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.funnyordie import FunnyOrDieIE
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.justintv import JustinTVIE
from .extractor.metacafe import MetacafeIE
+from .extractor.mixcloud import MixcloudIE
+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.rbmaradio import RBMARadioIE
+from .extractor.soundcloud import SoundcloudIE, SoundcloudSetIE
+from .extractor.stanfordoc import StanfordOpenClassroomIE
+from .extractor.steam import SteamIE
+from .extractor.ted import TEDIE
+from .extractor.ustream import UstreamIE
from .extractor.vimeo import VimeoIE
+from .extractor.worldstarhiphop import WorldStarHipHopIE
+from .extractor.xnxx import XNXXIE
+from .extractor.xvideos import XVideosIE
from .extractor.yahoo import YahooIE, YahooSearchIE
+from .extractor.youku import YoukuIE
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 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"""
-
- _WORKING = False # New API, but it seems good http://www.mixcloud.com/developers/documentation/
- _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)'
- IE_NAME = u'mixcloud'
-
- def report_download_json(self, file_id):
- """Report JSON download."""
- self.to_screen(u'Downloading json')
-
- def get_urls(self, jsonData, fmt, bitrate='best'):
- """Get urls from 'audio_formats' section in json"""
- file_url = None
- try:
- bitrate_list = jsonData[fmt]
- if bitrate is None or bitrate == 'best' or bitrate not in bitrate_list:
- bitrate = max(bitrate_list) # select highest
-
- url_list = jsonData[fmt][bitrate]
- except TypeError: # we have no bitrate info.
- url_list = jsonData[fmt]
- return url_list
-
- def check_urls(self, url_list):
- """Returns 1st active url from list"""
- for url in url_list:
- try:
- compat_urllib_request.urlopen(url)
- return url
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- url = None
-
- return None
-
- def _print_formats(self, formats):
- print('Available formats:')
- for fmt in formats.keys():
- for b in formats[fmt]:
- try:
- ext = formats[fmt][b][0]
- print('%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1]))
- except TypeError: # we have no bitrate info
- ext = formats[fmt][0]
- print('%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1]))
- break
-
- 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 & filename from url
- uploader = mobj.group(1).decode('utf-8')
- file_id = uploader + "-" + mobj.group(2).decode('utf-8')
-
- # construct API request
- file_url = 'http://www.mixcloud.com/api/1/cloudcast/' + '/'.join(url.split('/')[-3:-1]) + '.json'
- # retrieve .json file with links to files
- request = compat_urllib_request.Request(file_url)
- try:
- self.report_download_json(file_url)
- jsonData = 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: %s' % compat_str(err))
-
- # parse JSON
- json_data = json.loads(jsonData)
- player_url = json_data['player_swf_url']
- formats = dict(json_data['audio_formats'])
-
- req_format = self._downloader.params.get('format', None)
- bitrate = None
-
- if self._downloader.params.get('listformats', None):
- self._print_formats(formats)
- return
-
- if req_format is None or req_format == 'best':
- for format_param in formats.keys():
- url_list = self.get_urls(formats, format_param)
- # check urls
- file_url = self.check_urls(url_list)
- if file_url is not None:
- break # got it!
- else:
- if req_format not in formats:
- raise ExtractorError(u'Format is not available')
-
- url_list = self.get_urls(formats, req_format)
- file_url = self.check_urls(url_list)
- format_param = req_format
-
- return [{
- 'id': file_id.decode('utf-8'),
- 'url': file_url.decode('utf-8'),
- 'uploader': uploader.decode('utf-8'),
- 'upload_date': None,
- 'title': json_data['name'],
- 'ext': file_url.split('.')[-1].decode('utf-8'),
- 'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
- 'thumbnail': json_data['thumbnail_url'],
- 'description': json_data['description'],
- '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):
- _VALID_URL = r'(?:http://)?v\.youku\.com/v_show/id_(?P<ID>[A-Za-z0-9]+)\.html'
-
- def _gen_sid(self):
- nowTime = int(time.time() * 1000)
- random1 = random.randint(1000,1998)
- random2 = random.randint(1000,9999)
-
- return "%d%d%d" %(nowTime,random1,random2)
-
- def _get_file_ID_mix_string(self, seed):
- mixed = []
- source = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890")
- seed = float(seed)
- for i in range(len(source)):
- seed = (seed * 211 + 30031 ) % 65536
- index = math.floor(seed / 65536 * len(source) )
- mixed.append(source[int(index)])
- source.remove(source[int(index)])
- #return ''.join(mixed)
- return mixed
-
- def _get_file_id(self, fileId, seed):
- mixed = self._get_file_ID_mix_string(seed)
- ids = fileId.split('*')
- realId = []
- for ch in ids:
- if ch:
- realId.append(mixed[int(ch)])
- return ''.join(realId)
-
- 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')
-
- info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id
-
- jsondata = self._download_webpage(info_url, video_id)
-
- self.report_extraction(video_id)
- try:
- config = json.loads(jsondata)
-
- video_title = config['data'][0]['title']
- seed = config['data'][0]['seed']
-
- format = self._downloader.params.get('format', None)
- supported_format = list(config['data'][0]['streamfileids'].keys())
-
- if format is None or format == 'best':
- if 'hd2' in supported_format:
- format = 'hd2'
- else:
- format = 'flv'
- ext = u'flv'
- elif format == 'worst':
- format = 'mp4'
- ext = u'mp4'
- else:
- format = 'flv'
- ext = u'flv'
-
-
- fileid = config['data'][0]['streamfileids'][format]
- keys = [s['k'] for s in config['data'][0]['segs'][format]]
- except (UnicodeDecodeError, ValueError, KeyError):
- raise ExtractorError(u'Unable to extract info section')
-
- files_info=[]
- sid = self._gen_sid()
- fileid = self._get_file_id(fileid, seed)
-
- #column 8,9 of fileid represent the segment number
- #fileid[7:9] should be changed
- for index, key in enumerate(keys):
-
- temp_fileid = '%s%02X%s' % (fileid[0:8], index, fileid[10:])
- download_url = 'http://f.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key)
-
- info = {
- 'id': '%s_part%02d' % (video_id, index),
- 'url': download_url,
- 'uploader': None,
- 'upload_date': None,
- 'title': video_title,
- 'ext': ext,
- }
- files_info.append(info)
-
- return files_info
-
-
-class XNXXIE(InfoExtractor):
- """Information extractor for xnxx.com"""
-
- _VALID_URL = r'^(?:https?://)?video\.xnxx\.com/video([0-9]+)/(.*)'
- IE_NAME = u'xnxx'
- VIDEO_URL_RE = r'flv_url=(.*?)&'
- VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM'
- VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&'
-
- 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)
-
- # Get webpage content
- webpage = self._download_webpage(url, video_id)
-
- video_url = self._search_regex(self.VIDEO_URL_RE,
- webpage, u'video URL')
- video_url = compat_urllib_parse.unquote(video_url)
-
- video_title = self._html_search_regex(self.VIDEO_TITLE_RE,
- webpage, u'title')
-
- video_thumbnail = self._search_regex(self.VIDEO_THUMB_RE,
- webpage, u'thumbnail', fatal=False)
-
- return [{
- 'id': video_id,
- 'url': video_url,
- 'uploader': None,
- 'upload_date': None,
- 'title': video_title,
- 'ext': 'flv',
- 'thumbnail': video_thumbnail,
- 'description': None,
- }]
-
-
-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)?(?:\?.*)?$'
- IE_NAME = u'nba'
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
-
- video_id = mobj.group(1)
-
- webpage = self._download_webpage(url, video_id)
-
- video_url = u'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4'
-
- shortened_video_id = video_id.rpartition('/')[2]
- title = self._html_search_regex(r'<meta property="og:title" content="(.*?)"',
- webpage, 'title', default=shortened_video_id).replace('NBA.com: ', '')
-
- # It isn't there in the HTML it returns to us
- # uploader_date = self._html_search_regex(r'<b>Date:</b> (.*?)</div>', webpage, 'upload_date', fatal=False)
-
- description = self._html_search_regex(r'<meta name="description" (?:content|value)="(.*?)" />', webpage, 'description', fatal=False)
-
- info = {
- 'id': shortened_video_id,
- 'url': video_url,
- 'ext': 'mp4',
- 'title': title,
- # 'uploader_date': uploader_date,
- 'description': description,
- }
- return [info]
-
-class JustinTVIE(InfoExtractor):
- """Information extractor for justin.tv and twitch.tv"""
- # TODO: One broadcast may be split into multiple videos. The key
- # 'broadcast_id' is the same for all parts, and 'broadcast_part'
- # starts at 1 and increases. Can we treat all parts as one video?
-
- _VALID_URL = r"""(?x)^(?:http://)?(?:www\.)?(?:twitch|justin)\.tv/
- (?:
- (?P<channelid>[^/]+)|
- (?:(?:[^/]+)/b/(?P<videoid>[^/]+))|
- (?:(?:[^/]+)/c/(?P<chapterid>[^/]+))
- )
- /?(?:\#.*)?$
- """
- _JUSTIN_PAGE_LIMIT = 100
- IE_NAME = u'justin.tv'
-
- def report_download_page(self, channel, offset):
- """Report attempt to download a single page of videos."""
- self.to_screen(u'%s: Downloading video information from %d to %d' %
- (channel, offset, offset + self._JUSTIN_PAGE_LIMIT))
-
- # Return count of items, list of *valid* items
- def _parse_page(self, url, video_id):
- webpage = self._download_webpage(url, video_id,
- u'Downloading video info JSON',
- u'unable to download video info JSON')
-
- response = json.loads(webpage)
- if type(response) != list:
- error_text = response.get('error', 'unknown error')
- raise ExtractorError(u'Justin.tv API: %s' % error_text)
- info = []
- for clip in response:
- video_url = clip['video_file_url']
- if video_url:
- video_extension = os.path.splitext(video_url)[1][1:]
- video_date = re.sub('-', '', clip['start_time'][:10])
- video_uploader_id = clip.get('user_id', clip.get('channel_id'))
- video_id = clip['id']
- video_title = clip.get('title', video_id)
- info.append({
- 'id': video_id,
- 'url': video_url,
- 'title': video_title,
- 'uploader': clip.get('channel_name', video_uploader_id),
- 'uploader_id': video_uploader_id,
- 'upload_date': video_date,
- 'ext': video_extension,
- })
- return (len(response), info)
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- raise ExtractorError(u'invalid URL: %s' % url)
-
- api_base = 'http://api.justin.tv'
- paged = False
- if mobj.group('channelid'):
- paged = True
- video_id = mobj.group('channelid')
- api = api_base + '/channel/archives/%s.json' % video_id
- elif mobj.group('chapterid'):
- chapter_id = mobj.group('chapterid')
-
- webpage = self._download_webpage(url, chapter_id)
- m = re.search(r'PP\.archive_id = "([0-9]+)";', webpage)
- if not m:
- raise ExtractorError(u'Cannot find archive of a chapter')
- archive_id = m.group(1)
-
- api = api_base + '/broadcast/by_chapter/%s.xml' % chapter_id
- chapter_info_xml = self._download_webpage(api, chapter_id,
- note=u'Downloading chapter information',
- errnote=u'Chapter information download failed')
- doc = xml.etree.ElementTree.fromstring(chapter_info_xml)
- for a in doc.findall('.//archive'):
- if archive_id == a.find('./id').text:
- break
- else:
- raise ExtractorError(u'Could not find chapter in chapter information')
-
- video_url = a.find('./video_file_url').text
- video_ext = video_url.rpartition('.')[2] or u'flv'
-
- chapter_api_url = u'https://api.twitch.tv/kraken/videos/c' + chapter_id
- chapter_info_json = self._download_webpage(chapter_api_url, u'c' + chapter_id,
- note='Downloading chapter metadata',
- errnote='Download of chapter metadata failed')
- chapter_info = json.loads(chapter_info_json)
-
- bracket_start = int(doc.find('.//bracket_start').text)
- bracket_end = int(doc.find('.//bracket_end').text)
-
- # TODO determine start (and probably fix up file)
- # youtube-dl -v http://www.twitch.tv/firmbelief/c/1757457
- #video_url += u'?start=' + TODO:start_timestamp
- # bracket_start is 13290, but we want 51670615
- self._downloader.report_warning(u'Chapter detected, but we can just download the whole file. '
- u'Chapter starts at %s and ends at %s' % (formatSeconds(bracket_start), formatSeconds(bracket_end)))
-
- info = {
- 'id': u'c' + chapter_id,
- 'url': video_url,
- 'ext': video_ext,
- 'title': chapter_info['title'],
- 'thumbnail': chapter_info['preview'],
- 'description': chapter_info['description'],
- 'uploader': chapter_info['channel']['display_name'],
- 'uploader_id': chapter_info['channel']['name'],
- }
- return [info]
- else:
- video_id = mobj.group('videoid')
- api = api_base + '/broadcast/by_archive/%s.json' % video_id
-
- self.report_extraction(video_id)
-
- info = []
- offset = 0
- limit = self._JUSTIN_PAGE_LIMIT
- while True:
- if paged:
- self.report_download_page(video_id, offset)
- page_url = api + ('?offset=%d&limit=%d' % (offset, limit))
- page_count, page_info = self._parse_page(page_url, video_id)
- info.extend(page_info)
- if not paged or page_count != limit:
- break
- offset += limit
- return info
-
-class FunnyOrDieIE(InfoExtractor):
- _VALID_URL = r'^(?:https?://)?(?:www\.)?funnyordie\.com/videos/(?P<id>[0-9a-f]+)/.*$'
-
- 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)
-
- video_url = self._html_search_regex(r'<video[^>]*>\s*<source[^>]*>\s*<source src="(?P<url>[^"]+)"',
- webpage, u'video URL', flags=re.DOTALL)
-
- title = self._html_search_regex((r"<h1 class='player_page_h1'.*?>(?P<title>.*?)</h1>",
- r'<title>(?P<title>[^<]+?)</title>'), webpage, 'title', flags=re.DOTALL)
-
- 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': video_description,
- }
- return [info]
-
-class SteamIE(InfoExtractor):
- _VALID_URL = r"""http://store\.steampowered\.com/
- (agecheck/)?
- (?P<urltype>video|app)/ #If the page is only for videos or for a game
- (?P<gameID>\d+)/?
- (?P<videoID>\d*)(?P<extra>\??) #For urltype == video we sometimes get the videoID
- """
- _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):
- """Receives a URL and returns True if suitable for this IE."""
- return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
-
- def _real_extract(self, url):
- m = re.match(self._VALID_URL, url, re.VERBOSE)
- gameID = m.group('gameID')
-
- videourl = self._VIDEO_PAGE_TEMPLATE % gameID
- webpage = self._download_webpage(videourl, gameID)
-
- 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>'
- titles = re.finditer(namesRE, webpage)
- thumbsRE = r'<img class="movie_thumb" src="(?P<thumbnail>.+?)">'
- thumbs = re.finditer(thumbsRE, webpage)
- videos = []
- for vid,vtitle,thumb in zip(mweb,titles,thumbs):
- video_id = vid.group('videoID')
- title = vtitle.group('videoName')
- video_url = vid.group('videoURL')
- video_thumb = thumb.group('thumbnail')
- if not video_url:
- raise ExtractorError(u'Cannot find video url for %s' % video_id)
- info = {
- 'id':video_id,
- 'url':video_url,
- 'ext': 'flv',
- 'title': unescapeHTML(title),
- 'thumbnail': video_thumb
- }
- videos.append(info)
- return [self.playlist_result(videos, gameID, game_title)]
-
-class UstreamIE(InfoExtractor):
- _VALID_URL = r'https?://www\.ustream\.tv/recorded/(?P<videoID>\d+)'
- IE_NAME = u'ustream'
-
- def _real_extract(self, url):
- m = re.match(self._VALID_URL, url)
- video_id = m.group('videoID')
-
- video_url = u'http://tcdn.ustream.tv/video/%s' % video_id
- webpage = self._download_webpage(url, video_id)
-
- self.report_extraction(video_id)
-
- 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,
- 'ext': 'flv',
- 'title': video_title,
- 'uploader': uploader,
- 'thumbnail': thumbnail,
- }
- return info
-
-class WorldStarHipHopIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)'
- IE_NAME = u'WorldStarHipHop'
-
- def _real_extract(self, url):
- m = re.match(self._VALID_URL, url)
- video_id = m.group('id')
-
- webpage_src = self._download_webpage(url, video_id)
-
- video_url = self._search_regex(r'so\.addVariable\("file","(.*?)"\)',
- webpage_src, u'video URL')
-
- if 'mp4' in video_url:
- ext = 'mp4'
- else:
- ext = 'flv'
-
- video_title = self._html_search_regex(r"<title>(.*)</title>",
- webpage_src, u'title')
-
- # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
- 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:
- video_title = mobj.group(1)
-
- results = [{
- 'id': video_id,
- 'url' : video_url,
- 'title' : video_title,
- 'thumbnail' : thumbnail,
- 'ext' : ext,
- }]
- return results
-
-class RBMARadioIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?rbmaradio\.com/shows/(?P<videoID>[^/]+)$'
-
- def _real_extract(self, url):
- m = re.match(self._VALID_URL, url)
- video_id = m.group('videoID')
-
- webpage = self._download_webpage(url, video_id)
-
- json_data = self._search_regex(r'window\.gon.*?gon\.show=(.+?);$',
- webpage, u'json data', flags=re.MULTILINE)
-
- try:
- data = json.loads(json_data)
- except ValueError as e:
- raise ExtractorError(u'Invalid JSON: ' + str(e))
-
- video_url = data['akamai_url'] + '&cbr=256'
- url_parts = compat_urllib_parse_urlparse(video_url)
- video_ext = url_parts.path.rpartition('.')[2]
- info = {
- 'id': video_id,
- 'url': video_url,
- 'ext': video_ext,
- 'title': data['title'],
- 'description': data.get('teaser_text'),
- 'location': data.get('country_of_origin'),
- 'uploader': data.get('host', {}).get('name'),
- 'uploader_id': data.get('host', {}).get('slug'),
- 'thumbnail': data.get('image', {}).get('large_url_2x'),
- 'duration': data.get('duration'),
- }
- return [info]
-
class YouPornIE(InfoExtractor):
"""Information extractor for youporn.com."""
}
return [info]
-class TEDIE(InfoExtractor):
- _VALID_URL=r'''http://www\.ted\.com/
- (
- ((?P<type_playlist>playlists)/(?P<playlist_id>\d+)) # We have a playlist
- |
- ((?P<type_talk>talks)) # We have a simple talk
- )
- (/lang/(.*?))? # The url may contain the language
- /(?P<name>\w+) # Here goes the name and then ".html"
- '''
-
- @classmethod
- def suitable(cls, url):
- """Receives a URL and returns True if suitable for this IE."""
- return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
-
- def _real_extract(self, url):
- m=re.match(self._VALID_URL, url, re.VERBOSE)
- if m.group('type_talk'):
- return [self._talk_info(url)]
- else :
- playlist_id=m.group('playlist_id')
- name=m.group('name')
- self.to_screen(u'Getting info of playlist %s: "%s"' % (playlist_id,name))
- return [self._playlist_videos_info(url,name,playlist_id)]
-
- def _playlist_videos_info(self,url,name,playlist_id=0):
- '''Returns the videos of the playlist'''
- video_RE=r'''
- <li\ id="talk_(\d+)"([.\s]*?)data-id="(?P<video_id>\d+)"
- ([.\s]*?)data-playlist_item_id="(\d+)"
- ([.\s]*?)data-mediaslug="(?P<mediaSlug>.+?)"
- '''
- video_name_RE=r'<p\ class="talk-title"><a href="(?P<talk_url>/talks/(.+).html)">(?P<fullname>.+?)</a></p>'
- webpage=self._download_webpage(url, playlist_id, 'Downloading playlist webpage')
- m_videos=re.finditer(video_RE,webpage,re.VERBOSE)
- m_names=re.finditer(video_name_RE,webpage)
-
- 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):
- video_id=m_video.group('video_id')
- talk_url='http://www.ted.com%s' % m_name.group('talk_url')
- playlist_entries.append(self.url_result(talk_url, 'TED'))
- return self.playlist_result(playlist_entries, playlist_id = playlist_id, playlist_title = playlist_title)
-
- 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)
- 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 = 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': info['id'],
- 'url': info['htmlStreams'][-1]['file'],
- 'ext': 'mp4',
- 'title': title,
- 'thumbnail': thumbnail,
- 'description': desc,
- }
- return info
class MySpassIE(InfoExtractor):
_VALID_URL = r'http://www.myspass.de/.*'
projects / youtube-dl.git / blobdiff