) == 0:
# The Colbert Report embeds the information in a without
# a URL prefix; so extract the alternate reference
# and then add the URL prefix manually.
- altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', html)
+ altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', webpage)
if len(altMovieParams) == 0:
self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url)
return
else:
- mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
-
- playerUrl_raw = mMovieParams[0][0]
- self.report_player_url(epTitle)
- try:
- urlHandle = compat_urllib_request.urlopen(playerUrl_raw)
- playerUrl = urlHandle.geturl()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to find out player URL: ' + compat_str(err))
- return
+ mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
uri = mMovieParams[0][1]
indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + compat_urllib_parse.urlencode({'uri': uri})
idoc = xml.etree.ElementTree.fromstring(indexXml)
itemEls = idoc.findall('.//item')
- for itemEl in itemEls:
+ for partNum,itemEl in enumerate(itemEls):
mediaId = itemEl.findall('./guid')[0].text
shortMediaId = mediaId.split(':')[-1]
showId = mediaId.split(':')[-2].replace('.com', '')
configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' +
compat_urllib_parse.urlencode({'uri': mediaId}))
configReq = compat_urllib_request.Request(configUrl)
- self.report_config_download(epTitle)
+ self.report_config_download(epTitle, shortMediaId)
try:
configXml = compat_urllib_request.urlopen(configReq).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
return
# For now, just pick the highest bitrate
- format,video_url = turls[-1]
+ format,rtmp_video_url = turls[-1]
# Get the format arg from the arg stream
req_format = self._downloader.params.get('format', None)
# Select format if we can find one
for f,v in turls:
if f == req_format:
- format, video_url = f, v
+ format, rtmp_video_url = f, v
break
- # Patch to download from alternative CDN, which does not
- # break on current RTMPDump builds
- broken_cdn = "rtmpe://viacomccstrmfs.fplive.net/viacomccstrm/gsp.comedystor/"
- better_cdn = "rtmpe://cp10740.edgefcs.net/ondemand/mtvnorigin/gsp.comedystor/"
-
- if video_url.startswith(broken_cdn):
- video_url = video_url.replace(broken_cdn, better_cdn)
+ m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp.comedystor/.*)$', rtmp_video_url)
+ if not m:
+ raise ExtractorError(u'Cannot transform RTMP url')
+ base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/'
+ video_url = base + m.group('finalid')
- effTitle = showId + u'-' + epTitle
+ effTitle = showId + u'-' + epTitle + u' part ' + compat_str(partNum+1)
info = {
'id': shortMediaId,
'url': video_url,
'format': format,
'thumbnail': None,
'description': officialTitle,
- 'player_url': None #playerUrl
}
-
results.append(info)
return results
'uploader': showName,
'upload_date': None,
'title': showName,
- 'ext': 'flv',
+ 'ext': 'mp4',
'thumbnail': imgUrl,
'description': description,
'player_url': playerUrl,
return [info]
-
class CollegeHumorIE(InfoExtractor):
"""Information extractor for collegehumor.com"""
_VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
IE_NAME = u'xvideos'
- def report_webpage(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
-
def report_extraction(self, video_id):
"""Report information extraction."""
self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
return
video_id = mobj.group(1)
- self.report_webpage(video_id)
-
- request = compat_urllib_request.Request(r'http://www.xvideos.com/video' + video_id)
- try:
- webpage_bytes = compat_urllib_request.urlopen(request).read()
- webpage = webpage_bytes.decode('utf-8', 'replace')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
- return
+ webpage = self._download_webpage(url, video_id)
self.report_extraction(video_id)
stream_json_bytes = compat_urllib_request.urlopen(request).read()
stream_json = stream_json_bytes.decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
+ self._downloader.trouble(u'ERROR: unable to download stream definitions: %s' % compat_str(err))
return
streams = json.loads(stream_json)
class InfoQIE(InfoExtractor):
"""Information extractor for infoq.com"""
-
_VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$'
- IE_NAME = u'infoq'
-
- def report_webpage(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
def report_extraction(self, video_id):
"""Report information extraction."""
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return
- self.report_webpage(url)
-
- request = compat_urllib_request.Request(url)
- try:
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
- return
-
+ webpage = self._download_webpage(url, video_id=url)
self.report_extraction(url)
-
# Extract video URL
mobj = re.search(r"jsclassref='([^']*)'", webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract video url')
return
- video_url = 'rtmpe://video.infoq.com/cfx/st/' + compat_urllib_parse.unquote(mobj.group(1).decode('base64'))
-
+ real_id = compat_urllib_parse.unquote(base64.b64decode(mobj.group(1).encode('ascii')).decode('utf-8'))
+ video_url = 'rtmpe://video.infoq.com/cfx/st/' + real_id
# Extract title
mobj = re.search(r'contentTitle = "(.*?)";', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract video title')
return
- video_title = mobj.group(1).decode('utf-8')
+ video_title = mobj.group(1)
# Extract description
video_description = u'No description available.'
mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', webpage)
if mobj is not None:
- video_description = mobj.group(1).decode('utf-8')
+ video_description = mobj.group(1)
video_filename = video_url.split('/')[-1]
video_id, extension = video_filename.split('.')
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
+ raise ExtractorError(u'Invalid URL: %s' % url)
if mobj.group('course') and mobj.group('video'): # A specific video
course = mobj.group('course')
'upload_date': None,
}
- self.report_download_webpage(info['id'])
- try:
- coursepage = compat_urllib_request.urlopen(url).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download course info page: ' + compat_str(err))
- return
+ coursepage = self._download_webpage(url, info['id'],
+ note='Downloading course info page',
+ errnote='Unable to download course info page')
m = re.search('<h1>([^<]+)</h1>', coursepage)
if m:
assert entry['type'] == 'reference'
results += self.extract(entry['url'])
return results
-
else: # Root page
info = {
'id': 'Stanford OpenClassroom',
_VALID_URL = r'^(?P<proto>https?://)?(?:www\.)?mtv\.com/videos/[^/]+/(?P<videoid>[0-9]+)/[^/]+$'
IE_NAME = u'mtv'
- def report_webpage(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
-
def report_extraction(self, video_id):
"""Report information extraction."""
self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
if not mobj.group('proto'):
url = 'http://' + url
video_id = mobj.group('videoid')
- self.report_webpage(video_id)
- request = compat_urllib_request.Request(url)
- try:
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
- return
+ webpage = self._download_webpage(url, video_id)
mobj = re.search(r'<meta name="mtv_vt" content="([^"]+)"/>', webpage)
if mobj is None:
class YoukuIE(InfoExtractor):
-
_VALID_URL = r'(?:http://)?v\.youku\.com/v_show/id_(?P<ID>[A-Za-z0-9]+)\.html'
- IE_NAME = u'Youku'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
def report_download_webpage(self, file_id):
"""Report webpage download."""
- self._downloader.to_screen(u'[Youku] %s: Downloading webpage' % file_id)
+ self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, file_id))
def report_extraction(self, file_id):
"""Report information extraction."""
- self._downloader.to_screen(u'[Youku] %s: Extracting information' % file_id)
+ self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id))
def _gen_sid(self):
nowTime = int(time.time() * 1000)
class XNXXIE(InfoExtractor):
"""Information extractor for xnxx.com"""
- _VALID_URL = r'^http://video\.xnxx\.com/video([0-9]+)/(.*)'
+ _VALID_URL = r'^(?:https?://)?video\.xnxx\.com/video([0-9]+)/(.*)'
IE_NAME = u'xnxx'
VIDEO_URL_RE = r'flv_url=(.*?)&'
VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM'
_VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*)(\?.*)?$'
IE_NAME = u'nba'
- def report_extraction(self, video_id):
- self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
-
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
if video_id.endswith('/index.html'):
video_id = video_id[:-len('/index.html')]
- self.report_extraction(video_id)
- try:
- urlh = compat_urllib_request.urlopen(url)
- webpage_bytes = urlh.read()
- webpage = webpage_bytes.decode('utf-8', 'ignore')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % compat_str(err))
- return
+ webpage = self._download_webpage(url, video_id)
video_url = u'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4'
def _findProp(rexp, default=None):
return
response = json.loads(webpage)
+ if type(response) != list:
+ error_text = response.get('error', 'unknown error')
+ self._downloader.trouble(u'ERROR: Justin.tv API: %s' % error_text)
+ return
info = []
for clip in response:
video_url = clip['video_file_url']
if video_url:
video_extension = os.path.splitext(video_url)[1][1:]
- video_date = re.sub('-', '', clip['created_on'][:10])
+ video_date = re.sub('-', '', clip['start_time'][:10])
+ video_uploader_id = clip.get('user_id', clip.get('channel_id'))
+ video_id = clip['id']
+ video_title = clip.get('title', video_id)
info.append({
- 'id': clip['id'],
+ 'id': video_id,
'url': video_url,
- 'title': clip['title'],
- 'uploader': clip.get('user_id', clip.get('channel_id')),
+ 'title': video_title,
+ 'uploader': clip.get('channel_name', video_uploader_id),
+ 'uploader_id': video_uploader_id,
'upload_date': video_date,
'ext': video_extension,
})
paged = True
api += '/channel/archives/%s.json'
else:
- api += '/clip/show/%s.json'
+ api += '/broadcast/by_archive/%s.json'
api = api % (video_id,)
self.report_extraction(video_id)
class FunnyOrDieIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?funnyordie\.com/videos/(?P<id>[0-9a-f]+)/.*$'
- IE_NAME = u'FunnyOrDie'
-
- def report_extraction(self, video_id):
- self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
return
video_id = mobj.group('id')
- self.report_extraction(video_id)
- try:
- urlh = compat_urllib_request.urlopen(url)
- webpage_bytes = urlh.read()
- webpage = webpage_bytes.decode('utf-8', 'ignore')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
- return
+ webpage = self._download_webpage(url, video_id)
m = re.search(r'<video[^>]*>\s*<source[^>]*>\s*<source src="(?P<url>[^"]+)"', webpage, re.DOTALL)
if not m:
}
return [info]
-class TweetReelIE(InfoExtractor):
- _VALID_URL = r'^(?:https?://)?(?:www\.)?tweetreel\.com/[?](?P<id>[0-9a-z]+)$'
+class SteamIE(InfoExtractor):
+ _VALID_URL = r"""http://store.steampowered.com/
+ (?P<urltype>video|app)/ #If the page is only for videos or for a game
+ (?P<gameID>\d+)/?
+ (?P<videoID>\d*)(?P<extra>\??) #For urltype == video we sometimes get the videoID
+ """
- def report_extraction(self, video_id):
- self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+ @classmethod
+ def suitable(cls, url):
+ """Receives a URL and returns True if suitable for this IE."""
+ return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
+
+ def _real_extract(self, url):
+ m = re.match(self._VALID_URL, url, re.VERBOSE)
+ urlRE = r"'movie_(?P<videoID>\d+)': \{\s*FILENAME: \"(?P<videoURL>[\w:/\.\?=]+)\"(,\s*MOVIE_NAME: \"(?P<videoName>[\w:/\.\?=\+-]+)\")?\s*\},"
+ gameID = m.group('gameID')
+ videourl = 'http://store.steampowered.com/video/%s/' % gameID
+ webpage = self._download_webpage(videourl, gameID)
+ mweb = re.finditer(urlRE, webpage)
+ namesRE = r'<span class="title">(?P<videoName>.+?)</span>'
+ titles = re.finditer(namesRE, webpage)
+ thumbsRE = r'<img class="movie_thumb" src="(?P<thumbnail>.+?)">'
+ thumbs = re.finditer(thumbsRE, webpage)
+ videos = []
+ for vid,vtitle,thumb in zip(mweb,titles,thumbs):
+ video_id = vid.group('videoID')
+ title = vtitle.group('videoName')
+ video_url = vid.group('videoURL')
+ video_thumb = thumb.group('thumbnail')
+ if not video_url:
+ self._downloader.trouble(u'ERROR: Cannot find video url for %s' % video_id)
+ info = {
+ 'id':video_id,
+ 'url':video_url,
+ 'ext': 'flv',
+ 'title': unescapeHTML(title),
+ 'thumbnail': video_thumb
+ }
+ videos.append(info)
+ return videos
+
+class UstreamIE(InfoExtractor):
+ _VALID_URL = r'https?://www\.ustream\.tv/recorded/(?P<videoID>\d+)'
+ IE_NAME = u'ustream'
+
+ def _real_extract(self, url):
+ m = re.match(self._VALID_URL, url)
+ video_id = m.group('videoID')
+ video_url = u'http://tcdn.ustream.tv/video/%s' % video_id
+ webpage = self._download_webpage(url, video_id)
+ m = re.search(r'data-title="(?P<title>.+)"',webpage)
+ title = m.group('title')
+ m = re.search(r'<a class="state" data-content-type="channel" data-content-id="(?P<uploader>\d+)"',webpage)
+ uploader = m.group('uploader')
+ info = {
+ 'id':video_id,
+ 'url':video_url,
+ 'ext': 'flv',
+ 'title': title,
+ 'uploader': uploader
+ }
+ return [info]
+
+class WorldStarHipHopIE(InfoExtractor):
+ _VALID_URL = r'http://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)'
+ IE_NAME = u'WorldStarHipHop'
+
+ def _real_extract(self, url):
+ _src_url = r"""(http://hw-videos.*(?:mp4|flv))"""
+
+ webpage_src = compat_urllib_request.urlopen(str(url)).read()
+ webpage_src = webpage_src.decode('utf-8')
+
+ mobj = re.search(_src_url, webpage_src)
+
+ if mobj is not None:
+ video_url = mobj.group()
+ if 'mp4' in video_url:
+ ext = 'mp4'
+ else:
+ ext = 'flv'
+ else:
+ video_url = None
+ ext = None
+
+ _title = r"""<title>(.*)</title>"""
+
+ mobj = re.search(_title, webpage_src)
+
+ if mobj is not None:
+ title = mobj.group(1)
+ else:
+ title = 'World Start Hip Hop - %s' % time.ctime()
+
+ _thumbnail = r"""rel="image_src" href="(.*)" />"""
+ mobj = re.search(_thumbnail, webpage_src)
+
+ # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
+ if mobj is not None:
+ thumbnail = mobj.group(1)
+ else:
+ _title = r"""candytitles.*>(.*)</span>"""
+ mobj = re.search(_title, webpage_src)
+ if mobj is not None:
+ title = mobj.group(1)
+ thumbnail = None
+
+ m = re.match(self._VALID_URL, url)
+ video_id = m.group('id')
+
+ results = [{
+ 'id': video_id,
+ 'url' : video_url,
+ 'title' : title,
+ 'thumbnail' : thumbnail,
+ 'ext' : ext,
+ }]
+ return results
+
+class RBMARadioIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?rbmaradio\.com/shows/(?P<videoID>[^/]+)$'
+
+ def _real_extract(self, url):
+ m = re.match(self._VALID_URL, url)
+ video_id = m.group('videoID')
+
+ webpage = self._download_webpage(url, video_id)
+ m = re.search(r'<script>window.gon = {.*?};gon\.show=(.+?);</script>', webpage)
+ if not m:
+ raise ExtractorError(u'Cannot find metadata')
+ json_data = m.group(1)
+
+ try:
+ data = json.loads(json_data)
+ except ValueError as e:
+ raise ExtractorError(u'Invalid JSON: ' + str(e))
+
+ video_url = data['akamai_url'] + '&cbr=256'
+ url_parts = compat_urllib_parse_urlparse(video_url)
+ video_ext = url_parts.path.rpartition('.')[2]
+ info = {
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': video_ext,
+ 'title': data['title'],
+ 'description': data.get('teaser_text'),
+ 'location': data.get('country_of_origin'),
+ 'uploader': data.get('host', {}).get('name'),
+ 'uploader_id': data.get('host', {}).get('slug'),
+ 'thumbnail': data.get('image', {}).get('large_url_2x'),
+ 'duration': data.get('duration'),
+ }
+ return [info]
+
+
+class YouPornIE(InfoExtractor):
+ """Information extractor for youporn.com."""
+ _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+)'
+
+ def _print_formats(self, formats):
+ """Print all available formats"""
+ print(u'Available formats:')
+ print(u'ext\t\tformat')
+ print(u'---------------------------------')
+ for format in formats:
+ print(u'%s\t\t%s' % (format['ext'], format['format']))
+
+ def _specific(self, req_format, formats):
+ for x in formats:
+ if(x["format"]==req_format):
+ return x
+ return None
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return
- video_id = mobj.group('id')
- self.report_extraction(video_id)
- try:
- urlh = compat_urllib_request.urlopen(url)
- webpage_bytes = urlh.read()
- webpage = webpage_bytes.decode('utf-8', 'ignore')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
+ video_id = mobj.group('videoid')
+
+ req = compat_urllib_request.Request(url)
+ req.add_header('Cookie', 'age_verified=1')
+ webpage = self._download_webpage(req, video_id)
+
+ # Get the video title
+ result = re.search(r'<h1.*?>(?P<title>.*)</h1>', webpage)
+ if result is None:
+ raise ExtractorError(u'Unable to extract video title')
+ video_title = result.group('title').strip()
+
+ # Get the video date
+ result = re.search(r'Date:</label>(?P<date>.*) </li>', webpage)
+ if result is None:
+ self._downloader.report_warning(u'unable to extract video date')
+ upload_date = None
+ else:
+ upload_date = result.group('date').strip()
+
+ # Get the video uploader
+ result = re.search(r'Submitted:</label>(?P<uploader>.*)</li>', webpage)
+ if result is None:
+ self._downloader.report_warning(u'unable to extract uploader')
+ video_uploader = None
+ else:
+ video_uploader = result.group('uploader').strip()
+ video_uploader = clean_html( video_uploader )
+
+ # Get all of the formats available
+ DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
+ result = re.search(DOWNLOAD_LIST_RE, webpage)
+ if result is None:
+ raise ExtractorError(u'Unable to extract download list')
+ download_list_html = result.group('download_list').strip()
+
+ # Get all of the links from the page
+ LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">'
+ links = re.findall(LINK_RE, download_list_html)
+ if(len(links) == 0):
+ raise ExtractorError(u'ERROR: no known formats available for video')
+
+ self._downloader.to_screen(u'[youporn] Links found: %d' % len(links))
+
+ formats = []
+ for link in links:
+
+ # A link looks like this:
+ # http://cdn1.download.youporn.phncdn.com/201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4?nvb=20121113051249&nva=20121114051249&ir=1200&sr=1200&hash=014b882080310e95fb6a0
+ # A path looks like this:
+ # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4
+ video_url = unescapeHTML( link )
+ path = compat_urllib_parse_urlparse( video_url ).path
+ extension = os.path.splitext( path )[1][1:]
+ format = path.split('/')[4].split('_')[:2]
+ size = format[0]
+ bitrate = format[1]
+ format = "-".join( format )
+ title = u'%s-%s-%s' % (video_title, size, bitrate)
+
+ formats.append({
+ 'id': video_id,
+ 'url': video_url,
+ 'uploader': video_uploader,
+ 'upload_date': upload_date,
+ 'title': title,
+ 'ext': extension,
+ 'format': format,
+ 'thumbnail': None,
+ 'description': None,
+ 'player_url': None
+ })
+
+ if self._downloader.params.get('listformats', None):
+ self._print_formats(formats)
return
- m = re.search(r'<div id="left" status_id="([0-9]+)">', webpage)
- if not m:
- self._downloader.trouble(u'ERROR: Cannot find status ID')
- status_id = m.group(1)
+ req_format = self._downloader.params.get('format', None)
+ self._downloader.to_screen(u'[youporn] Format: %s' % req_format)
- m = re.search(r'<div class="tweet_text">(.*?)</div>', webpage, flags=re.DOTALL)
- if not m:
- self._downloader.trouble(u'WARNING: Cannot find description')
- desc = unescapeHTML(re.sub('<a.*?</a>', '', m.group(1))).strip()
+ if req_format is None or req_format == 'best':
+ return [formats[0]]
+ elif req_format == 'worst':
+ return [formats[-1]]
+ elif req_format in ('-1', 'all'):
+ return formats
+ else:
+ format = self._specific( req_format, formats )
+ if result is None:
+ self._downloader.trouble(u'ERROR: requested format not available')
+ return
+ return [format]
+
+
+
+class PornotubeIE(InfoExtractor):
+ """Information extractor for pornotube.com."""
+ _VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+
+ video_id = mobj.group('videoid')
+ video_title = mobj.group('title')
+
+ # Get webpage content
+ webpage = self._download_webpage(url, video_id)
+
+ # Get the video URL
+ VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",'
+ result = re.search(VIDEO_URL_RE, webpage)
+ if result is None:
+ self._downloader.trouble(u'ERROR: unable to extract video url')
+ return
+ video_url = compat_urllib_parse.unquote(result.group('url'))
+
+ #Get the uploaded date
+ VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by'
+ result = re.search(VIDEO_UPLOADED_RE, webpage)
+ if result is None:
+ self._downloader.trouble(u'ERROR: unable to extract video title')
+ return
+ upload_date = result.group('date')
+
+ info = {'id': video_id,
+ 'url': video_url,
+ 'uploader': None,
+ 'upload_date': upload_date,
+ 'title': video_title,
+ 'ext': 'flv',
+ 'format': 'flv'}
+
+ return [info]
+
+class YouJizzIE(InfoExtractor):
+ """Information extractor for youjizz.com."""
+ _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$'
- m = re.search(r'<div class="tweet_info">.*?from <a target="_blank" href="https?://twitter.com/(?P<uploader_id>.+?)">(?P<uploader>.+?)</a>', webpage, flags=re.DOTALL)
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+
+ video_id = mobj.group('videoid')
+
+ # Get webpage content
+ webpage = self._download_webpage(url, video_id)
+
+ # Get the video title
+ result = re.search(r'<title>(?P<title>.*)</title>', webpage)
+ if result is None:
+ raise ExtractorError(u'ERROR: unable to extract video title')
+ video_title = result.group('title').strip()
+
+ # Get the embed page
+ result = re.search(r'https?://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)', webpage)
+ if result is None:
+ raise ExtractorError(u'ERROR: unable to extract embed page')
+
+ embed_page_url = result.group(0).strip()
+ video_id = result.group('videoid')
+
+ webpage = self._download_webpage(embed_page_url, video_id)
+
+ # Get the video URL
+ result = re.search(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);', webpage)
+ if result is None:
+ raise ExtractorError(u'ERROR: unable to extract video url')
+ video_url = result.group('source')
+
+ info = {'id': video_id,
+ 'url': video_url,
+ 'title': video_title,
+ 'ext': 'flv',
+ 'format': 'flv',
+ 'player_url': embed_page_url}
+
+ return [info]
+
+class EightTracksIE(InfoExtractor):
+ IE_NAME = '8tracks'
+ _VALID_URL = r'https?://8tracks.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ raise ExtractorError(u'Invalid URL: %s' % url)
+ playlist_id = mobj.group('id')
+
+ webpage = self._download_webpage(url, playlist_id)
+
+ m = re.search(r"PAGE.mix = (.*?);\n", webpage, flags=re.DOTALL)
if not m:
- self._downloader.trouble(u'ERROR: Cannot find uploader')
+ raise ExtractorError(u'Cannot find trax information')
+ json_like = m.group(1)
+ data = json.loads(json_like)
+
+ session = str(random.randint(0, 1000000000))
+ mix_id = data['id']
+ track_count = data['tracks_count']
+ first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id)
+ next_url = first_url
+ res = []
+ for i in itertools.count():
+ api_json = self._download_webpage(next_url, playlist_id,
+ note=u'Downloading song information %s/%s' % (str(i+1), track_count),
+ errnote=u'Failed to download song information')
+ api_data = json.loads(api_json)
+ track_data = api_data[u'set']['track']
+ info = {
+ 'id': track_data['id'],
+ 'url': track_data['track_file_stream_url'],
+ 'title': track_data['performer'] + u' - ' + track_data['name'],
+ 'raw_title': track_data['name'],
+ 'uploader_id': data['user']['login'],
+ 'ext': 'm4a',
+ }
+ res.append(info)
+ if api_data['set']['at_last_track']:
+ break
+ next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % (session, mix_id, track_data['id'])
+ return res
+
+class KeekIE(InfoExtractor):
+ _VALID_URL = r'http://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<videoID>\w+)'
+ IE_NAME = u'keek'
+
+ def _real_extract(self, url):
+ m = re.match(self._VALID_URL, url)
+ video_id = m.group('videoID')
+ video_url = u'http://cdn.keek.com/keek/video/%s' % video_id
+ thumbnail = u'http://cdn.keek.com/keek/thumbnail/%s/w100/h75' % video_id
+ webpage = self._download_webpage(url, video_id)
+ m = re.search(r'<meta property="og:title" content="(?P<title>.+)"', webpage)
+ title = unescapeHTML(m.group('title'))
+ m = re.search(r'<div class="bio-names-and-report">[\s\n]+<h4>(?P<uploader>\w+)</h4>', webpage)
uploader = unescapeHTML(m.group('uploader'))
- uploader_id = unescapeHTML(m.group('uploader_id'))
+ info = {
+ 'id':video_id,
+ 'url':video_url,
+ 'ext': 'mp4',
+ 'title': title,
+ 'thumbnail': thumbnail,
+ 'uploader': uploader
+ }
+ return [info]
- m = re.search(r'<span unixtime="([0-9]+)"', webpage)
- if not m:
- self._downloader.trouble(u'ERROR: Cannot find upload date')
- upload_date = datetime.datetime.fromtimestamp(int(m.group(1))).strftime('%Y%m%d')
+class TEDIE(InfoExtractor):
+ _VALID_URL=r'''http://www.ted.com/
+ (
+ ((?P<type_playlist>playlists)/(?P<playlist_id>\d+)) # We have a playlist
+ |
+ ((?P<type_talk>talks)) # We have a simple talk
+ )
+ /(?P<name>\w+) # Here goes the name and then ".html"
+ '''
+
+ @classmethod
+ def suitable(cls, url):
+ """Receives a URL and returns True if suitable for this IE."""
+ return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
+
+ def _real_extract(self, url):
+ m=re.match(self._VALID_URL, url, re.VERBOSE)
+ if m.group('type_talk'):
+ return [self._talk_info(url)]
+ else :
+ playlist_id=m.group('playlist_id')
+ name=m.group('name')
+ self._downloader.to_screen(u'[%s] Getting info of playlist %s: "%s"' % (self.IE_NAME,playlist_id,name))
+ return self._playlist_videos_info(url,name,playlist_id)
+
+ def _talk_video_link(self,mediaSlug):
+ '''Returns the video link for that mediaSlug'''
+ return 'http://download.ted.com/talks/%s.mp4' % mediaSlug
+
+ def _playlist_videos_info(self,url,name,playlist_id=0):
+ '''Returns the videos of the playlist'''
+ video_RE=r'''
+ <li\ id="talk_(\d+)"([.\s]*?)data-id="(?P<video_id>\d+)"
+ ([.\s]*?)data-playlist_item_id="(\d+)"
+ ([.\s]*?)data-mediaslug="(?P<mediaSlug>.+?)"
+ '''
+ video_name_RE=r'<p\ class="talk-title"><a href="(?P<talk_url>/talks/(.+).html)">(?P<fullname>.+?)</a></p>'
+ webpage=self._download_webpage(url, playlist_id, 'Downloading playlist webpage')
+ m_videos=re.finditer(video_RE,webpage,re.VERBOSE)
+ m_names=re.finditer(video_name_RE,webpage)
+ info=[]
+ for m_video, m_name in zip(m_videos,m_names):
+ video_id=m_video.group('video_id')
+ talk_url='http://www.ted.com%s' % m_name.group('talk_url')
+ info.append(self._talk_info(talk_url,video_id))
+ return info
+
+ def _talk_info(self, url, video_id=0):
+ """Return the video for the talk in the url"""
+ m=re.match(self._VALID_URL, url,re.VERBOSE)
+ videoName=m.group('name')
+ webpage=self._download_webpage(url, video_id, 'Downloading \"%s\" page' % videoName)
+ # If the url includes the language we get the title translated
+ title_RE=r'<h1><span id="altHeadline" >(?P<title>.*)</span></h1>'
+ title=re.search(title_RE, webpage).group('title')
+ info_RE=r'''<script\ type="text/javascript">var\ talkDetails\ =(.*?)
+ "id":(?P<videoID>[\d]+).*?
+ "mediaSlug":"(?P<mediaSlug>[\w\d]+?)"'''
+ thumb_RE=r'</span>[\s.]*</div>[\s.]*<img src="(?P<thumbnail>.*?)"'
+ thumb_match=re.search(thumb_RE,webpage)
+ info_match=re.search(info_RE,webpage,re.VERBOSE)
+ video_id=info_match.group('videoID')
+ mediaSlug=info_match.group('mediaSlug')
+ video_url=self._talk_video_link(mediaSlug)
+ info = {
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'title': title,
+ 'thumbnail': thumb_match.group('thumbnail')
+ }
+ return info
- title = desc
- video_url = 'http://files.tweetreel.com/video/' + status_id + '.mov'
+class MySpassIE(InfoExtractor):
+ _VALID_URL = r'http://www.myspass.de/.*'
+ def _real_extract(self, url):
+ META_DATA_URL_TEMPLATE = 'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=%s'
+
+ # video id is the last path element of the URL
+ # usually there is a trailing slash, so also try the second but last
+ url_path = compat_urllib_parse_urlparse(url).path
+ url_parent_path, video_id = os.path.split(url_path)
+ if not video_id:
+ _, video_id = os.path.split(url_parent_path)
+
+ # get metadata
+ metadata_url = META_DATA_URL_TEMPLATE % video_id
+ metadata_text = self._download_webpage(metadata_url, video_id)
+ metadata = xml.etree.ElementTree.fromstring(metadata_text.encode('utf-8'))
+
+ # extract values from metadata
+ url_flv_el = metadata.find('url_flv')
+ if url_flv_el is None:
+ self._downloader.trouble(u'ERROR: unable to extract download url')
+ return
+ video_url = url_flv_el.text
+ extension = os.path.splitext(video_url)[1][1:]
+ title_el = metadata.find('title')
+ if title_el is None:
+ self._downloader.trouble(u'ERROR: unable to extract title')
+ return
+ title = title_el.text
+ format_id_el = metadata.find('format_id')
+ if format_id_el is None:
+ format = ext
+ else:
+ format = format_id_el.text
+ description_el = metadata.find('description')
+ if description_el is not None:
+ description = description_el.text
+ else:
+ description = None
+ imagePreview_el = metadata.find('imagePreview')
+ if imagePreview_el is not None:
+ thumbnail = imagePreview_el.text
+ else:
+ thumbnail = None
info = {
'id': video_id,
'url': video_url,
- 'ext': 'mov',
'title': title,
- 'description': desc,
- 'uploader': uploader,
- 'uploader_id': uploader_id,
- 'internal_id': status_id,
- 'upload_date': upload_date
+ 'ext': extension,
+ 'format': format,
+ 'thumbnail': thumbnail,
+ 'description': description
}
return [info]
+
+def gen_extractors():
+ """ Return a list of an instance of every supported extractor.
+ The order does matter; the first extractor matched is the one handling the URL.
+ """
+ return [
+ YoutubePlaylistIE(),
+ YoutubeChannelIE(),
+ YoutubeUserIE(),
+ YoutubeSearchIE(),
+ YoutubeIE(),
+ MetacafeIE(),
+ DailymotionIE(),
+ GoogleSearchIE(),
+ PhotobucketIE(),
+ YahooIE(),
+ YahooSearchIE(),
+ DepositFilesIE(),
+ FacebookIE(),
+ BlipTVUserIE(),
+ BlipTVIE(),
+ VimeoIE(),
+ MyVideoIE(),
+ ComedyCentralIE(),
+ EscapistIE(),
+ CollegeHumorIE(),
+ XVideosIE(),
+ SoundcloudIE(),
+ InfoQIE(),
+ MixcloudIE(),
+ StanfordOpenClassroomIE(),
+ MTVIE(),
+ YoukuIE(),
+ XNXXIE(),
+ YouJizzIE(),
+ PornotubeIE(),
+ YouPornIE(),
+ GooglePlusIE(),
+ ArteTvIE(),
+ NBAIE(),
+ WorldStarHipHopIE(),
+ JustinTVIE(),
+ FunnyOrDieIE(),
+ SteamIE(),
+ UstreamIE(),
+ RBMARadioIE(),
+ EightTracksIE(),
+ KeekIE(),
+ TEDIE(),
+ MySpassIE(),
+ GenericIE()
+ ]
+
+
projects / youtube-dl / blobdiff