X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube_dl%2FInfoExtractors.py;h=c06ecbe52aad148ce036cd98c74ef1f371b27c78;hb=9f5daf0006091124799e13c834db17201ebdbbc5;hp=51b3a0fad43a31480347c494132d8bcfeb6ec4d4;hpb=0143dc029c6cf9fa187960f6bfa9861c171a9f40;p=youtube-dl.git diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 51b3a0fad..c06ecbe52 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -20,11 +20,13 @@ from .extractor.common import InfoExtractor, SearchInfoExtractor from .extractor.ard import ARDIE from .extractor.arte import ArteTvIE +from .extractor.bandcamp import BandcampIE 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.eighttracks import EightTracksIE from .extractor.escapist import EscapistIE from .extractor.facebook import FacebookIE from .extractor.funnyordie import FunnyOrDieIE @@ -34,24 +36,34 @@ from .extractor.googleplus import GooglePlusIE from .extractor.googlesearch import GoogleSearchIE from .extractor.infoq import InfoQIE from .extractor.justintv import JustinTVIE +from .extractor.keek import KeekIE +from .extractor.liveleak import LiveLeakIE from .extractor.metacafe import MetacafeIE from .extractor.mixcloud import MixcloudIE from .extractor.mtv import MTVIE +from .extractor.myspass import MySpassIE from .extractor.myvideo import MyVideoIE from .extractor.nba import NBAIE from .extractor.statigram import StatigramIE from .extractor.photobucket import PhotobucketIE +from .extractor.pornotube import PornotubeIE from .extractor.rbmaradio import RBMARadioIE +from .extractor.redtube import RedTubeIE from .extractor.soundcloud import SoundcloudIE, SoundcloudSetIE +from .extractor.spiegel import SpiegelIE from .extractor.stanfordoc import StanfordOpenClassroomIE from .extractor.steam import SteamIE from .extractor.ted import TEDIE +from .extractor.tumblr import TumblrIE from .extractor.ustream import UstreamIE +from .extractor.vbox7 import Vbox7IE from .extractor.vimeo import VimeoIE +from .extractor.vine import VineIE from .extractor.worldstarhiphop import WorldStarHipHopIE from .extractor.xnxx import XNXXIE from .extractor.xvideos import XVideosIE from .extractor.yahoo import YahooIE, YahooSearchIE +from .extractor.youjizz import YouJizzIE from .extractor.youku import YoukuIE from .extractor.youporn import YouPornIE from .extractor.youtube import YoutubeIE, YoutubePlaylistIE, YoutubeSearchIE, YoutubeUserIE, YoutubeChannelIE @@ -79,385 +91,18 @@ from .extractor.zdf import ZDFIE -class PornotubeIE(InfoExtractor): - """Information extractor for pornotube.com.""" - _VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P[0-9]+))?(/m/(?P[0-9]+))(/(?P.+))$' - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) - - video_id = mobj.group('videoid') - video_title = mobj.group('title') - - # Get webpage content - webpage = self._download_webpage(url, video_id) - - # Get the video URL - VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",' - video_url = self._search_regex(VIDEO_URL_RE, webpage, u'video url') - video_url = compat_urllib_parse.unquote(video_url) - - #Get the uploaded date - VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by' - upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, u'upload date', fatal=False) - if upload_date: upload_date = unified_strdate(upload_date) - - info = {'id': video_id, - 'url': video_url, - 'uploader': None, - 'upload_date': upload_date, - 'title': video_title, - 'ext': 'flv', - 'format': 'flv'} - - return [info] - -class YouJizzIE(InfoExtractor): - """Information extractor for youjizz.com.""" - _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$' - - 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') - - # Get webpage content - webpage = self._download_webpage(url, video_id) - - # Get the video title - video_title = self._html_search_regex(r'<title>(?P<title>.*)', - webpage, u'title').strip() - - # Get the embed page - result = re.search(r'https?://www.youjizz.com/videos/embed/(?P[0-9]+)', webpage) - if result is None: - raise ExtractorError(u'ERROR: unable to extract embed page') - - embed_page_url = result.group(0).strip() - video_id = result.group('videoid') - - webpage = self._download_webpage(embed_page_url, video_id) - - # Get the video URL - video_url = self._search_regex(r'so.addVariable\("file",encodeURIComponent\("(?P[^"]+)"\)\);', - webpage, u'video URL') - - info = {'id': video_id, - 'url': video_url, - 'title': video_title, - 'ext': 'flv', - 'format': 'flv', - 'player_url': embed_page_url} - - return [info] - -class EightTracksIE(InfoExtractor): - IE_NAME = '8tracks' - _VALID_URL = r'https?://8tracks.com/(?P[^/]+)/(?P[^/#]+)(?:#.*)?$' - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) - playlist_id = mobj.group('id') - - webpage = self._download_webpage(url, playlist_id) - - 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)) - mix_id = data['id'] - track_count = data['tracks_count'] - first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id) - next_url = first_url - res = [] - for i in itertools.count(): - api_json = self._download_webpage(next_url, playlist_id, - note=u'Downloading song information %s/%s' % (str(i+1), track_count), - errnote=u'Failed to download song information') - api_data = json.loads(api_json) - track_data = api_data[u'set']['track'] - info = { - 'id': track_data['id'], - 'url': track_data['track_file_stream_url'], - 'title': track_data['performer'] + u' - ' + track_data['name'], - 'raw_title': track_data['name'], - 'uploader_id': data['user']['login'], - 'ext': 'm4a', - } - res.append(info) - if api_data['set']['at_last_track']: - break - next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % (session, mix_id, track_data['id']) - return res - -class KeekIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P\w+)' - IE_NAME = u'keek' - - def _real_extract(self, url): - m = re.match(self._VALID_URL, url) - video_id = m.group('videoID') - - video_url = u'http://cdn.keek.com/keek/video/%s' % video_id - thumbnail = u'http://cdn.keek.com/keek/thumbnail/%s/w100/h75' % video_id - webpage = self._download_webpage(url, video_id) - - video_title = self._html_search_regex(r'[\S\s]+?

(?P.+?)

', - webpage, u'uploader', fatal=False) - - info = { - 'id': video_id, - 'url': video_url, - 'ext': 'mp4', - 'title': video_title, - 'thumbnail': thumbnail, - 'uploader': uploader - } - return [info] - - -class MySpassIE(InfoExtractor): - _VALID_URL = r'http://www.myspass.de/.*' - - def _real_extract(self, url): - META_DATA_URL_TEMPLATE = 'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=%s' - - # video id is the last path element of the URL - # usually there is a trailing slash, so also try the second but last - url_path = compat_urllib_parse_urlparse(url).path - url_parent_path, video_id = os.path.split(url_path) - if not video_id: - _, video_id = os.path.split(url_parent_path) - - # get metadata - metadata_url = META_DATA_URL_TEMPLATE % video_id - metadata_text = self._download_webpage(metadata_url, video_id) - metadata = xml.etree.ElementTree.fromstring(metadata_text.encode('utf-8')) - - # extract values from metadata - url_flv_el = metadata.find('url_flv') - if url_flv_el is None: - raise ExtractorError(u'Unable to extract download url') - video_url = url_flv_el.text - extension = os.path.splitext(video_url)[1][1:] - title_el = metadata.find('title') - if title_el is None: - raise ExtractorError(u'Unable to extract title') - title = title_el.text - format_id_el = metadata.find('format_id') - if format_id_el is None: - format = ext - else: - format = format_id_el.text - description_el = metadata.find('description') - if description_el is not None: - description = description_el.text - else: - description = None - imagePreview_el = metadata.find('imagePreview') - if imagePreview_el is not None: - thumbnail = imagePreview_el.text - else: - thumbnail = None - info = { - 'id': video_id, - 'url': video_url, - 'title': title, - 'ext': extension, - 'format': format, - 'thumbnail': thumbnail, - 'description': description - } - return [info] -class SpiegelIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P[0-9]+)(?:\.html)?(?:#.*)?$' - def _real_extract(self, url): - m = re.match(self._VALID_URL, url) - video_id = m.group('videoID') - webpage = self._download_webpage(url, video_id) - video_title = self._html_search_regex(r'
(.*?)
', - webpage, u'title') - xml_url = u'http://video2.spiegel.de/flash/' + video_id + u'.xml' - xml_code = self._download_webpage(xml_url, video_id, - note=u'Downloading XML', errnote=u'Failed to download XML') - idoc = xml.etree.ElementTree.fromstring(xml_code) - last_type = idoc[-1] - filename = last_type.findall('./filename')[0].text - duration = float(last_type.findall('./duration')[0].text) - video_url = 'http://video2.spiegel.de/flash/' + filename - video_ext = filename.rpartition('.')[2] - info = { - 'id': video_id, - 'url': video_url, - 'ext': video_ext, - 'title': video_title, - 'duration': duration, - } - return [info] -class LiveLeakIE(InfoExtractor): - _VALID_URL = r'^(?:http?://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P[\w_]+)(?:.*)' - IE_NAME = u'liveleak' - 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('video_id') - - webpage = self._download_webpage(url, video_id) - - video_url = self._search_regex(r'file: "(.*?)",', - webpage, u'video URL') - - video_title = self._html_search_regex(r'', - webpage, u'uploader', fatal=False) - - info = { - 'id': video_id, - 'url': video_url, - 'ext': 'mp4', - 'title': video_title, - 'description': video_description, - 'uploader': video_uploader - } - - return [info] - - - -class TumblrIE(InfoExtractor): - _VALID_URL = r'http://(?P.*?)\.tumblr\.com/((post)|(video))/(?P\d*)/(.*?)' - - def _real_extract(self, url): - m_url = re.match(self._VALID_URL, url) - video_id = m_url.group('id') - blog = m_url.group('blog_name') - - url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id) - webpage = self._download_webpage(url, video_id) - - re_video = r'src=\\x22(?Phttp://%s\.tumblr\.com/video_file/%s/(.*?))\\x22 type=\\x22video/(?P.*?)\\x22' % (blog, video_id) - video = re.search(re_video, webpage) - if video is None: - raise ExtractorError(u'Unable to extract video') - video_url = video.group('video_url') - ext = video.group('ext') - - video_thumbnail = self._search_regex(r'posters(.*?)\[\\x22(?P.*?)\\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 - video_title = self._html_search_regex(r'(?P<title>.*?)', - webpage, u'title', flags=re.DOTALL) - - return [{'id': video_id, - 'url': video_url, - 'title': video_title, - 'thumbnail': video_thumbnail, - 'ext': ext - }] - -class BandcampIE(InfoExtractor): - _VALID_URL = r'http://.*?\.bandcamp\.com/track/(?P.*)' - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - title = mobj.group('title') - webpage = self._download_webpage(url, title) - # 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 found') - - download_link = m_download.group(1) - id = re.search(r'var TralbumData = {(.*?)id: (?P<id>\d*?)$', - webpage, re.MULTILINE|re.DOTALL).group('id') - - download_webpage = self._download_webpage(download_link, id, - 'Downloading free downloads page') - # We get the dictionary of the track from some javascrip code - info = re.search(r'items: (.*?),$', - download_webpage, re.MULTILINE).group(1) - info = json.loads(info)[0] - # We pick mp3-320 for now, until format selection can be easily implemented. - mp3_info = info[u'downloads'][u'mp3-320'] - # If we try to use this url it says the link has expired - initial_url = mp3_info[u'url'] - re_url = r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$' - m_url = re.match(re_url, initial_url) - #We build the url we will use to get the final track url - # This url is build in Bandcamp in the script download_bunde_*.js - request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), id, m_url.group('ts')) - final_url_webpage = self._download_webpage(request_url, id, 'Requesting download url') - # If we could correctly generate the .rand field the url would be - #in the "download_url" key - final_url = re.search(r'"retry_url":"(.*?)"', final_url_webpage).group(1) - - track_info = {'id':id, - 'title' : info[u'title'], - 'ext' : 'mp3', - 'url' : final_url, - 'thumbnail' : info[u'thumb_url'], - 'uploader' : info[u'artist'] - } - - return [track_info] - -class RedTubeIE(InfoExtractor): - """Information Extractor for redtube""" - _VALID_URL = r'(?:http://)?(?:www\.)?redtube\.com/(?P<id>[0-9]+)' - - 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_extension = 'mp4' - webpage = self._download_webpage(url, video_id) - - self.report_extraction(video_id) - - video_url = self._html_search_regex(r'<source src="(.+?)" type="video/mp4">', - webpage, u'video URL') - - video_title = self._html_search_regex('<h1 class="videoTitle slidePanelMovable">(.+?)</h1>', - webpage, u'title') - - return [{ - 'id': video_id, - 'url': video_url, - 'ext': video_extension, - 'title': video_title, - }] - class InaIE(InfoExtractor): """Information Extractor for Ina.fr""" _VALID_URL = r'(?:http://)?(?:www\.)?ina\.fr/video/(?P<id>I[0-9]+)/.*' @@ -519,39 +164,6 @@ class HowcastIE(InfoExtractor): 'thumbnail': thumbnail, }] -class VineIE(InfoExtractor): - """Information Extractor for Vine.co""" - _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') - webpage_url = 'https://vine.co/v/' + video_id - webpage = self._download_webpage(webpage_url, video_id) - - self.report_extraction(video_id) - - video_url = self._html_search_regex(r'<meta property="twitter:player:stream" content="(.+?)"', - webpage, u'video URL') - - video_title = self._html_search_regex(r'<meta property="og:title" content="(.+?)"', - webpage, u'title') - - thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.+?)(\?.*?)?"', - webpage, u'thumbnail', fatal=False) - - uploader = self._html_search_regex(r'<div class="user">.*?<h2>(.+?)</h2>', - webpage, u'uploader', fatal=False, flags=re.DOTALL) - - return [{ - 'id': video_id, - 'url': video_url, - 'ext': 'mp4', - 'title': video_title, - 'thumbnail': thumbnail, - 'uploader': uploader, - }] class FlickrIE(InfoExtractor): """Information Extractor for Flickr videos""" @@ -743,41 +355,6 @@ class HypemIE(InfoExtractor): 'artist': artist, }] -class Vbox7IE(InfoExtractor): - """Information Extractor for Vbox7""" - _VALID_URL = r'(?:http://)?(?:www\.)?vbox7\.com/play:([^/]+)' - - 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) - - redirect_page, urlh = self._download_webpage_handle(url, video_id) - 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 = self._html_search_regex(r'<title>(.*)', - webpage, u'title').split('/')[0].strip() - - ext = "flv" - info_url = "http://vbox7.com/play/magare.do" - data = compat_urllib_parse.urlencode({'as3':'1','vid':video_id}) - info_request = compat_urllib_request.Request(info_url, data) - info_request.add_header('Content-Type', 'application/x-www-form-urlencoded') - 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, thumbnail_url) = map(lambda x: x.split('=')[1], info_response.split('&')) - - return [{ - 'id': video_id, - 'url': final_url, - 'ext': ext, - 'title': title, - 'thumbnail': thumbnail_url, - }] def gen_extractors():