import urllib
from .utils import *
+from .extractor.common import InfoExtractor, SearchInfoExtractor
+from .extractor.ard import ARDIE
+from .extractor.arte import ArteTvIE
+from .extractor.dailymotion import DailymotionIE
+from .extractor.metacafe import MetacafeIE
+from .extractor.statigram import StatigramIE
+from .extractor.photobucket import PhotobucketIE
+from .extractor.vimeo import VimeoIE
+from .extractor.yahoo import YahooIE
+from .extractor.youtube import YoutubeIE, YoutubePlaylistIE, YoutubeUserIE, YoutubeChannelIE
+from .extractor.zdf import ZDFIE
-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.
- 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 subtitle 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)
-
- @classmethod
- def suitable(cls, url):
- """Receives a URL and returns True if suitable for this IE."""
- return re.match(cls._VALID_URL, url) is not None
-
- @classmethod
- def working(cls):
- """Getter method for _WORKING."""
- return cls._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]
-
- def _request_webpage(self, url_or_request, video_id, note=None, errnote=None):
- """ Returns the response handle """
- if note is None:
- self.report_download_webpage(video_id)
- elif note is not False:
- self.to_screen(u'%s: %s' % (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_handle(self, url_or_request, video_id, note=None, errnote=None):
- """ Returns a tuple (page content as string, URL handle) """
- urlh = self._request_webpage(url_or_request, video_id, note, errnote)
- content_type = urlh.headers.get('Content-Type', '')
- m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
- if m:
- encoding = m.group(1)
- else:
- encoding = 'utf-8'
- webpage_bytes = urlh.read()
- if self._downloader.params.get('dump_intermediate_pages', False):
- try:
- url = url_or_request.get_full_url()
- except AttributeError:
- url = url_or_request
- self.to_screen(u'Dumping request to ' + url)
- dump = base64.b64encode(webpage_bytes).decode('ascii')
- self._downloader.to_screen(dump)
- content = webpage_bytes.decode(encoding, 'replace')
- return (content, urlh)
-
- def _download_webpage(self, url_or_request, video_id, note=None, errnote=None):
- """ Returns the data of the page as a string """
- return self._download_webpage_handle(url_or_request, video_id, note, errnote)[0]
-
- def to_screen(self, msg):
- """Print msg to screen, prefixing it with '[ie_name]'"""
- self._downloader.to_screen(u'[%s] %s' % (self.IE_NAME, msg))
-
- def report_extraction(self, id_or_name):
- """Report information extraction."""
- self.to_screen(u'%s: Extracting information' % id_or_name)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self.to_screen(u'%s: Downloading webpage' % video_id)
-
- def report_age_confirmation(self):
- """Report attempt to confirm age."""
- self.to_screen(u'Confirming age')
-
- #Methods for following #608
- #They set the correct value of the '_type' key
- def video_result(self, video_info):
- """Returns a video"""
- video_info['_type'] = 'video'
- return video_info
- def url_result(self, url, ie=None):
- """Returns a url that points to a page that should be processed"""
- #TODO: ie should be the class used for getting the info
- video_info = {'_type': 'url',
- 'url': url,
- 'ie_key': ie}
- return video_info
- def playlist_result(self, entries, playlist_id=None, playlist_title=None):
- """Returns a playlist"""
- video_info = {'_type': 'playlist',
- 'entries': entries}
- if playlist_id:
- video_info['id'] = playlist_id
- if playlist_title:
- video_info['title'] = playlist_title
- return video_info
-
-class SearchInfoExtractor(InfoExtractor):
- """
- Base class for paged search queries extractors.
- They accept urls in the format _SEARCH_KEY(|all|[0-9]):{query}
- Instances should define _SEARCH_KEY and _MAX_RESULTS.
- """
-
- @classmethod
- def _make_valid_url(cls):
- return r'%s(?P<prefix>|[1-9][0-9]*|all):(?P<query>[\s\S]+)' % cls._SEARCH_KEY
-
- @classmethod
- def suitable(cls, url):
- return re.match(cls._make_valid_url(), url) is not None
-
- def _real_extract(self, query):
- mobj = re.match(self._make_valid_url(), query)
- if mobj is None:
- raise ExtractorError(u'Invalid search query "%s"' % query)
-
- prefix = mobj.group('prefix')
- query = mobj.group('query')
- if prefix == '':
- return self._get_n_results(query, 1)
- elif prefix == 'all':
- return self._get_n_results(query, self._MAX_RESULTS)
- else:
- n = int(prefix)
- if n <= 0:
- raise ExtractorError(u'invalid download number %s for query "%s"' % (n, query))
- elif n > self._MAX_RESULTS:
- self._downloader.report_warning(u'%s returns max %i results (you requested %i)' % (self._SEARCH_KEY, self._MAX_RESULTS, n))
- n = self._MAX_RESULTS
- return self._get_n_results(query, n)
-
- def _get_n_results(self, query, n):
- """Get a specified number of results for a query"""
- raise NotImplementedError("This method must be implemented by sublclasses")
-
-
-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
- (?: # 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'https://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
- _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'
- # 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'
-
- @classmethod
- def suitable(cls, url):
- """Receives a URL and returns True if suitable for this IE."""
- 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."""
- self.to_screen(u'Setting language')
-
- def report_login(self):
- """Report attempt to log in."""
- self.to_screen(u'Logging in')
-
- def report_video_webpage_download(self, video_id):
- """Report attempt to download video webpage."""
- self.to_screen(u'%s: Downloading video webpage' % video_id)
-
- def report_video_info_webpage_download(self, video_id):
- """Report attempt to download video info webpage."""
- self.to_screen(u'%s: Downloading video info webpage' % video_id)
-
- def report_video_subtitles_download(self, video_id):
- """Report attempt to download video info webpage."""
- self.to_screen(u'%s: Checking available subtitles' % video_id)
-
- def report_video_subtitles_request(self, video_id, sub_lang, format):
- """Report attempt to download video info webpage."""
- self.to_screen(u'%s: Downloading video subtitles for %s.%s' % (video_id, sub_lang, format))
-
- def report_video_subtitles_available(self, video_id, sub_lang_list):
- """Report available subtitles."""
- sub_lang = ",".join(list(sub_lang_list.keys()))
- self.to_screen(u'%s: Available subtitles for video: %s' % (video_id, sub_lang))
-
- def report_information_extraction(self, video_id):
- """Report attempt to extract video information."""
- self.to_screen(u'%s: Extracting video information' % video_id)
-
- def report_unavailable_format(self, video_id, format):
- """Report extracted video URL."""
- self.to_screen(u'%s: Format %s not available' % (video_id, format))
-
- def report_rtmp_download(self):
- """Indicate the download will use the RTMP protocol."""
- self.to_screen(u'RTMP download detected')
-
- def _get_available_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:
- sub_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'unable to download video subtitles: %s' % compat_str(err), None)
- sub_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', sub_list)
- sub_lang_list = dict((l[1], l[0]) for l in sub_lang_list)
- if not sub_lang_list:
- return (u'video doesn\'t have subtitles', None)
- return sub_lang_list
-
- def _list_available_subtitles(self, video_id):
- sub_lang_list = self._get_available_subtitles(video_id)
- self.report_video_subtitles_available(video_id, sub_lang_list)
-
- def _request_subtitle(self, sub_lang, sub_name, video_id, format):
- """
- Return tuple:
- (error_message, sub_lang, sub)
- """
- self.report_video_subtitles_request(video_id, sub_lang, format)
- params = compat_urllib_parse.urlencode({
- 'lang': sub_lang,
- 'name': sub_name,
- 'v': video_id,
- 'fmt': format,
- })
- url = 'http://www.youtube.com/api/timedtext?' + params
- try:
- sub = compat_urllib_request.urlopen(url).read().decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- return (u'unable to download video subtitles: %s' % compat_str(err), None, None)
- if not sub:
- return (u'Did not fetch video subtitles', None, None)
- return (None, sub_lang, sub)
-
- def _request_automatic_caption(self, video_id, webpage):
- """We need the webpage for getting the captions url, pass it as an
- argument to speed up the process."""
- sub_lang = self._downloader.params.get('subtitleslang')
- sub_format = self._downloader.params.get('subtitlesformat')
- self.to_screen(u'%s: Looking for automatic captions' % video_id)
- mobj = re.search(r';ytplayer.config = ({.*?});', webpage)
- err_msg = u'Couldn\'t find automatic captions for "%s"' % sub_lang
- if mobj is None:
- return [(err_msg, None, None)]
- player_config = json.loads(mobj.group(1))
- try:
- args = player_config[u'args']
- caption_url = args[u'ttsurl']
- timestamp = args[u'timestamp']
- params = compat_urllib_parse.urlencode({
- 'lang': 'en',
- 'tlang': sub_lang,
- 'fmt': sub_format,
- 'ts': timestamp,
- 'kind': 'asr',
- })
- subtitles_url = caption_url + '&' + params
- sub = self._download_webpage(subtitles_url, video_id, u'Downloading automatic captions')
- return [(None, sub_lang, sub)]
- except KeyError:
- return [(err_msg, None, None)]
-
- def _extract_subtitle(self, video_id):
- """
- Return a list with a tuple:
- [(error_message, sub_lang, sub)]
- """
- sub_lang_list = self._get_available_subtitles(video_id)
- sub_format = self._downloader.params.get('subtitlesformat')
- if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles
- return [(sub_lang_list[0], None, None)]
- if self._downloader.params.get('subtitleslang', False):
- sub_lang = self._downloader.params.get('subtitleslang')
- elif 'en' in sub_lang_list:
- sub_lang = 'en'
- else:
- sub_lang = list(sub_lang_list.keys())[0]
- if not sub_lang in sub_lang_list:
- return [(u'no closed captions found in the specified language "%s"' % sub_lang, None, None)]
-
- subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format)
- return [subtitle]
-
- def _extract_all_subtitles(self, video_id):
- sub_lang_list = self._get_available_subtitles(video_id)
- sub_format = self._downloader.params.get('subtitlesformat')
- if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles
- return [(sub_lang_list[0], None, None)]
- subtitles = []
- for sub_lang in sub_lang_list:
- subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format)
- subtitles.append(subtitle)
- return subtitles
-
- 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.report_warning(u'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.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_strs = {
- u'continue': u'https://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[^>]* 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.report_warning(u'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:
- raise ExtractorError(u'Unable to confirm age: %s' % compat_str(err))
-
- def _extract_id(self, url):
- mobj = re.match(self._VALID_URL, url, re.VERBOSE)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
- 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 = 'https://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 = 'https://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:
- raise ExtractorError(u'Unable to download video webpage: %s' % compat_str(err))
-
- 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 = ('https://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
- % (video_id, el_type))
- video_info_webpage = self._download_webpage(video_info_url, video_id,
- note=False,
- errnote='unable to download video info webpage')
- video_info = compat_parse_qs(video_info_webpage)
- if 'token' in video_info:
- break
- if 'token' not in video_info:
- if 'reason' in video_info:
- raise ExtractorError(u'YouTube said: %s' % video_info['reason'][0])
- else:
- raise ExtractorError(u'"token" parameter not in video info for unknown reason')
-
- # Check for "rental" videos
- if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
- raise ExtractorError(u'"rental" videos not supported')
-
- # Start extracting information
- self.report_information_extraction(video_id)
-
- # uploader
- if 'author' not in video_info:
- raise ExtractorError(u'Unable to extract uploader name')
- 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|channel)/([^"]+)">', video_webpage)
- if mobj is not None:
- video_uploader_id = mobj.group(1)
- else:
- self._downloader.report_warning(u'unable to extract uploader nickname')
-
- # title
- if 'title' not in video_info:
- raise ExtractorError(u'Unable to extract video title')
- video_title = compat_urllib_parse.unquote_plus(video_info['title'][0])
-
- # thumbnail image
- if 'thumbnail_url' not in video_info:
- self._downloader.report_warning(u'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())
- upload_date = unified_strdate(upload_date)
-
- # description
- video_description = get_element_by_id("eow-description", video_webpage)
- if video_description:
- video_description = clean_html(video_description)
- else:
- fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)
- if fd_mobj:
- video_description = unescapeHTML(fd_mobj.group(1))
- else:
- video_description = u''
-
- # subtitles
- video_subtitles = None
-
- if self._downloader.params.get('writesubtitles', False):
- video_subtitles = self._extract_subtitle(video_id)
- if video_subtitles:
- (sub_error, sub_lang, sub) = video_subtitles[0]
- if sub_error:
- # We try with the automatic captions
- video_subtitles = self._request_automatic_caption(video_id, video_webpage)
- (sub_error_auto, sub_lang, sub) = video_subtitles[0]
- if sub is not None:
- pass
- else:
- # We report the original error
- self._downloader.report_error(sub_error)
-
- if self._downloader.params.get('allsubtitles', False):
- video_subtitles = self._extract_all_subtitles(video_id)
- for video_subtitle in video_subtitles:
- (sub_error, sub_lang, sub) = video_subtitle
- if sub_error:
- self._downloader.report_error(sub_error)
-
- if self._downloader.params.get('listsubtitles', False):
- sub_lang_list = self._list_available_subtitles(video_id)
- return
-
- if 'length_seconds' not in video_info:
- self._downloader.report_warning(u'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_map = {}
- for url_data_str in video_info['url_encoded_fmt_stream_map'][0].split(','):
- url_data = compat_parse_qs(url_data_str)
- if 'itag' in url_data and 'url' in url_data:
- url = url_data['url'][0] + '&signature=' + url_data['sig'][0]
- if not 'ratebypass' in url: url += '&ratebypass=yes'
- url_map[url_data['itag'][0]] = url
-
- 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:
- raise ExtractorError(u'no known formats available for video')
- 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:
- raise ExtractorError(u'requested format not available')
- else:
- raise ExtractorError(u'no conn or url_encoded_fmt_stream_map information found in video info')
-
- 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 report_disclaimer(self):
- """Report disclaimer retrieval."""
- self.to_screen(u'Retrieving disclaimer')
-
- 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:
- raise ExtractorError(u'Unable to retrieve disclaimer: %s' % compat_str(err))
-
- # 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:
- raise ExtractorError(u'Unable to confirm age: %s' % compat_str(err))
-
- def _real_extract(self, url):
- # Extract id and simplified title from URL
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
-
- video_id = mobj.group(1)
-
- # Check if video comes from YouTube
- mobj2 = re.match(r'^yt-(.*)$', video_id)
- if mobj2 is not None:
- return [self.url_result('http://www.youtube.com/watch?v=%s' % mobj2.group(1), 'Youtube')]
-
- # Retrieve video webpage to extract further information
- webpage = self._download_webpage('http://www.metacafe.com/watch/%s/' % video_id, video_id)
-
- # 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:
- raise ExtractorError(u'Unable to extract media URL')
- vardict = compat_parse_qs(mobj.group(1))
- if 'mediaData' not in vardict:
- raise ExtractorError(u'Unable to extract media URL')
- mobj = re.search(r'"mediaURL":"(?P<mediaURL>http.*?)",(.*?)"key":"(?P<key>.*?)"', vardict['mediaData'][0])
- if mobj is None:
- raise ExtractorError(u'Unable to extract media URL')
- mediaURL = mobj.group('mediaURL').replace('\\/', '/')
- video_extension = mediaURL[-3:]
- video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key'))
-
- mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract title')
- video_title = mobj.group(1).decode('utf-8')
-
- mobj = re.search(r'submitter=(.*?);', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract uploader nickname')
- 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 _real_extract(self, url):
- # Extract id and simplified title from URL
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
-
- 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')
- webpage = self._download_webpage(request, video_id)
-
- # Extract URL, uploader and title from webpage
- self.report_extraction(video_id)
- mobj = re.search(r'\s*var flashvars = (.*)', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract media URL')
- 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.to_screen(u'Using %s' % key)
- break
- else:
- raise ExtractorError(u'Unable to extract video URL')
-
- mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars)
- if mobj is None:
- raise ExtractorError(u'Unable to extract video URL')
-
- 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:
- raise ExtractorError(u'Unable to extract title')
- 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.report_warning(u'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."""
-
- # TODO: the original _VALID_URL was:
- # r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
- # Check if it's necessary to keep the old extracion process
- _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*(([\?\&]current=)|_)(?P<id>.*)\.(?P<ext>(flv)|(mp4))'
- IE_NAME = u'photobucket'
-
- def _real_extract(self, url):
- # Extract id from URL
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
-
- video_id = mobj.group('id')
-
- video_extension = mobj.group('ext')
-
- # Retrieve video webpage to extract further information
- webpage = self._download_webpage(url, video_id)
-
- # Extract URL, uploader, and title from webpage
- self.report_extraction(video_id)
- # We try first by looking the javascript code:
- mobj = re.search(r'Pb\.Data\.Shared\.put\(Pb\.Data\.Shared\.MEDIA, (?P<json>.*?)\);', webpage)
- if mobj is not None:
- info = json.loads(mobj.group('json'))
- return [{
- 'id': video_id,
- 'url': info[u'downloadUrl'],
- 'uploader': info[u'username'],
- 'upload_date': datetime.date.fromtimestamp(info[u'creationDate']).strftime('%Y%m%d'),
- 'title': info[u'title'],
- 'ext': video_extension,
- 'thumbnail': info[u'thumbUrl'],
- }]
-
- # We try looking in other parts of the webpage
- mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract media URL')
- 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:
- raise ExtractorError(u'Unable to extract title')
- 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 screen.yahoo.com."""
- _VALID_URL = r'http://screen\.yahoo\.com/.*?-(?P<id>\d*?)\.html'
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
- video_id = mobj.group('id')
- webpage = self._download_webpage(url, video_id)
- m_id = re.search(r'YUI\.namespace\("Media"\)\.CONTENT_ID = "(?P<new_id>.+?)";', webpage)
-
- if m_id is None:
- # TODO: Check which url parameters are required
- info_url = 'http://cosmos.bcst.yahoo.com/rest/v2/pops;lmsoverride=1;outputformat=mrss;cb=974419660;id=%s;rd=news.yahoo.com;datacontext=mdb;lg=KCa2IihxG3qE60vQ7HtyUy' % video_id
- webpage = self._download_webpage(info_url, video_id, u'Downloading info webpage')
- info_re = r'''<title><!\[CDATA\[(?P<title>.*?)\]\]></title>.*
- <description><!\[CDATA\[(?P<description>.*?)\]\]></description>.*
- <media:pubStart><!\[CDATA\[(?P<date>.*?)\ .*\]\]></media:pubStart>.*
- <media:content\ medium="image"\ url="(?P<thumb>.*?)"\ name="LARGETHUMB"
- '''
- self.report_extraction(video_id)
- m_info = re.search(info_re, webpage, re.VERBOSE|re.DOTALL)
- if m_info is None:
- raise ExtractorError(u'Unable to extract video info')
- video_title = m_info.group('title')
- video_description = m_info.group('description')
- video_thumb = m_info.group('thumb')
- video_date = m_info.group('date')
- video_date = datetime.datetime.strptime(video_date, '%m/%d/%Y').strftime('%Y%m%d')
-
- # TODO: Find a way to get mp4 videos
- rest_url = 'http://cosmos.bcst.yahoo.com/rest/v2/pops;element=stream;outputformat=mrss;id=%s;lmsoverride=1;bw=375;dynamicstream=1;cb=83521105;tech=flv,mp4;rd=news.yahoo.com;datacontext=mdb;lg=KCa2IihxG3qE60vQ7HtyUy' % video_id
- webpage = self._download_webpage(rest_url, video_id, u'Downloading video url webpage')
- m_rest = re.search(r'<media:content url="(?P<url>.*?)" path="(?P<path>.*?)"', webpage)
- video_url = m_rest.group('url')
- video_path = m_rest.group('path')
- if m_rest is None:
- raise ExtractorError(u'Unable to extract video url')
-
- else: # We have to use a different method if another id is defined
- long_id = m_id.group('new_id')
- info_url = 'http://video.query.yahoo.com/v1/public/yql?q=SELECT%20*%20FROM%20yahoo.media.video.streams%20WHERE%20id%3D%22' + long_id + '%22%20AND%20format%3D%22mp4%2Cflv%22%20AND%20protocol%3D%22rtmp%2Chttp%22%20AND%20plrs%3D%2286Gj0vCaSzV_Iuf6hNylf2%22%20AND%20acctid%3D%22389%22%20AND%20plidl%3D%22%22%20AND%20pspid%3D%22792700001%22%20AND%20offnetwork%3D%22false%22%20AND%20site%3D%22ivy%22%20AND%20lang%3D%22en-US%22%20AND%20region%3D%22US%22%20AND%20override%3D%22none%22%3B&env=prod&format=json&callback=YUI.Env.JSONP.yui_3_8_1_1_1368368376830_335'
- webpage = self._download_webpage(info_url, video_id, u'Downloading info json')
- json_str = re.search(r'YUI.Env.JSONP.yui.*?\((.*?)\);', webpage).group(1)
- info = json.loads(json_str)
- res = info[u'query'][u'results'][u'mediaObj'][0]
- stream = res[u'streams'][0]
- video_path = stream[u'path']
- video_url = stream[u'host']
- meta = res[u'meta']
- video_title = meta[u'title']
- video_description = meta[u'description']
- video_thumb = meta[u'thumbnail']
- video_date = None # I can't find it
-
- info_dict = {
- 'id': video_id,
- 'url': video_url,
- 'play_path': video_path,
- 'title':video_title,
- 'description': video_description,
- 'thumbnail': video_thumb,
- 'upload_date': video_date,
- 'ext': 'flv',
- }
- return info_dict
-
-class VimeoIE(InfoExtractor):
- """Information extractor for vimeo.com."""
-
- # _VALID_URL matches Vimeo URLs
- _VALID_URL = r'(?P<proto>https?://)?(?:(?:www|player)\.)?vimeo(?P<pro>pro)?\.com/(?:(?:(?:groups|album)/[^/]+)|(?:.*?)/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)'
- IE_NAME = u'vimeo'
-
- def _real_extract(self, url, new_video=True):
- # Extract ID from URL
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
-
- video_id = mobj.group('id')
- if not mobj.group('proto'):
- url = 'https://' + url
- if mobj.group('direct_link') or mobj.group('pro'):
- url = 'https://vimeo.com/' + video_id
-
- # Retrieve video webpage to extract further information
- request = compat_urllib_request.Request(url, None, std_headers)
- webpage = self._download_webpage(request, video_id)
-
- # 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:
- if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
- raise ExtractorError(u'The author has restricted the access to this video, try with the "--referer" option')
- else:
- raise ExtractorError(u'Unable to extract info section')
-
- # 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] if config["video"]["owner"]["url"] else None
-
- # 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 = u''
-
- # 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.to_screen(u'%s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality))
- break
- else:
- raise ExtractorError(u'No known codec found')
-
- 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 fetch_webpage(self, url):
- 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:
- raise ExtractorError(u'Unable to retrieve video webpage: %s' % compat_str(err))
- except ValueError as err:
- raise ExtractorError(u'Invalid URL: %s' % url)
- 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:
- raise ExtractorError(u'Invalid URL: %s' % url)
-
- for (i, key, err) in matchTuples:
- if mobj.group(i) is None:
- raise ExtractorError(err)
- 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'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'could not extract video path: %s' % url),
- (2, 'player', u'could not extract video player: %s' % url),
- (3, 'url', u'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'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'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'could not extract video id: %s' % url),
- (2, 'title', u'could not extract video title: %s' % url),
- (3, 'date', u'could not extract video date: %s' % url),
- (4, 'url', u'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': unified_strdate(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):
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:
+ # Try to find twitter cards info
+ mobj = re.search(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)
+ if mobj is None:
+ # We look for Open Graph info:
+ # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
+ m_video_type = re.search(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
+ # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
+ if m_video_type is not None:
+ mobj = re.search(r'<meta.*?property="og:video".*?content="(.*?)"', webpage)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
# 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:
- raise ExtractorError(u'Unable to extract title')
- video_title = mobj.group(1)
+ video_title = self._html_search_regex(r'<title>(.*)</title>',
+ webpage, u'video title')
# video uploader is domain name
- mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
- if mobj is None:
- raise ExtractorError(u'Unable to extract title')
- video_uploader = mobj.group(1)
+ video_uploader = self._search_regex(r'(?:https?://)?([^/]*)/.*',
+ url, u'video uploader')
return [{
'id': video_id,
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 _get_n_results(self, query, n):
if (pagenum * 10 > n) or not re.search(self._MORE_PAGES_INDICATOR, webpage):
return res
-class YahooSearchIE(SearchInfoExtractor):
- """Information Extractor for Yahoo! Video search queries."""
-
- _MAX_RESULTS = 1000
- IE_NAME = u'screen.yahoo:search'
- _SEARCH_KEY = 'yvsearch'
-
- def _get_n_results(self, query, n):
- """Get a specified number of results for a query"""
-
- res = {
- '_type': 'playlist',
- 'id': query,
- 'entries': []
- }
- for pagenum in itertools.count(0):
- result_url = u'http://video.search.yahoo.com/search/?p=%s&fr=screen&o=js&gs=0&b=%d' % (compat_urllib_parse.quote_plus(query), pagenum * 30)
- webpage = self._download_webpage(result_url, query,
- note='Downloading results page '+str(pagenum+1))
- info = json.loads(webpage)
- m = info[u'm']
- results = info[u'results']
-
- for (i, r) in enumerate(results):
- if (pagenum * 30) +i >= n:
- break
- mobj = re.search(r'(?P<url>screen\.yahoo\.com/.*?-\d*?\.html)"', r)
- e = self.url_result('http://' + mobj.group('url'), 'Yahoo')
- res['entries'].append(e)
- if (pagenum * 30 +i >= n) or (m[u'last'] >= (m[u'total'] -1 )):
- break
-
- return res
-
-
-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)=
- | p/
- )
- ((?: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'
-
- @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):
- # Extract playlist id
- mobj = re.match(self._VALID_URL, url, re.VERBOSE)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
-
- # Download playlist videos from API
- playlist_id = mobj.group(1) or mobj.group(2)
- page_num = 1
- videos = []
-
- while True:
- url = self._TEMPLATE_URL % (playlist_id, self._MAX_RESULTS, self._MAX_RESULTS * (page_num - 1) + 1)
- page = self._download_webpage(url, playlist_id, u'Downloading page #%s' % page_num)
-
- try:
- response = json.loads(page)
- except ValueError as err:
- raise ExtractorError(u'Invalid JSON in API response: ' + compat_str(err))
-
- if 'feed' not in response:
- raise ExtractorError(u'Got a malformed response from YouTube API')
- playlist_title = response['feed']['title']['$t']
- if 'entry' not in response['feed']:
- # Number of videos is a multiple of self._MAX_RESULTS
- break
-
- 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)]
-
- url_results = [self.url_result(url, 'Youtube') for url in videos]
- return [self.playlist_result(url_results, playlist_id, playlist_title)]
-
-
-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 = 'yt-uix-load-more'
- _MORE_PAGES_URL = 'http://www.youtube.com/channel_ajax?action_load_more_videos=1&flow=list&paging=%s&view=0&sort=da&channel_id=%s'
- IE_NAME = u'youtube:channel'
-
- def extract_videos_from_page(self, page):
- ids_in_page = []
- for mobj in re.finditer(r'href="/watch\?v=([0-9A-Za-z_-]+)&?', page):
- if mobj.group(1) not in ids_in_page:
- ids_in_page.append(mobj.group(1))
- return ids_in_page
-
- def _real_extract(self, url):
- # Extract channel id
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
-
- # Download channel page
- channel_id = mobj.group(1)
- video_ids = []
- pagenum = 1
-
- url = self._TEMPLATE_URL % (channel_id, pagenum)
- page = self._download_webpage(url, channel_id,
- u'Downloading page #%s' % pagenum)
-
- # Extract video identifiers
- ids_in_page = self.extract_videos_from_page(page)
- video_ids.extend(ids_in_page)
-
- # Download any subsequent channel pages using the json-based channel_ajax query
- if self._MORE_PAGES_INDICATOR in page:
- while True:
- pagenum = pagenum + 1
-
- url = self._MORE_PAGES_URL % (pagenum, channel_id)
- page = self._download_webpage(url, channel_id,
- u'Downloading page #%s' % pagenum)
-
- page = json.loads(page)
-
- ids_in_page = self.extract_videos_from_page(page['content_html'])
- video_ids.extend(ids_in_page)
-
- if self._MORE_PAGES_INDICATOR not in page['load_more_widget_html']:
- break
-
- self._downloader.to_screen(u'[youtube] Channel %s: Found %i videos' % (channel_id, len(video_ids)))
-
- urls = ['http://www.youtube.com/watch?v=%s' % id for id in video_ids]
- url_entries = [self.url_result(url, 'Youtube') for url in urls]
- return [self.playlist_result(url_entries, channel_id)]
-
-
-class YoutubeUserIE(InfoExtractor):
- """Information Extractor for YouTube users."""
-
- _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
- _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
- _GDATA_PAGE_SIZE = 50
- _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d'
- _VIDEO_INDICATOR = r'/watch\?v=(.+?)[\<&]'
- IE_NAME = u'youtube:user'
-
- def _real_extract(self, url):
- # Extract username
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
-
- username = mobj.group(1)
-
- # Download video ids using YouTube Data API. Result size per
- # query is limited (currently to 50 videos) so we need to query
- # page by page until there are no video ids - it means we got
- # all of them.
-
- video_ids = []
- pagenum = 0
-
- while True:
- start_index = pagenum * self._GDATA_PAGE_SIZE + 1
-
- gdata_url = self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index)
- page = self._download_webpage(gdata_url, username,
- u'Downloading video ids from %d to %d' % (start_index, start_index + self._GDATA_PAGE_SIZE))
-
- # Extract video identifiers
- ids_in_page = []
-
- for mobj in re.finditer(self._VIDEO_INDICATOR, page):
- if mobj.group(1) not in ids_in_page:
- ids_in_page.append(mobj.group(1))
+class YahooSearchIE(SearchInfoExtractor):
+ """Information Extractor for Yahoo! Video search queries."""
- video_ids.extend(ids_in_page)
+ _MAX_RESULTS = 1000
+ IE_NAME = u'screen.yahoo:search'
+ _SEARCH_KEY = 'yvsearch'
- # A little optimization - if current page is not
- # "full", ie. does not contain PAGE_SIZE video ids then
- # we can assume that this page is the last one - there
- # are no more ids on further pages - no need to query
- # again.
+ def _get_n_results(self, query, n):
+ """Get a specified number of results for a query"""
- if len(ids_in_page) < self._GDATA_PAGE_SIZE:
- break
+ res = {
+ '_type': 'playlist',
+ 'id': query,
+ 'entries': []
+ }
+ for pagenum in itertools.count(0):
+ result_url = u'http://video.search.yahoo.com/search/?p=%s&fr=screen&o=js&gs=0&b=%d' % (compat_urllib_parse.quote_plus(query), pagenum * 30)
+ webpage = self._download_webpage(result_url, query,
+ note='Downloading results page '+str(pagenum+1))
+ info = json.loads(webpage)
+ m = info[u'm']
+ results = info[u'results']
- pagenum += 1
+ for (i, r) in enumerate(results):
+ if (pagenum * 30) +i >= n:
+ break
+ mobj = re.search(r'(?P<url>screen\.yahoo\.com/.*?-\d*?\.html)"', r)
+ e = self.url_result('http://' + mobj.group('url'), 'Yahoo')
+ res['entries'].append(e)
+ if (pagenum * 30 +i >= n) or (m[u'last'] >= (m[u'total'] -1 )):
+ break
- urls = ['http://www.youtube.com/watch?v=%s' % video_id for video_id in video_ids]
- url_results = [self.url_result(url, 'Youtube') for url in urls]
- return [self.playlist_result(url_results, playlist_title = username)]
+ return res
class BlipTVUserIE(InfoExtractor):
file_extension = os.path.splitext(file_url)[1][1:]
# Search for file title
- mobj = re.search(r'<b title="(.*?)">', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract title')
- file_title = mobj.group(1).decode('utf-8')
+ file_title = self._search_regex(r'<b title="(.*?)">', webpage, u'title')
return [{
'id': file_id.decode('utf-8'),
video_duration = int(video_data['video_duration'])
thumbnail = video_data['thumbnail_src']
- 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))
+ video_title = self._html_search_regex('<h2 class="uiHeaderTitle">([^<]+)</h2>',
+ webpage, u'title')
info = {
'id': video_id,
self.report_extraction(video_id)
video_url = mobj.group(1) + '.flv'
- mobj = re.search('<title>([^<]+)</title>', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract title')
- video_title = mobj.group(1)
+ video_title = self._html_search_regex('<title>([^<]+)</title>',
+ webpage, u'title')
- mobj = re.search('[.](.+?)$', video_url)
- if mobj is None:
- raise ExtractorError(u'Unable to extract extention')
- video_ext = mobj.group(1)
+ video_ext = self._search_regex('[.](.+?)$', video_url, u'extension')
return [{
'id': video_id,
# extracting infos
self.report_extraction(video_id)
+ video_url = None
mobj = re.search('connectionurl=\'(.*?)\'', dec_data)
- if mobj is None:
- raise ExtractorError(u'unable to extract rtmpurl')
- video_rtmpurl = compat_urllib_parse.unquote(mobj.group(1))
- if 'myvideo2flash' in video_rtmpurl:
- self._downloader.report_warning(u'forcing RTMPT ...')
- video_rtmpurl = video_rtmpurl.replace('rtmpe://', 'rtmpt://')
-
- # extract non rtmp videos
- if (video_rtmpurl is None) or (video_rtmpurl == ''):
+ if mobj:
+ video_url = compat_urllib_parse.unquote(mobj.group(1))
+ if 'myvideo2flash' in video_url:
+ self._downloader.report_warning(u'forcing RTMPT ...')
+ video_url = video_url.replace('rtmpe://', 'rtmpt://')
+
+ if not video_url:
+ # extract non rtmp videos
mobj = re.search('path=\'(http.*?)\' source=\'(.*?)\'', dec_data)
if mobj is None:
raise ExtractorError(u'unable to extract url')
- video_rtmpurl = compat_urllib_parse.unquote(mobj.group(1)) + compat_urllib_parse.unquote(mobj.group(2))
+ video_url = compat_urllib_parse.unquote(mobj.group(1)) + compat_urllib_parse.unquote(mobj.group(2))
- mobj = re.search('source=\'(.*?)\'', dec_data)
- if mobj is None:
- raise ExtractorError(u'unable to extract swfobj')
- video_file = compat_urllib_parse.unquote(mobj.group(1))
+ video_file = self._search_regex('source=\'(.*?)\'', dec_data, u'video file')
+ video_file = compat_urllib_parse.unquote(video_file)
if not video_file.endswith('f4m'):
ppath, prefix = video_file.split('.')
video_filepath + video_file
).replace('.f4m', '.m3u8')
- mobj = re.search('swfobject.embedSWF\(\'(.+?)\'', webpage)
- if mobj is None:
- raise ExtractorError(u'unable to extract swfobj')
- video_swfobj = compat_urllib_parse.unquote(mobj.group(1))
+ video_swfobj = self._search_regex('swfobject.embedSWF\(\'(.+?)\'', webpage, u'swfobj')
+ video_swfobj = compat_urllib_parse.unquote(video_swfobj)
- mobj = re.search("<h1(?: class='globalHd')?>(.*?)</h1>", webpage)
- if mobj is None:
- raise ExtractorError(u'unable to extract title')
- video_title = mobj.group(1)
+ video_title = self._html_search_regex("<h1(?: class='globalHd')?>(.*?)</h1>",
+ webpage, u'title')
return [{
'id': video_id,
- 'url': video_rtmpurl,
- 'tc_url': video_rtmpurl,
+ 'url': video_url,
+ 'tc_url': video_url,
'uploader': None,
'upload_date': None,
'title': video_title,
'player_url': video_swfobj,
}]
+
class ComedyCentralIE(InfoExtractor):
"""Information extractor for The Daily Show and Colbert Report """
showName = mobj.group('showname')
videoId = mobj.group('episode')
- self.report_extraction(showName)
- webPage = self._download_webpage(url, showName)
+ self.report_extraction(videoId)
+ webpage = self._download_webpage(url, videoId)
+
+ videoDesc = self._html_search_regex('<meta name="description" content="([^"]*)"',
+ webpage, u'description', fatal=False)
+
+ imgUrl = self._html_search_regex('<meta property="og:image" content="([^"]*)"',
+ webpage, u'thumbnail', fatal=False)
- descMatch = re.search('<meta name="description" content="([^"]*)"', webPage)
- description = unescapeHTML(descMatch.group(1))
- imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage)
- imgUrl = unescapeHTML(imgMatch.group(1))
- playerUrlMatch = re.search('<meta property="og:video" content="([^"]*)"', webPage)
- playerUrl = unescapeHTML(playerUrlMatch.group(1))
- configUrlMatch = re.search('config=(.*)$', playerUrl)
- configUrl = compat_urllib_parse.unquote(configUrlMatch.group(1))
+ playerUrl = self._html_search_regex('<meta property="og:video" content="([^"]*)"',
+ webpage, u'player url')
- configJSON = self._download_webpage(configUrl, showName,
+ title = self._html_search_regex('<meta name="title" content="([^"]*)"',
+ webpage, u'player url').split(' : ')[-1]
+
+ configUrl = self._search_regex('config=(.*)$', playerUrl, u'config url')
+ configUrl = compat_urllib_parse.unquote(configUrl)
+
+ configJSON = self._download_webpage(configUrl, videoId,
u'Downloading configuration',
u'unable to download configuration')
'url': videoUrl,
'uploader': showName,
'upload_date': None,
- 'title': showName,
+ 'title': title,
'ext': 'mp4',
'thumbnail': imgUrl,
- 'description': description,
+ 'description': videoDesc,
'player_url': playerUrl,
}
self.report_extraction(video_id)
-
# Extract video URL
- mobj = re.search(r'flv_url=(.+?)&', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract video url')
- video_url = compat_urllib_parse.unquote(mobj.group(1))
-
+ video_url = compat_urllib_parse.unquote(self._search_regex(r'flv_url=(.+?)&',
+ webpage, u'video URL'))
# Extract title
- mobj = re.search(r'<title>(.*?)\s+-\s+XVID', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract video title')
- video_title = mobj.group(1)
-
+ video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XVID',
+ webpage, u'title')
# Extract video thumbnail
- mobj = re.search(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/([a-fA-F0-9.]+jpg)', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract video thumbnail')
- video_thumbnail = mobj.group(0)
+ video_thumbnail = self._search_regex(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/([a-fA-F0-9.]+jpg)',
+ webpage, u'thumbnail', fatal=False)
info = {
'id': video_id,
video_url = 'rtmpe://video.infoq.com/cfx/st/' + real_id
# Extract title
- mobj = re.search(r'contentTitle = "(.*?)";', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract video title')
- video_title = mobj.group(1)
+ video_title = self._search_regex(r'contentTitle = "(.*?)";',
+ webpage, u'title')
# 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)
+ video_description = self._html_search_regex(r'<meta name="description" content="(.*)"(?:\s*/)?>',
+ webpage, u'description', fatal=False)
video_filename = video_url.split('/')[-1]
video_id, extension = video_filename.split('.')
note='Downloading course info page',
errnote='Unable to download course info page')
- m = re.search('<h1>([^<]+)</h1>', coursepage)
- if m:
- info['title'] = unescapeHTML(m.group(1))
- else:
- info['title'] = info['id']
+ info['title'] = self._html_search_regex('<h1>([^<]+)</h1>', coursepage, 'title', default=info['id'])
- m = re.search('<description>([^<]+)</description>', coursepage)
- if m:
- info['description'] = unescapeHTML(m.group(1))
+ info['description'] = self._html_search_regex('<description>([^<]+)</description>',
+ coursepage, u'description', fatal=False)
links = orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage))
info['list'] = [
webpage = self._download_webpage(url, video_id)
- mobj = re.search(r'<meta name="mtv_vt" content="([^"]+)"/>', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract song name')
- song_name = unescapeHTML(mobj.group(1).decode('iso-8859-1'))
- mobj = re.search(r'<meta name="mtv_an" content="([^"]+)"/>', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract performer')
- performer = unescapeHTML(mobj.group(1).decode('iso-8859-1'))
- video_title = performer + ' - ' + song_name
+ song_name = self._html_search_regex(r'<meta name="mtv_vt" content="([^"]+)"/>',
+ webpage, u'song name', fatal=False)
- mobj = re.search(r'<meta name="mtvn_uri" content="([^"]+)"/>', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to mtvn_uri')
- mtvn_uri = mobj.group(1)
+ video_title = self._html_search_regex(r'<meta name="mtv_an" content="([^"]+)"/>',
+ webpage, u'title')
- mobj = re.search(r'MTVN.Player.defaultPlaylistId = ([0-9]+);', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract content id')
- content_id = mobj.group(1)
+ mtvn_uri = self._html_search_regex(r'<meta name="mtvn_uri" content="([^"]+)"/>',
+ webpage, u'mtvn_uri', fatal=False)
+
+ content_id = self._search_regex(r'MTVN.Player.defaultPlaylistId = ([0-9]+);',
+ webpage, u'content id', fatal=False)
videogen_url = 'http://www.mtv.com/player/includes/mediaGen.jhtml?uri=' + mtvn_uri + '&id=' + content_id + '&vid=' + video_id + '&ref=www.mtvn.com&viewUri=' + mtvn_uri
self.report_extraction(video_id)
# Get webpage content
webpage = self._download_webpage(url, video_id)
- result = re.search(self.VIDEO_URL_RE, webpage)
- if result is None:
- raise ExtractorError(u'Unable to extract video url')
- video_url = compat_urllib_parse.unquote(result.group(1))
+ video_url = self._search_regex(self.VIDEO_URL_RE,
+ webpage, u'video URL')
+ video_url = compat_urllib_parse.unquote(video_url)
- result = re.search(self.VIDEO_TITLE_RE, webpage)
- if result is None:
- raise ExtractorError(u'Unable to extract video title')
- video_title = result.group(1)
+ video_title = self._html_search_regex(self.VIDEO_TITLE_RE,
+ webpage, u'title')
- result = re.search(self.VIDEO_THUMB_RE, webpage)
- if result is None:
- raise ExtractorError(u'Unable to extract video thumbnail')
- video_thumbnail = result.group(1)
+ video_thumbnail = self._search_regex(self.VIDEO_THUMB_RE,
+ webpage, u'thumbnail', fatal=False)
return [{
'id': video_id,
_VALID_URL = r'(?:https://)?plus\.google\.com/(?:[^/]+/)*?posts/(\w+)'
IE_NAME = u'plus.google'
- def report_extract_entry(self, url):
- """Report downloading extry"""
- self.to_screen(u'Downloading entry: %s' % url)
-
- def report_date(self, upload_date):
- """Report downloading extry"""
- self.to_screen(u'Entry date: %s' % upload_date)
-
- def report_uploader(self, uploader):
- """Report downloading extry"""
- self.to_screen(u'Uploader: %s' % uploader)
-
- def report_title(self, video_title):
- """Report downloading extry"""
- self.to_screen(u'Title: %s' % video_title)
-
- def report_extract_vid_page(self, video_page):
- """Report information extraction."""
- self.to_screen(u'Extracting video page: %s' % video_page)
-
def _real_extract(self, url):
# Extract id from URL
mobj = re.match(self._VALID_URL, url)
video_extension = 'flv'
# Step 1, Retrieve post webpage to extract further information
- self.report_extract_entry(post_url)
webpage = self._download_webpage(post_url, video_id, u'Downloading entry webpage')
+ self.report_extraction(video_id)
+
# Extract update date
- upload_date = None
- pattern = 'title="Timestamp">(.*?)</a>'
- mobj = re.search(pattern, webpage)
- if mobj:
- upload_date = mobj.group(1)
+ upload_date = self._html_search_regex('title="Timestamp">(.*?)</a>',
+ webpage, u'upload date', fatal=False)
+ if upload_date:
# Convert timestring to a format suitable for filename
upload_date = datetime.datetime.strptime(upload_date, "%Y-%m-%d")
upload_date = upload_date.strftime('%Y%m%d')
- self.report_date(upload_date)
# Extract uploader
- uploader = None
- pattern = r'rel\="author".*?>(.*?)</a>'
- mobj = re.search(pattern, webpage)
- if mobj:
- uploader = mobj.group(1)
- self.report_uploader(uploader)
+ uploader = self._html_search_regex(r'rel\="author".*?>(.*?)</a>',
+ webpage, u'uploader', fatal=False)
# Extract title
# Get the first line for title
- video_title = u'NA'
- pattern = r'<meta name\=\"Description\" content\=\"(.*?)[\n<"]'
- mobj = re.search(pattern, webpage)
- if mobj:
- video_title = mobj.group(1)
- self.report_title(video_title)
+ video_title = self._html_search_regex(r'<meta name\=\"Description\" content\=\"(.*?)[\n<"]',
+ webpage, 'title', default=u'NA')
# Step 2, Stimulate clicking the image box to launch video
- pattern = '"(https\://plus\.google\.com/photos/.*?)",,"image/jpeg","video"\]'
- mobj = re.search(pattern, webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract video page URL')
-
- video_page = mobj.group(1)
+ video_page = self._search_regex('"(https\://plus\.google\.com/photos/.*?)",,"image/jpeg","video"\]',
+ webpage, u'video page URL')
webpage = self._download_webpage(video_page, video_id, u'Downloading video page')
- self.report_extract_vid_page(video_page)
-
# Extract video links on video page
"""Extract video links of all sizes"""
}]
class NBAIE(InfoExtractor):
- _VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*)(\?.*)?$'
+ _VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*?)(?:/index\.html)?(?:\?.*)?$'
IE_NAME = u'nba'
def _real_extract(self, url):
raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group(1)
- if video_id.endswith('/index.html'):
- video_id = video_id[:-len('/index.html')]
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):
- m = re.search(rexp, webpage)
- if m:
- return unescapeHTML(m.group(1))
- else:
- return default
shortened_video_id = video_id.rpartition('/')[2]
- title = _findProp(r'<meta property="og:title" content="(.*?)"', shortened_video_id).replace('NBA.com: ', '')
+ title = self._html_search_regex(r'<meta property="og:title" content="(.*?)"',
+ webpage, 'title', default=shortened_video_id).replace('NBA.com: ', '')
+
+ # It isn't there in the HTML it returns to us
+ # uploader_date = self._html_search_regex(r'<b>Date:</b> (.*?)</div>', webpage, 'upload_date', fatal=False)
+
+ description = self._html_search_regex(r'<meta name="description" (?:content|value)="(.*?)" />', webpage, 'description', fatal=False)
+
info = {
'id': shortened_video_id,
'url': video_url,
'ext': 'mp4',
'title': title,
- 'uploader_date': _findProp(r'<b>Date:</b> (.*?)</div>'),
- 'description': _findProp(r'<div class="description">(.*?)</h1>'),
+ # 'uploader_date': uploader_date,
+ 'description': description,
}
return [info]
video_id = mobj.group('id')
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:
- raise ExtractorError(u'Unable to find video information')
- video_url = unescapeHTML(m.group('url'))
+ video_url = self._html_search_regex(r'<video[^>]*>\s*<source[^>]*>\s*<source src="(?P<url>[^"]+)"',
+ webpage, u'video URL', flags=re.DOTALL)
- m = re.search(r"<h1 class='player_page_h1'.*?>(?P<title>.*?)</h1>", webpage, flags=re.DOTALL)
- if not m:
- m = re.search(r'<title>(?P<title>[^<]+?)</title>', webpage)
- if not m:
- raise ExtractorError(u'Cannot find video title')
- title = clean_html(m.group('title'))
+ title = self._html_search_regex((r"<h1 class='player_page_h1'.*?>(?P<title>.*?)</h1>",
+ r'<title>(?P<title>[^<]+?)</title>'), webpage, 'title', flags=re.DOTALL)
- m = re.search(r'<meta property="og:description" content="(?P<desc>.*?)"', webpage)
- if m:
- desc = unescapeHTML(m.group('desc'))
- else:
- desc = None
+ video_description = self._html_search_regex(r'<meta property="og:description" content="(?P<desc>.*?)"',
+ webpage, u'description', fatal=False, flags=re.DOTALL)
info = {
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': title,
- 'description': desc,
+ 'description': video_description,
}
return [info]
(?P<gameID>\d+)/?
(?P<videoID>\d*)(?P<extra>\??) #For urltype == video we sometimes get the videoID
"""
+ _VIDEO_PAGE_TEMPLATE = 'http://store.steampowered.com/video/%s/'
+ _AGECHECK_TEMPLATE = 'http://store.steampowered.com/agecheck/video/%s/?snr=1_agecheck_agecheck__age-gate&ageDay=1&ageMonth=January&ageYear=1970'
@classmethod
def suitable(cls, url):
def _real_extract(self, url):
m = re.match(self._VALID_URL, url, re.VERBOSE)
gameID = m.group('gameID')
- videourl = 'http://store.steampowered.com/agecheck/video/%s/?snr=1_agecheck_agecheck__age-gate&ageDay=1&ageMonth=January&ageYear=1970' % gameID
- self.report_age_confirmation()
+
+ videourl = self._VIDEO_PAGE_TEMPLATE % gameID
webpage = self._download_webpage(videourl, gameID)
- game_title = re.search(r'<h2 class="pageheader">(?P<game_title>.*?)</h2>', webpage).group('game_title')
-
+
+ if re.search('<h2>Please enter your birth date to continue:</h2>', webpage) is not None:
+ videourl = self._AGECHECK_TEMPLATE % gameID
+ self.report_age_confirmation()
+ webpage = self._download_webpage(videourl, gameID)
+
+ self.report_extraction(gameID)
+ game_title = self._html_search_regex(r'<h2 class="pageheader">(.*?)</h2>',
+ webpage, 'game title')
+
urlRE = r"'movie_(?P<videoID>\d+)': \{\s*FILENAME: \"(?P<videoURL>[\w:/\.\?=]+)\"(,\s*MOVIE_NAME: \"(?P<videoName>[\w:/\.\?=\+-]+)\")?\s*\},"
mweb = re.finditer(urlRE, webpage)
namesRE = r'<span class="title">(?P<videoName>.+?)</span>'
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)
+
self.report_extraction(video_id)
- try:
- m = re.search(r'data-title="(?P<title>.+)"',webpage)
- title = m.group('title')
- m = re.search(r'data-content-type="channel".*?>(?P<uploader>.*?)</a>',
- webpage, re.DOTALL)
- uploader = unescapeHTML(m.group('uploader').strip())
- m = re.search(r'<link rel="image_src" href="(?P<thumb>.*?)"', webpage)
- thumb = m.group('thumb')
- except AttributeError:
- raise ExtractorError(u'Unable to extract info')
+
+ video_title = self._html_search_regex(r'data-title="(?P<title>.+)"',
+ webpage, u'title')
+
+ uploader = self._html_search_regex(r'data-content-type="channel".*?>(?P<uploader>.*?)</a>',
+ webpage, u'uploader', fatal=False, flags=re.DOTALL)
+
+ thumbnail = self._html_search_regex(r'<link rel="image_src" href="(?P<thumb>.*?)"',
+ webpage, u'thumbnail', fatal=False)
+
info = {
- 'id':video_id,
- 'url':video_url,
+ 'id': video_id,
+ 'url': video_url,
'ext': 'flv',
- 'title': title,
+ 'title': video_title,
'uploader': uploader,
- 'thumbnail': thumb,
- }
+ 'thumbnail': thumbnail,
+ }
return info
class WorldStarHipHopIE(InfoExtractor):
IE_NAME = u'WorldStarHipHop'
def _real_extract(self, url):
- _src_url = r'so\.addVariable\("file","(.*?)"\)'
-
m = re.match(self._VALID_URL, url)
video_id = m.group('id')
- webpage_src = self._download_webpage(url, video_id)
+ webpage_src = self._download_webpage(url, video_id)
- mobj = re.search(_src_url, webpage_src)
+ video_url = self._search_regex(r'so\.addVariable\("file","(.*?)"\)',
+ webpage_src, u'video URL')
- if mobj is not None:
- video_url = mobj.group(1)
- if 'mp4' in video_url:
- ext = 'mp4'
- else:
- ext = 'flv'
+ if 'mp4' in video_url:
+ ext = 'mp4'
else:
- raise ExtractorError(u'Cannot find video url for %s' % video_id)
+ ext = 'flv'
- mobj = re.search(r"<title>(.*)</title>", webpage_src)
+ video_title = self._html_search_regex(r"<title>(.*)</title>",
+ webpage_src, u'title')
- if mobj is None:
- raise ExtractorError(u'Cannot determine title')
- title = mobj.group(1)
-
- mobj = re.search(r'rel="image_src" href="(.*)" />', 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:
+ thumbnail = self._html_search_regex(r'rel="image_src" href="(.*)" />',
+ webpage_src, u'thumbnail', fatal=False)
+
+ if not thumbnail:
_title = r"""candytitles.*>(.*)</span>"""
mobj = re.search(_title, webpage_src)
if mobj is not None:
- title = mobj.group(1)
- thumbnail = None
+ video_title = mobj.group(1)
results = [{
'id': video_id,
'url' : video_url,
- 'title' : title,
+ 'title' : video_title,
'thumbnail' : thumbnail,
'ext' : ext,
}]
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)
+
+ json_data = self._search_regex(r'window\.gon.*?gon\.show=(.+?);$',
+ webpage, u'json data', flags=re.MULTILINE)
try:
data = json.loads(json_data)
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
-
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 = unified_strdate(result.group('date').strip())
+ # Get JSON parameters
+ json_params = self._search_regex(r'var currentVideo = new Video\((.*)\);', webpage, u'JSON parameters')
+ try:
+ params = json.loads(json_params)
+ except:
+ raise ExtractorError(u'Invalid JSON')
- # 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 )
+ self.report_extraction(video_id)
+ try:
+ video_title = params['title']
+ upload_date = unified_strdate(params['release_date_f'])
+ video_description = params['description']
+ video_uploader = params['submitted_by']
+ thumbnail = params['thumbnails'][0]['image']
+ except KeyError:
+ raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1])
# 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()
+ download_list_html = self._search_regex(DOWNLOAD_LIST_RE,
+ webpage, u'download list').strip()
# Get all of the links from the page
LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">'
size = format[0]
bitrate = format[1]
format = "-".join( format )
- title = u'%s-%s-%s' % (video_title, size, bitrate)
+ # 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,
+ 'title': video_title,
'ext': extension,
'format': format,
- 'thumbnail': None,
- 'description': None,
- 'player_url': None
+ 'thumbnail': thumbnail,
+ 'description': video_description
})
if self._downloader.params.get('listformats', None):
# 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:
- raise ExtractorError(u'Unable to extract video url')
- video_url = compat_urllib_parse.unquote(result.group('url'))
+ video_url = self._search_regex(VIDEO_URL_RE, webpage, u'video url')
+ video_url = compat_urllib_parse.unquote(video_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:
- raise ExtractorError(u'Unable to extract video title')
- upload_date = unified_strdate(result.group('date'))
+ upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, u'upload date', fatal=False)
+ if upload_date: upload_date = unified_strdate(upload_date)
info = {'id': video_id,
'url': video_url,
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()
+ video_title = self._html_search_regex(r'<title>(?P<title>.*)</title>',
+ webpage, u'title').strip()
# Get the embed page
result = re.search(r'https?://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)', webpage)
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')
+ video_url = self._search_regex(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);',
+ webpage, u'video URL')
info = {'id': video_id,
'url': video_url,
webpage = self._download_webpage(url, playlist_id)
- m = re.search(r"PAGE.mix = (.*?);\n", webpage, flags=re.DOTALL)
- if not m:
- raise ExtractorError(u'Cannot find trax information')
- json_like = m.group(1)
+ json_like = self._search_regex(r"PAGE.mix = (.*?);\n", webpage, u'trax information', flags=re.DOTALL)
data = json.loads(json_like)
session = str(random.randint(0, 1000000000))
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="user-name-and-bio">[\S\s]+?<h2>(?P<uploader>.+?)</h2>', webpage)
- uploader = clean_html(m.group('uploader'))
+
+ video_title = self._html_search_regex(r'<meta property="og:title" content="(?P<title>.*?)"',
+ webpage, u'title')
+
+ uploader = self._html_search_regex(r'<div class="user-name-and-bio">[\S\s]+?<h2>(?P<uploader>.+?)</h2>',
+ webpage, u'uploader', fatal=False)
+
info = {
'id': video_id,
'url': video_url,
'ext': 'mp4',
- 'title': title,
+ 'title': video_title,
'thumbnail': thumbnail,
'uploader': uploader
}
self.to_screen(u'Getting info of playlist %s: "%s"' % (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'''
m_videos=re.finditer(video_RE,webpage,re.VERBOSE)
m_names=re.finditer(video_name_RE,webpage)
- playlist_RE = r'div class="headline">(\s*?)<h1>(\s*?)<span>(?P<playlist_title>.*?)</span>'
- m_playlist = re.search(playlist_RE, webpage)
- playlist_title = m_playlist.group('playlist_title')
+ playlist_title = self._html_search_regex(r'div class="headline">\s*?<h1>\s*?<span>(.*?)</span>',
+ webpage, 'playlist title')
playlist_entries = []
for m_video, m_name in zip(m_videos,m_names):
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)
+ m = re.match(self._VALID_URL, url,re.VERBOSE)
+ video_name = m.group('name')
+ webpage = self._download_webpage(url, video_id, 'Downloading \"%s\" page' % video_name)
+ self.report_extraction(video_name)
# If the url includes the language we get the title translated
- title_RE=r'<span id="altHeadline" >(?P<title>.*)</span>'
- 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)
+ title = self._html_search_regex(r'<span id="altHeadline" >(?P<title>.*)</span>',
+ webpage, 'title')
+ json_data = self._search_regex(r'<script.*?>var talkDetails = ({.*?})</script>',
+ webpage, 'json data')
+ info = json.loads(json_data)
+ desc = self._html_search_regex(r'<div class="talk-intro">.*?<p.*?>(.*?)</p>',
+ webpage, 'description', flags = re.DOTALL)
+
+ thumbnail = self._search_regex(r'</span>[\s.]*</div>[\s.]*<img src="(.*?)"',
+ webpage, 'thumbnail')
info = {
- 'id': video_id,
- 'url': video_url,
+ 'id': info['id'],
+ 'url': info['htmlStreams'][-1]['file'],
'ext': 'mp4',
'title': title,
- 'thumbnail': thumb_match.group('thumbnail')
+ 'thumbnail': thumbnail,
+ 'description': desc,
}
return info
video_id = m.group('videoID')
webpage = self._download_webpage(url, video_id)
- m = re.search(r'<div class="module-title">(.*?)</div>', webpage)
- if not m:
- raise ExtractorError(u'Cannot find title')
- video_title = unescapeHTML(m.group(1))
+
+ video_title = self._html_search_regex(r'<div class="module-title">(.*?)</div>',
+ webpage, u'title')
xml_url = u'http://video2.spiegel.de/flash/' + video_id + u'.xml'
xml_code = self._download_webpage(xml_url, video_id,
webpage = self._download_webpage(url, video_id)
- m = re.search(r'file: "(.*?)",', webpage)
- if not m:
- raise ExtractorError(u'Unable to find video url')
- video_url = m.group(1)
+ video_url = self._search_regex(r'file: "(.*?)",',
+ webpage, u'video URL')
- m = re.search(r'<meta property="og:title" content="(?P<title>.*?)"', webpage)
- if not m:
- raise ExtractorError(u'Cannot find video title')
- title = unescapeHTML(m.group('title')).replace('LiveLeak.com -', '').strip()
+ video_title = self._html_search_regex(r'<meta property="og:title" content="(?P<title>.*?)"',
+ webpage, u'title').replace('LiveLeak.com -', '').strip()
- m = re.search(r'<meta property="og:description" content="(?P<desc>.*?)"', webpage)
- if m:
- desc = unescapeHTML(m.group('desc'))
- else:
- desc = None
+ video_description = self._html_search_regex(r'<meta property="og:description" content="(?P<desc>.*?)"',
+ webpage, u'description', fatal=False)
- m = re.search(r'By:.*?(\w+)</a>', webpage)
- if m:
- uploader = clean_html(m.group(1))
- else:
- uploader = None
+ video_uploader = self._html_search_regex(r'By:.*?(\w+)</a>',
+ webpage, u'uploader', fatal=False)
info = {
'id': video_id,
'url': video_url,
'ext': 'mp4',
- 'title': title,
- 'description': desc,
- 'uploader': uploader
+ 'title': video_title,
+ 'description': video_description,
+ 'uploader': video_uploader
}
return [info]
-class ARDIE(InfoExtractor):
- _VALID_URL = r'^(?:https?://)?(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[^/\?]+)(?:\?.*)?'
- _TITLE = r'<h1(?: class="boxTopHeadline")?>(?P<title>.*)</h1>'
- _MEDIA_STREAM = r'mediaCollection\.addMediaStream\((?P<media_type>\d+), (?P<quality>\d+), "(?P<rtmp_url>[^"]*)", "(?P<video_url>[^"]*)", "[^"]*"\)'
- def _real_extract(self, url):
- # determine video id from url
- m = re.match(self._VALID_URL, url)
-
- numid = re.search(r'documentId=([0-9]+)', url)
- if numid:
- video_id = numid.group(1)
- else:
- video_id = m.group('video_id')
-
- # determine title and media streams from webpage
- html = self._download_webpage(url, video_id)
- title = re.search(self._TITLE, html).group('title')
- streams = [m.groupdict() for m in re.finditer(self._MEDIA_STREAM, html)]
- if not streams:
- assert '"fsk"' in html
- raise ExtractorError(u'This video is only available after 8:00 pm')
-
- # choose default media type and highest quality for now
- stream = max([s for s in streams if int(s["media_type"]) == 0],
- key=lambda s: int(s["quality"]))
-
- # there's two possibilities: RTMP stream or HTTP download
- info = {'id': video_id, 'title': title, 'ext': 'mp4'}
- if stream['rtmp_url']:
- self.to_screen(u'RTMP download detected')
- assert stream['video_url'].startswith('mp4:')
- info["url"] = stream["rtmp_url"]
- info["play_path"] = stream['video_url']
- else:
- assert stream["video_url"].endswith('.mp4')
- info["url"] = stream["video_url"]
- return [info]
class TumblrIE(InfoExtractor):
_VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/((post)|(video))/(?P<id>\d*)/(.*?)'
re_video = r'src=\\x22(?P<video_url>http://%s\.tumblr\.com/video_file/%s/(.*?))\\x22 type=\\x22video/(?P<ext>.*?)\\x22' % (blog, video_id)
video = re.search(re_video, webpage)
if video is None:
- self.to_screen("No video found")
- return []
+ raise ExtractorError(u'Unable to extract video')
video_url = video.group('video_url')
ext = video.group('ext')
- re_thumb = r'posters(.*?)\[\\x22(?P<thumb>.*?)\\x22' # We pick the first poster
- thumb = re.search(re_thumb, webpage).group('thumb').replace('\\', '')
+ video_thumbnail = self._search_regex(r'posters(.*?)\[\\x22(?P<thumb>.*?)\\x22',
+ webpage, u'thumbnail', fatal=False) # We pick the first poster
+ if video_thumbnail: video_thumbnail = video_thumbnail.replace('\\', '')
# The only place where you can get a title, it's not complete,
# but searching in other places doesn't work for all videos
- re_title = r'<title>(?P<title>.*?)</title>'
- title = unescapeHTML(re.search(re_title, webpage, re.DOTALL).group('title'))
+ video_title = self._html_search_regex(r'<title>(?P<title>.*?)</title>',
+ webpage, u'title', flags=re.DOTALL)
return [{'id': video_id,
'url': video_url,
- 'title': title,
- 'thumbnail': thumb,
+ 'title': video_title,
+ 'thumbnail': video_thumbnail,
'ext': ext
}]
# We get the link to the free download page
m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage)
if m_download is None:
- raise ExtractorError(u'No free songs founded')
+ raise ExtractorError(u'No free songs found')
download_link = m_download.group(1)
id = re.search(r'var TralbumData = {(.*?)id: (?P<id>\d*?)$',
track_info = {'id':id,
'title' : info[u'title'],
- 'ext' : 'mp3',
- 'url' : final_url,
+ 'ext' : 'mp3',
+ 'url' : final_url,
'thumbnail' : info[u'thumb_url'],
- 'uploader' : info[u'artist']
+ 'uploader' : info[u'artist']
}
return [track_info]
video_id = mobj.group('id')
video_extension = 'mp4'
webpage = self._download_webpage(url, video_id)
+
self.report_extraction(video_id)
- mobj = re.search(r'<source src="'+'(.+)'+'" type="video/mp4">',webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract media URL')
+ video_url = self._html_search_regex(r'<source src="(.+?)" type="video/mp4">',
+ webpage, u'video URL')
- video_url = mobj.group(1)
- mobj = re.search('<h1 class="videoTitle slidePanelMovable">(.+)</h1>',webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract title')
- video_title = mobj.group(1)
+ video_title = self._html_search_regex('<h1 class="videoTitle slidePanelMovable">(.+?)</h1>',
+ webpage, u'title')
return [{
'id': video_id,
video_extension = 'mp4'
webpage = self._download_webpage(mrss_url, video_id)
- mobj = re.search(r'<media:player url="(?P<mp4url>http://mp4.ina.fr/[^"]+\.mp4)', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract media URL')
- video_url = mobj.group(1)
+ self.report_extraction(video_id)
- mobj = re.search(r'<title><!\[CDATA\[(?P<titre>.*?)]]></title>', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract title')
- video_title = mobj.group(1)
+ video_url = self._html_search_regex(r'<media:player url="(?P<mp4url>http://mp4.ina.fr/[^"]+\.mp4)',
+ webpage, u'video URL')
+
+ video_title = self._search_regex(r'<title><!\[CDATA\[(?P<titre>.*?)]]></title>',
+ webpage, u'title')
return [{
'id': video_id,
self.report_extraction(video_id)
- mobj = re.search(r'\'?file\'?: "(http://mobile-media\.howcast\.com/[0-9]+\.mp4)"', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract video URL')
- video_url = mobj.group(1)
+ video_url = self._search_regex(r'\'?file\'?: "(http://mobile-media\.howcast\.com/[0-9]+\.mp4)',
+ webpage, u'video URL')
- mobj = re.search(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') property=\'og:title\'', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract title')
- video_title = mobj.group(1) or mobj.group(2)
+ video_title = self._html_search_regex(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') property=\'og:title\'',
+ webpage, u'title')
- mobj = re.search(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') name=\'description\'', webpage)
- if mobj is None:
- self._downloader.report_warning(u'unable to extract description')
- video_description = None
- else:
- video_description = mobj.group(1) or mobj.group(2)
+ video_description = self._html_search_regex(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') name=\'description\'',
+ webpage, u'description', fatal=False)
- mobj = re.search(r'<meta content=\'(.+?)\' property=\'og:image\'', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract thumbnail')
- thumbnail = mobj.group(1)
+ thumbnail = self._html_search_regex(r'<meta content=\'(.+?)\' property=\'og:image\'',
+ webpage, u'thumbnail', fatal=False)
return [{
'id': video_id,
_VALID_URL = r'(?:https?://)?(?:www\.)?vine\.co/v/(?P<id>\w+)'
def _real_extract(self, url):
-
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
self.report_extraction(video_id)
- mobj = re.search(r'<meta property="twitter:player:stream" content="(.+?)"', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract video URL')
- video_url = mobj.group(1)
+ video_url = self._html_search_regex(r'<meta property="twitter:player:stream" content="(.+?)"',
+ webpage, u'video URL')
- mobj = re.search(r'<meta property="og:title" content="(.+?)"', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract title')
- video_title = mobj.group(1)
+ video_title = self._html_search_regex(r'<meta property="og:title" content="(.+?)"',
+ webpage, u'title')
- mobj = re.search(r'<meta property="og:image" content="(.+?)(\?.*?)?"', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract thumbnail')
- thumbnail = mobj.group(1)
+ thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.+?)(\?.*?)?"',
+ webpage, u'thumbnail', fatal=False)
- mobj = re.search(r'<div class="user">.*?<h2>(.+?)</h2>', webpage, re.DOTALL)
- if mobj is None:
- raise ExtractorError(u'Unable to extract uploader')
- uploader = mobj.group(1)
+ uploader = self._html_search_regex(r'<div class="user">.*?<h2>(.+?)</h2>',
+ webpage, u'uploader', fatal=False, flags=re.DOTALL)
return [{
'id': video_id,
webpage_url = 'http://www.flickr.com/photos/' + video_uploader_id + '/' + video_id
webpage = self._download_webpage(webpage_url, video_id)
- mobj = re.search(r"photo_secret: '(\w+)'", webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract video secret')
- secret = mobj.group(1)
+ secret = self._search_regex(r"photo_secret: '(\w+)'", webpage, u'secret')
first_url = 'https://secure.flickr.com/apps/video/video_mtl_xml.gne?v=x&photo_id=' + video_id + '&secret=' + secret + '&bitrate=700&target=_self'
first_xml = self._download_webpage(first_url, video_id, 'Downloading first data webpage')
- mobj = re.search(r'<Item id="id">(\d+-\d+)</Item>', first_xml)
- if mobj is None:
- raise ExtractorError(u'Unable to extract node_id')
- node_id = mobj.group(1)
+ node_id = self._html_search_regex(r'<Item id="id">(\d+-\d+)</Item>',
+ first_xml, u'node_id')
second_url = 'https://secure.flickr.com/video_playlist.gne?node_id=' + node_id + '&tech=flash&mode=playlist&bitrate=700&secret=' + secret + '&rd=video.yahoo.com&noad=1'
second_xml = self._download_webpage(second_url, video_id, 'Downloading second data webpage')
raise ExtractorError(u'Unable to extract video url')
video_url = mobj.group(1) + unescapeHTML(mobj.group(2))
- mobj = re.search(r'<meta property="og:title" content=(?:"([^"]+)"|\'([^\']+)\')', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract title')
- video_title = mobj.group(1) or mobj.group(2)
+ video_title = self._html_search_regex(r'<meta property="og:title" content=(?:"([^"]+)"|\'([^\']+)\')',
+ webpage, u'video title')
- mobj = re.search(r'<meta property="og:description" content=(?:"([^"]+)"|\'([^\']+)\')', webpage)
- if mobj is None:
- self._downloader.report_warning(u'unable to extract description')
- video_description = None
- else:
- video_description = mobj.group(1) or mobj.group(2)
+ video_description = self._html_search_regex(r'<meta property="og:description" content=(?:"([^"]+)"|\'([^\']+)\')',
+ webpage, u'description', fatal=False)
- mobj = re.search(r'<meta property="og:image" content=(?:"([^"]+)"|\'([^\']+)\')', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract thumbnail')
- thumbnail = mobj.group(1) or mobj.group(2)
+ thumbnail = self._html_search_regex(r'<meta property="og:image" content=(?:"([^"]+)"|\'([^\']+)\')',
+ webpage, u'thumbnail', fatal=False)
return [{
'id': video_id,
url_title = mobj.group('url_title')
webpage = self._download_webpage(url, url_title)
- mobj = re.search(r'<article class="video" data-id="(\d+?)"', webpage)
- video_id = mobj.group(1)
+ video_id = self._html_search_regex(r'<article class="video" data-id="(\d+?)"',
+ webpage, u'video id')
self.report_extraction(video_id)
- mobj = re.search(r'<meta property="og:title" content="(.+?)"', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract title')
- video_title = mobj.group(1)
+ video_title = self._html_search_regex(r'<meta property="og:title" content="(.+?)"',
+ webpage, u'title')
- mobj = re.search(r'<meta property="og:image" content="(.+?)"', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract thumbnail')
- thumbnail = mobj.group(1)
+ thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.+?)"',
+ webpage, u'thumbnail', fatal=False)
- mobj = re.search(r'<meta property="og:description" content="(.*?)"', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract description')
- description = mobj.group(1)
+ video_description = self._html_search_regex(r'<meta property="og:description" content="(.*?)"',
+ webpage, u'description', fatal=False)
data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
data = self._download_webpage(data_url, video_id, 'Downloading data webpage')
- mobj = re.search(r'<file type="high".*?>(.*?)</file>', data)
- if mobj is None:
- raise ExtractorError(u'Unable to extract video url')
- video_url = mobj.group(1)
+
+ video_url = self._html_search_regex(r'<file type="high".*?>(.*?)</file>',
+ data, u'video URL')
return [{
'id': video_id,
'ext': 'mp4',
'title': video_title,
'thumbnail': thumbnail,
- 'description': description,
+ 'description': video_description,
}]
-
+
class XHamsterIE(InfoExtractor):
"""Information Extractor for xHamster"""
_VALID_URL = r'(?:http://)?(?:www.)?xhamster\.com/movies/(?P<id>[0-9]+)/.*\.html'
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
- mrss_url='http://xhamster.com/movies/%s/.html' % video_id
+ mrss_url = 'http://xhamster.com/movies/%s/.html' % video_id
webpage = self._download_webpage(mrss_url, video_id)
+
mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)
if mobj is None:
raise ExtractorError(u'Unable to extract media URL')
video_url = mobj.group('server')+'/key='+mobj.group('file')
video_extension = video_url.split('.')[-1]
- mobj = re.search(r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract title')
- video_title = unescapeHTML(mobj.group('title'))
+ video_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>',
+ webpage, u'title')
- mobj = re.search(r'<span>Description: </span>(?P<description>[^<]+)', webpage)
- if mobj is None:
- video_description = u''
- else:
- video_description = unescapeHTML(mobj.group('description'))
+ # Can't see the description anywhere in the UI
+ # video_description = self._html_search_regex(r'<span>Description: </span>(?P<description>[^<]+)',
+ # webpage, u'description', fatal=False)
+ # if video_description: video_description = unescapeHTML(video_description)
mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract upload date')
- video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d')
-
- mobj = re.search(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^>]+)', webpage)
- if mobj is None:
- video_uploader_id = u'anonymous'
+ if mobj:
+ video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d')
else:
- video_uploader_id = mobj.group('uploader_id')
+ video_upload_date = None
+ self._downloader.report_warning(u'Unable to extract upload date')
- mobj = re.search(r'\'image\':\'(?P<thumbnail>[^\']+)\'', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract thumbnail URL')
- video_thumbnail = mobj.group('thumbnail')
+ video_uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
+ webpage, u'uploader id', default=u'anonymous')
+
+ video_thumbnail = self._search_regex(r'\'image\':\'(?P<thumbnail>[^\']+)\'',
+ webpage, u'thumbnail', fatal=False)
return [{
'id': video_id,
'url': video_url,
'ext': video_extension,
'title': video_title,
- 'description': video_description,
+ # 'description': video_description,
'upload_date': video_upload_date,
'uploader_id': video_uploader_id,
'thumbnail': video_thumbnail
cookie = urlh.headers.get('Set-Cookie', '')
self.report_extraction(track_id)
- mobj = re.search(r'<script type="application/json" id="displayList-data">(.*?)</script>', response, flags=re.MULTILINE|re.DOTALL)
- if mobj is None:
- raise ExtractorError(u'Unable to extrack tracks')
- html_tracks = mobj.group(1).strip()
+
+ html_tracks = self._html_search_regex(r'<script type="application/json" id="displayList-data">(.*?)</script>',
+ response, u'tracks', flags=re.MULTILINE|re.DOTALL).strip()
try:
track_list = json.loads(html_tracks)
track = track_list[u'tracks'][0]
video_id = mobj.group(1)
redirect_page, urlh = self._download_webpage_handle(url, video_id)
- redirect_url = urlh.geturl() + re.search(r'window\.location = \'(.*)\';', redirect_page).group(1)
+ new_location = self._search_regex(r'window\.location = \'(.*)\';', redirect_page, u'redirect location')
+ redirect_url = urlh.geturl() + new_location
webpage = self._download_webpage(redirect_url, video_id, u'Downloading redirect page')
- title = re.search(r'<title>(.*)</title>', webpage)
- title = (title.group(1)).split('/')[0].strip()
+ title = self._html_search_regex(r'<title>(.*)</title>',
+ webpage, u'title').split('/')[0].strip()
ext = "flv"
info_url = "http://vbox7.com/play/magare.do"
info_response = self._download_webpage(info_request, video_id, u'Downloading info webpage')
if info_response is None:
raise ExtractorError(u'Unable to extract the media url')
- final_url = (info_response.split('&')[0]).split('=')[1]
+ (final_url, thumbnail_url) = map(lambda x: x.split('=')[1], info_response.split('&'))
return [{
- 'id': video_id,
- 'url': final_url,
- 'ext': ext,
- 'title': title,
+ 'id': video_id,
+ 'url': final_url,
+ 'ext': ext,
+ 'title': title,
+ 'thumbnail': thumbnail_url,
}]
+class GametrailersIE(InfoExtractor):
+ _VALID_URL = r'http://www.gametrailers.com/(?P<type>videos|reviews|full-episodes)/(?P<id>.*?)/(?P<title>.*)'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ raise ExtractorError(u'Invalid URL: %s' % url)
+ video_id = mobj.group('id')
+ video_type = mobj.group('type')
+ webpage = self._download_webpage(url, video_id)
+ if video_type == 'full-episodes':
+ mgid_re = r'data-video="(?P<mgid>mgid:.*?)"'
+ else:
+ mgid_re = r'data-contentId=\'(?P<mgid>mgid:.*?)\''
+ mgid = self._search_regex(mgid_re, webpage, u'mgid')
+ data = compat_urllib_parse.urlencode({'uri': mgid, 'acceptMethods': 'fms'})
+
+ info_page = self._download_webpage('http://www.gametrailers.com/feeds/mrss?' + data,
+ video_id, u'Downloading video info')
+ links_webpage = self._download_webpage('http://www.gametrailers.com/feeds/mediagen/?' + data,
+ video_id, u'Downloading video urls info')
+
+ self.report_extraction(video_id)
+ info_re = r'''<title><!\[CDATA\[(?P<title>.*?)\]\]></title>.*
+ <description><!\[CDATA\[(?P<description>.*?)\]\]></description>.*
+ <image>.*
+ <url>(?P<thumb>.*?)</url>.*
+ </image>'''
+
+ m_info = re.search(info_re, info_page, re.VERBOSE|re.DOTALL)
+ if m_info is None:
+ raise ExtractorError(u'Unable to extract video info')
+ video_title = m_info.group('title')
+ video_description = m_info.group('description')
+ video_thumb = m_info.group('thumb')
+
+ m_urls = list(re.finditer(r'<src>(?P<url>.*)</src>', links_webpage))
+ if m_urls is None or len(m_urls) == 0:
+ raise ExtractError(u'Unable to extrat video url')
+ # They are sorted from worst to best quality
+ video_url = m_urls[-1].group('url')
+
+ return {'url': video_url,
+ 'id': video_id,
+ 'title': video_title,
+ # Videos are actually flv not mp4
+ 'ext': 'flv',
+ 'thumbnail': video_thumb,
+ 'description': video_description,
+ }
+
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.
SpiegelIE(),
LiveLeakIE(),
ARDIE(),
+ ZDFIE(),
TumblrIE(),
BandcampIE(),
RedTubeIE(),
XHamsterIE(),
HypemIE(),
Vbox7IE(),
+ GametrailersIE(),
+ StatigramIE(),
GenericIE()
]