from .extractor.ard import ARDIE
from .extractor.arte import ArteTvIE
from .extractor.bliptv import BlipTVIE, BlipTVUserIE
+from .extractor.comedycentral import ComedyCentralIE
+from .extractor.collegehumor import CollegeHumorIE
from .extractor.dailymotion import DailymotionIE
+from .extractor.depositfiles import DepositFilesIE
+from .extractor.escapist import EscapistIE
+from .extractor.facebook import FacebookIE
from .extractor.gametrailers import GametrailersIE
from .extractor.generic import GenericIE
+from .extractor.googleplus import GooglePlusIE
+from .extractor.googlesearch import GoogleSearchIE
+from .extractor.infoq import InfoQIE
from .extractor.metacafe import MetacafeIE
+from .extractor.mtv import MTVIE
from .extractor.myvideo import MyVideoIE
+from .extractor.nba import NBAIE
from .extractor.statigram import StatigramIE
from .extractor.photobucket import PhotobucketIE
+from .extractor.soundcloud import SoundcloudIE, SoundcloudSetIE
+from .extractor.stanfordoc import StanfordOpenClassroomIE
from .extractor.vimeo import VimeoIE
+from .extractor.xvideos import XVideosIE
from .extractor.yahoo import YahooIE, YahooSearchIE
from .extractor.youtube import YoutubeIE, YoutubePlaylistIE, YoutubeSearchIE, YoutubeUserIE, YoutubeChannelIE
from .extractor.zdf import ZDFIE
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-class DepositFilesIE(InfoExtractor):
- """Information extractor for depositfiles.com"""
-
- _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)'
-
- def _real_extract(self, url):
- file_id = url.split('/')[-1]
- # Rebuild url in english locale
- url = 'http://depositfiles.com/en/files/' + file_id
-
- # Retrieve file webpage with 'Free download' button pressed
- free_download_indication = { 'gateway_result' : '1' }
- request = compat_urllib_request.Request(url, compat_urllib_parse.urlencode(free_download_indication))
- try:
- self.report_download_webpage(file_id)
- 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 file webpage: %s' % compat_str(err))
-
- # Search for the real file URL
- mobj = re.search(r'<form action="(http://fileshare.+?)"', webpage)
- if (mobj is None) or (mobj.group(1) is None):
- # Try to figure out reason of the error.
- mobj = re.search(r'<strong>(Attention.*?)</strong>', webpage, re.DOTALL)
- if (mobj is not None) and (mobj.group(1) is not None):
- restriction_message = re.sub('\s+', ' ', mobj.group(1)).strip()
- raise ExtractorError(u'%s' % restriction_message)
- else:
- raise ExtractorError(u'Unable to extract download URL from: %s' % url)
-
- file_url = mobj.group(1)
- file_extension = os.path.splitext(file_url)[1][1:]
-
- # Search for file title
- file_title = self._search_regex(r'<b title="(.*?)">', webpage, u'title')
-
- return [{
- 'id': file_id.decode('utf-8'),
- 'url': file_url.decode('utf-8'),
- 'uploader': None,
- 'upload_date': None,
- 'title': file_title,
- 'ext': file_extension.decode('utf-8'),
- }]
-
-
-class FacebookIE(InfoExtractor):
- """Information Extractor for Facebook"""
-
- _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
- _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&'
- _NETRC_MACHINE = 'facebook'
- IE_NAME = u'facebook'
-
- def report_login(self):
- """Report attempt to log in."""
- self.to_screen(u'Logging in')
-
- def _real_initialize(self):
- if self._downloader is None:
- return
-
- useremail = 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:
- useremail = 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:
- useremail = 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
-
- if useremail is None:
- return
-
- # Log in
- login_form = {
- 'email': useremail,
- 'pass': password,
- 'login': 'Log+In'
- }
- request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form))
- try:
- self.report_login()
- login_results = compat_urllib_request.urlopen(request).read()
- if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None:
- self._downloader.report_warning(u'unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
- return
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_warning(u'unable to log in: %s' % compat_str(err))
- return
-
- 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')
-
- url = 'https://www.facebook.com/video/video.php?v=%s' % video_id
- webpage = self._download_webpage(url, video_id)
-
- BEFORE = '{swf.addParam(param[0], param[1]);});\n'
- AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});'
- m = re.search(re.escape(BEFORE) + '(.*?)' + re.escape(AFTER), webpage)
- if not m:
- raise ExtractorError(u'Cannot parse data')
- data = dict(json.loads(m.group(1)))
- params_raw = compat_urllib_parse.unquote(data['params'])
- params = json.loads(params_raw)
- video_data = params['video_data'][0]
- video_url = video_data.get('hd_src')
- if not video_url:
- video_url = video_data['sd_src']
- if not video_url:
- raise ExtractorError(u'Cannot find video URL')
- video_duration = int(video_data['video_duration'])
- thumbnail = video_data['thumbnail_src']
-
- video_title = self._html_search_regex('<h2 class="uiHeaderTitle">([^<]+)</h2>',
- webpage, u'title')
-
- info = {
- 'id': video_id,
- 'title': video_title,
- 'url': video_url,
- 'ext': 'mp4',
- 'duration': video_duration,
- 'thumbnail': thumbnail,
- }
- return [info]
-
-
-
-
-
-class ComedyCentralIE(InfoExtractor):
- """Information extractor for The Daily Show and Colbert Report """
-
- # urls can be abbreviations like :thedailyshow or :colbert
- # urls for episodes like:
- # or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day
- # or: http://www.colbertnation.com/the-colbert-report-videos/421667/november-29-2012/moon-shattering-news
- # or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524
- _VALID_URL = r"""^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport)
- |(https?://)?(www\.)?
- (?P<showname>thedailyshow|colbertnation)\.com/
- (full-episodes/(?P<episode>.*)|
- (?P<clip>
- (the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
- |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)))))
- $"""
-
- _available_formats = ['3500', '2200', '1700', '1200', '750', '400']
-
- _video_extensions = {
- '3500': 'mp4',
- '2200': 'mp4',
- '1700': 'mp4',
- '1200': 'mp4',
- '750': 'mp4',
- '400': 'mp4',
- }
- _video_dimensions = {
- '3500': '1280x720',
- '2200': '960x540',
- '1700': '768x432',
- '1200': '640x360',
- '750': '512x288',
- '400': '384x216',
- }
-
- @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 _print_formats(self, formats):
- print('Available formats:')
- for x in formats:
- print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'mp4'), self._video_dimensions.get(x, '???')))
-
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url, re.VERBOSE)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
-
- if mobj.group('shortname'):
- if mobj.group('shortname') in ('tds', 'thedailyshow'):
- url = u'http://www.thedailyshow.com/full-episodes/'
- else:
- url = u'http://www.colbertnation.com/full-episodes/'
- mobj = re.match(self._VALID_URL, url, re.VERBOSE)
- assert mobj is not None
-
- if mobj.group('clip'):
- if mobj.group('showname') == 'thedailyshow':
- epTitle = mobj.group('tdstitle')
- else:
- epTitle = mobj.group('cntitle')
- dlNewest = False
- else:
- dlNewest = not mobj.group('episode')
- if dlNewest:
- epTitle = mobj.group('showname')
- else:
- epTitle = mobj.group('episode')
-
- self.report_extraction(epTitle)
- webpage,htmlHandle = self._download_webpage_handle(url, epTitle)
- if dlNewest:
- url = htmlHandle.geturl()
- mobj = re.match(self._VALID_URL, url, re.VERBOSE)
- if mobj is None:
- raise ExtractorError(u'Invalid redirected URL: ' + url)
- if mobj.group('episode') == '':
- raise ExtractorError(u'Redirected URL is still not specific: ' + url)
- epTitle = mobj.group('episode')
-
- mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage)
-
- if len(mMovieParams) == 0:
- # The Colbert Report embeds the information in a without
- # a URL prefix; so extract the alternate reference
- # and then add the URL prefix manually.
-
- altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', webpage)
- if len(altMovieParams) == 0:
- raise ExtractorError(u'unable to find Flash URL in webpage ' + url)
- else:
- mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
-
- uri = mMovieParams[0][1]
- indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + compat_urllib_parse.urlencode({'uri': uri})
- indexXml = self._download_webpage(indexUrl, epTitle,
- u'Downloading show index',
- u'unable to download episode index')
-
- results = []
-
- idoc = xml.etree.ElementTree.fromstring(indexXml)
- itemEls = idoc.findall('.//item')
- for partNum,itemEl in enumerate(itemEls):
- mediaId = itemEl.findall('./guid')[0].text
- shortMediaId = mediaId.split(':')[-1]
- showId = mediaId.split(':')[-2].replace('.com', '')
- officialTitle = itemEl.findall('./title')[0].text
- officialDate = unified_strdate(itemEl.findall('./pubDate')[0].text)
-
- configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' +
- compat_urllib_parse.urlencode({'uri': mediaId}))
- configXml = self._download_webpage(configUrl, epTitle,
- u'Downloading configuration for %s' % shortMediaId)
-
- cdoc = xml.etree.ElementTree.fromstring(configXml)
- turls = []
- for rendition in cdoc.findall('.//rendition'):
- finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text)
- turls.append(finfo)
-
- if len(turls) == 0:
- self._downloader.report_error(u'unable to download ' + mediaId + ': No videos found')
- continue
-
- if self._downloader.params.get('listformats', None):
- self._print_formats([i[0] for i in turls])
- return
-
- # For now, just pick the highest bitrate
- format,rtmp_video_url = turls[-1]
-
- # Get the format arg from the arg stream
- req_format = self._downloader.params.get('format', None)
-
- # Select format if we can find one
- for f,v in turls:
- if f == req_format:
- format, rtmp_video_url = f, v
- break
-
- m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp.comedystor/.*)$', rtmp_video_url)
- if not m:
- raise ExtractorError(u'Cannot transform RTMP url')
- base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/'
- video_url = base + m.group('finalid')
-
- effTitle = showId + u'-' + epTitle + u' part ' + compat_str(partNum+1)
- info = {
- 'id': shortMediaId,
- 'url': video_url,
- 'uploader': showId,
- 'upload_date': officialDate,
- 'title': effTitle,
- 'ext': 'mp4',
- 'format': format,
- 'thumbnail': None,
- 'description': officialTitle,
- }
- results.append(info)
-
- return results
-
-
-class EscapistIE(InfoExtractor):
- """Information extractor for The Escapist """
-
- _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
- IE_NAME = u'escapist'
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
- showName = mobj.group('showname')
- videoId = mobj.group('episode')
-
- self.report_extraction(videoId)
- webpage = self._download_webpage(url, videoId)
-
- videoDesc = self._html_search_regex('<meta name="description" content="([^"]*)"',
- webpage, u'description', fatal=False)
-
- imgUrl = self._html_search_regex('<meta property="og:image" content="([^"]*)"',
- webpage, u'thumbnail', fatal=False)
-
- playerUrl = self._html_search_regex('<meta property="og:video" content="([^"]*)"',
- webpage, u'player url')
-
- title = self._html_search_regex('<meta name="title" content="([^"]*)"',
- webpage, u'player url').split(' : ')[-1]
-
- configUrl = self._search_regex('config=(.*)$', playerUrl, u'config url')
- configUrl = compat_urllib_parse.unquote(configUrl)
-
- configJSON = self._download_webpage(configUrl, videoId,
- u'Downloading configuration',
- u'unable to download configuration')
-
- # Technically, it's JavaScript, not JSON
- configJSON = configJSON.replace("'", '"')
-
- try:
- config = json.loads(configJSON)
- except (ValueError,) as err:
- raise ExtractorError(u'Invalid JSON in configuration file: ' + compat_str(err))
-
- playlist = config['playlist']
- videoUrl = playlist[1]['url']
-
- info = {
- 'id': videoId,
- 'url': videoUrl,
- 'uploader': showName,
- 'upload_date': None,
- 'title': title,
- 'ext': 'mp4',
- 'thumbnail': imgUrl,
- 'description': videoDesc,
- 'player_url': playerUrl,
- }
-
- return [info]
-
-class CollegeHumorIE(InfoExtractor):
- """Information extractor for collegehumor.com"""
-
- _WORKING = False
- _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/video/(?P<videoid>[0-9]+)/(?P<shorttitle>.*)$'
- IE_NAME = u'collegehumor'
-
- def report_manifest(self, video_id):
- """Report information extraction."""
- self.to_screen(u'%s: Downloading XML manifest' % video_id)
-
- 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('videoid')
-
- info = {
- 'id': video_id,
- 'uploader': None,
- 'upload_date': None,
- }
-
- self.report_extraction(video_id)
- xmlUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id
- try:
- metaXml = compat_urllib_request.urlopen(xmlUrl).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- raise ExtractorError(u'Unable to download video info XML: %s' % compat_str(err))
-
- mdoc = xml.etree.ElementTree.fromstring(metaXml)
- try:
- videoNode = mdoc.findall('./video')[0]
- info['description'] = videoNode.findall('./description')[0].text
- info['title'] = videoNode.findall('./caption')[0].text
- info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
- manifest_url = videoNode.findall('./file')[0].text
- except IndexError:
- raise ExtractorError(u'Invalid metadata XML file')
-
- manifest_url += '?hdcore=2.10.3'
- self.report_manifest(video_id)
- try:
- manifestXml = compat_urllib_request.urlopen(manifest_url).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- raise ExtractorError(u'Unable to download video info XML: %s' % compat_str(err))
-
- adoc = xml.etree.ElementTree.fromstring(manifestXml)
- try:
- media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0]
- node_id = media_node.attrib['url']
- video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text
- except IndexError as err:
- raise ExtractorError(u'Invalid manifest file')
-
- url_pr = compat_urllib_parse_urlparse(manifest_url)
- url = url_pr.scheme + '://' + url_pr.netloc + '/z' + video_id[:-2] + '/' + node_id + 'Seg1-Frag1'
-
- info['url'] = url
- info['ext'] = 'f4f'
- return [info]
-
-
-class XVideosIE(InfoExtractor):
- """Information extractor for xvideos.com"""
-
- _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
- IE_NAME = u'xvideos'
-
- 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(1)
-
- webpage = self._download_webpage(url, video_id)
-
- self.report_extraction(video_id)
-
- # Extract video URL
- video_url = compat_urllib_parse.unquote(self._search_regex(r'flv_url=(.+?)&',
- webpage, u'video URL'))
-
- # Extract title
- video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XVID',
- webpage, u'title')
-
- # Extract video thumbnail
- 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,
- 'url': video_url,
- 'uploader': None,
- 'upload_date': None,
- 'title': video_title,
- 'ext': 'flv',
- 'thumbnail': video_thumbnail,
- 'description': None,
- }
-
- return [info]
-
-
-class SoundcloudIE(InfoExtractor):
- """Information extractor for soundcloud.com
- To access the media, the uid of the song and a stream token
- must be extracted from the page source and the script must make
- a request to media.soundcloud.com/crossdomain.xml. Then
- the media can be grabbed by requesting from an url composed
- of the stream token and uid
- """
-
- _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)'
- IE_NAME = u'soundcloud'
-
- def report_resolve(self, video_id):
- """Report information extraction."""
- self.to_screen(u'%s: Resolving id' % video_id)
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
-
- # extract uploader (which is in the url)
- uploader = mobj.group(1)
- # extract simple title (uploader + slug of song title)
- slug_title = mobj.group(2)
- simple_title = uploader + u'-' + slug_title
- full_title = '%s/%s' % (uploader, slug_title)
-
- self.report_resolve(full_title)
-
- url = 'http://soundcloud.com/%s/%s' % (uploader, slug_title)
- resolv_url = 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
- info_json = self._download_webpage(resolv_url, full_title, u'Downloading info JSON')
-
- info = json.loads(info_json)
- video_id = info['id']
- self.report_extraction(full_title)
-
- streams_url = 'https://api.sndcdn.com/i1/tracks/' + str(video_id) + '/streams?client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
- stream_json = self._download_webpage(streams_url, full_title,
- u'Downloading stream definitions',
- u'unable to download stream definitions')
-
- streams = json.loads(stream_json)
- mediaURL = streams['http_mp3_128_url']
- upload_date = unified_strdate(info['created_at'])
-
- return [{
- 'id': info['id'],
- 'url': mediaURL,
- 'uploader': info['user']['username'],
- 'upload_date': upload_date,
- 'title': info['title'],
- 'ext': u'mp3',
- 'description': info['description'],
- }]
-
-class SoundcloudSetIE(InfoExtractor):
- """Information extractor for soundcloud.com sets
- To access the media, the uid of the song and a stream token
- must be extracted from the page source and the script must make
- a request to media.soundcloud.com/crossdomain.xml. Then
- the media can be grabbed by requesting from an url composed
- of the stream token and uid
- """
-
- _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)'
- IE_NAME = u'soundcloud:set'
-
- def report_resolve(self, video_id):
- """Report information extraction."""
- self.to_screen(u'%s: Resolving id' % video_id)
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
-
- # extract uploader (which is in the url)
- uploader = mobj.group(1)
- # extract simple title (uploader + slug of song title)
- slug_title = mobj.group(2)
- simple_title = uploader + u'-' + slug_title
- full_title = '%s/sets/%s' % (uploader, slug_title)
-
- self.report_resolve(full_title)
-
- url = 'http://soundcloud.com/%s/sets/%s' % (uploader, slug_title)
- resolv_url = 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
- info_json = self._download_webpage(resolv_url, full_title)
-
- videos = []
- info = json.loads(info_json)
- if 'errors' in info:
- for err in info['errors']:
- self._downloader.report_error(u'unable to download video webpage: %s' % compat_str(err['error_message']))
- return
-
- self.report_extraction(full_title)
- for track in info['tracks']:
- video_id = track['id']
-
- streams_url = 'https://api.sndcdn.com/i1/tracks/' + str(video_id) + '/streams?client_id=b45b1aa10f1ac2941910a7f0d10f8e28'
- stream_json = self._download_webpage(streams_url, video_id, u'Downloading track info JSON')
-
- self.report_extraction(video_id)
- streams = json.loads(stream_json)
- mediaURL = streams['http_mp3_128_url']
-
- videos.append({
- 'id': video_id,
- 'url': mediaURL,
- 'uploader': track['user']['username'],
- 'upload_date': unified_strdate(track['created_at']),
- 'title': track['title'],
- 'ext': u'mp3',
- 'description': track['description'],
- })
- return videos
-
-
-class InfoQIE(InfoExtractor):
- """Information extractor for infoq.com"""
- _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$'
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
-
- webpage = self._download_webpage(url, video_id=url)
- self.report_extraction(url)
-
- # Extract video URL
- mobj = re.search(r"jsclassref ?= ?'([^']*)'", webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract video url')
- real_id = compat_urllib_parse.unquote(base64.b64decode(mobj.group(1).encode('ascii')).decode('utf-8'))
- video_url = 'rtmpe://video.infoq.com/cfx/st/' + real_id
-
- # Extract title
- video_title = self._search_regex(r'contentTitle = "(.*?)";',
- webpage, u'title')
-
- # Extract description
- 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('.')
-
- info = {
- 'id': video_id,
- 'url': video_url,
- 'uploader': None,
- 'upload_date': None,
- 'title': video_title,
- 'ext': extension, # Extension is always(?) mp4, but seems to be flv
- 'thumbnail': None,
- 'description': video_description,
- }
-
- return [info]
-
class MixcloudIE(InfoExtractor):
"""Information extractor for www.mixcloud.com"""
'player_url': player_url.decode('utf-8'),
}]
-class StanfordOpenClassroomIE(InfoExtractor):
- """Information extractor for Stanford's Open ClassRoom"""
- _VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
- IE_NAME = u'stanfordoc'
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
-
- if mobj.group('course') and mobj.group('video'): # A specific video
- course = mobj.group('course')
- video = mobj.group('video')
- info = {
- 'id': course + '_' + video,
- 'uploader': None,
- 'upload_date': None,
- }
-
- self.report_extraction(info['id'])
- baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/'
- xmlUrl = baseUrl + video + '.xml'
- try:
- metaXml = compat_urllib_request.urlopen(xmlUrl).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- raise ExtractorError(u'Unable to download video info XML: %s' % compat_str(err))
- mdoc = xml.etree.ElementTree.fromstring(metaXml)
- try:
- info['title'] = mdoc.findall('./title')[0].text
- info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text
- except IndexError:
- raise ExtractorError(u'Invalid metadata XML file')
- info['ext'] = info['url'].rpartition('.')[2]
- return [info]
- elif mobj.group('course'): # A course page
- course = mobj.group('course')
- info = {
- 'id': course,
- 'type': 'playlist',
- 'uploader': None,
- 'upload_date': None,
- }
-
- coursepage = self._download_webpage(url, info['id'],
- note='Downloading course info page',
- errnote='Unable to download course info page')
-
- info['title'] = self._html_search_regex('<h1>([^<]+)</h1>', coursepage, 'title', default=info['id'])
-
- info['description'] = self._html_search_regex('<description>([^<]+)</description>',
- coursepage, u'description', fatal=False)
-
- links = orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage))
- info['list'] = [
- {
- 'type': 'reference',
- 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(vpage),
- }
- for vpage in links]
- results = []
- for entry in info['list']:
- assert entry['type'] == 'reference'
- results += self.extract(entry['url'])
- return results
- else: # Root page
- info = {
- 'id': 'Stanford OpenClassroom',
- 'type': 'playlist',
- 'uploader': None,
- 'upload_date': None,
- }
-
- self.report_download_webpage(info['id'])
- rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php'
- try:
- rootpage = compat_urllib_request.urlopen(rootURL).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- raise ExtractorError(u'Unable to download course info page: ' + compat_str(err))
-
- info['title'] = info['id']
-
- links = orderedSet(re.findall('<a href="(CoursePage.php\?[^"]+)">', rootpage))
- info['list'] = [
- {
- 'type': 'reference',
- 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(cpage),
- }
- for cpage in links]
-
- results = []
- for entry in info['list']:
- assert entry['type'] == 'reference'
- results += self.extract(entry['url'])
- return results
-
-class MTVIE(InfoExtractor):
- """Information extractor for MTV.com"""
-
- _VALID_URL = r'^(?P<proto>https?://)?(?:www\.)?mtv\.com/videos/[^/]+/(?P<videoid>[0-9]+)/[^/]+$'
- IE_NAME = u'mtv'
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
- if not mobj.group('proto'):
- url = 'http://' + url
- video_id = mobj.group('videoid')
-
- webpage = self._download_webpage(url, video_id)
-
- song_name = self._html_search_regex(r'<meta name="mtv_vt" content="([^"]+)"/>',
- webpage, u'song name', fatal=False)
-
- video_title = self._html_search_regex(r'<meta name="mtv_an" content="([^"]+)"/>',
- webpage, u'title')
-
- 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)
- request = compat_urllib_request.Request(videogen_url)
- try:
- metadataXml = 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 metadata: %s' % compat_str(err))
-
- mdoc = xml.etree.ElementTree.fromstring(metadataXml)
- renditions = mdoc.findall('.//rendition')
-
- # For now, always pick the highest quality.
- rendition = renditions[-1]
-
- try:
- _,_,ext = rendition.attrib['type'].partition('/')
- format = ext + '-' + rendition.attrib['width'] + 'x' + rendition.attrib['height'] + '_' + rendition.attrib['bitrate']
- video_url = rendition.find('./src').text
- except KeyError:
- raise ExtractorError('Invalid rendition field.')
-
- info = {
- 'id': video_id,
- 'url': video_url,
- 'uploader': performer,
- 'upload_date': None,
- 'title': video_title,
- 'ext': ext,
- 'format': format,
- }
-
- return [info]
class YoukuIE(InfoExtractor):
}]
-class GooglePlusIE(InfoExtractor):
- """Information extractor for plus.google.com."""
- _VALID_URL = r'(?:https://)?plus\.google\.com/(?:[^/]+/)*?posts/(\w+)'
- IE_NAME = u'plus.google'
-
- 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)
-
- post_url = mobj.group(0)
- video_id = mobj.group(1)
-
- video_extension = 'flv'
-
- # Step 1, Retrieve post webpage to extract further information
- webpage = self._download_webpage(post_url, video_id, u'Downloading entry webpage')
-
- self.report_extraction(video_id)
-
- # Extract update date
- 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')
-
- # Extract 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 = 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
- 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')
-
- # Extract video links on video page
- """Extract video links of all sizes"""
- pattern = '\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"'
- mobj = re.findall(pattern, webpage)
- if len(mobj) == 0:
- raise ExtractorError(u'Unable to extract video links')
-
- # Sort in resolution
- links = sorted(mobj)
-
- # Choose the lowest of the sort, i.e. highest resolution
- video_url = links[-1]
- # Only get the url. The resolution part in the tuple has no use anymore
- video_url = video_url[-1]
- # Treat escaped \u0026 style hex
- try:
- video_url = video_url.decode("unicode_escape")
- except AttributeError: # Python 3
- video_url = bytes(video_url, 'ascii').decode('unicode-escape')
-
-
- return [{
- 'id': video_id,
- 'url': video_url,
- 'uploader': uploader,
- 'upload_date': upload_date,
- 'title': video_title,
- 'ext': video_extension,
- }]
-
-class NBAIE(InfoExtractor):
- _VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*?)(?:/index\.html)?(?:\?.*)?$'
- IE_NAME = u'nba'
-
- 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(1)
-
- webpage = self._download_webpage(url, video_id)
-
- video_url = u'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4'
-
- shortened_video_id = video_id.rpartition('/')[2]
- 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': uploader_date,
- 'description': description,
- }
- return [info]
class JustinTVIE(InfoExtractor):
"""Information extractor for justin.tv and twitch.tv"""