X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2FInfoExtractors.py;h=672ef9eedb40b1f8aa7db86e0a20b591c88511f3;hb=3823342d9d0a2c50327aa3e1f85a7e8e1221b0bc;hp=1b7e5649d4dbfd386aa17f3b4d2f59c0df808b85;hpb=80cbb6ddbbcd84fce12a9f918cd2417529239a18;p=youtube-dl diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 1b7e5649d..672ef9eed 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -1,1397 +1,4 @@ -import base64 -import datetime -import itertools -import netrc -import os -import re -import socket -import time -import email.utils -import xml.etree.ElementTree -import random -import math -import operator -import hashlib -import binascii -import urllib +# Legacy file for backwards compatibility, use youtube_dl.extractor instead! -from .utils import * from .extractor.common import InfoExtractor, SearchInfoExtractor - -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.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.soundcloud import SoundcloudIE, SoundcloudSetIE -from .extractor.stanfordoc import StanfordOpenClassroomIE -from .extractor.ted import TEDIE -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 YoukuIE(InfoExtractor): - _VALID_URL = r'(?:http://)?v\.youku\.com/v_show/id_(?P[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'(.*?)\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 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>[^<]+?)'), webpage, 'title', flags=re.DOTALL) - - video_description = self._html_search_regex(r'video|app)/ #If the page is only for videos or for a game - (?P\d+)/? - (?P\d*)(?P\??) #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('

Please enter your birth date to continue:

', 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'

(.*?)

', - webpage, 'game title') - - urlRE = r"'movie_(?P\d+)': \{\s*FILENAME: \"(?P[\w:/\.\?=]+)\"(,\s*MOVIE_NAME: \"(?P[\w:/\.\?=\+-]+)\")?\s*\}," - mweb = re.finditer(urlRE, webpage) - namesRE = r'(?P.+?)' - titles = re.finditer(namesRE, webpage) - thumbsRE = r'' - 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\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.+)"', - 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>(.*)", - 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.*>(.*)""" - 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[^/]+)$' - - def _real_extract(self, url): - m = re.match(self._VALID_URL, url) - video_id = m.group('videoID') - - webpage = self._download_webpage(url, video_id) - - json_data = self._search_regex(r'window\.gon.*?gon\.show=(.+?);$', - 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.""" - _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P[0-9]+)/(?P[^/]+)' - - def _print_formats(self, formats): - """Print all available formats""" - print(u'Available formats:') - print(u'ext\t\tformat') - print(u'---------------------------------') - for format in formats: - print(u'%s\t\t%s' % (format['ext'], format['format'])) - - def _specific(self, req_format, formats): - for x in formats: - if(x["format"]==req_format): - return x - return None - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) - video_id = mobj.group('videoid') - - req = compat_urllib_request.Request(url) - req.add_header('Cookie', 'age_verified=1') - webpage = self._download_webpage(req, video_id) - - # Get JSON parameters - json_params = self._search_regex(r'var currentVideo = new Video\((.*)\);', webpage, u'JSON parameters') - try: - params = json.loads(json_params) - except: - raise ExtractorError(u'Invalid JSON') - - self.report_extraction(video_id) - try: - video_title = params['title'] - upload_date = unified_strdate(params['release_date_f']) - video_description = params['description'] - video_uploader = params['submitted_by'] - thumbnail = params['thumbnails'][0]['image'] - except KeyError: - raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1]) - - # Get all of the formats available - DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>' - download_list_html = self._search_regex(DOWNLOAD_LIST_RE, - webpage, u'download list').strip() - - # Get all of the links from the page - LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">' - links = re.findall(LINK_RE, download_list_html) - if(len(links) == 0): - raise ExtractorError(u'ERROR: no known formats available for video') - - self.to_screen(u'Links found: %d' % len(links)) - - formats = [] - for link in links: - - # A link looks like this: - # http://cdn1.download.youporn.phncdn.com/201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4?nvb=20121113051249&nva=20121114051249&ir=1200&sr=1200&hash=014b882080310e95fb6a0 - # A path looks like this: - # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4 - video_url = unescapeHTML( link ) - path = compat_urllib_parse_urlparse( video_url ).path - extension = os.path.splitext( path )[1][1:] - format = path.split('/')[4].split('_')[:2] - size = format[0] - bitrate = format[1] - format = "-".join( format ) - # title = u'%s-%s-%s' % (video_title, size, bitrate) - - formats.append({ - 'id': video_id, - 'url': video_url, - 'uploader': video_uploader, - 'upload_date': upload_date, - 'title': video_title, - 'ext': extension, - 'format': format, - 'thumbnail': thumbnail, - 'description': video_description - }) - - if self._downloader.params.get('listformats', None): - self._print_formats(formats) - return - - req_format = self._downloader.params.get('format', None) - self.to_screen(u'Format: %s' % req_format) - - if req_format is None or req_format == 'best': - return [formats[0]] - elif req_format == 'worst': - return [formats[-1]] - elif req_format in ('-1', 'all'): - return formats - else: - format = self._specific( req_format, formats ) - if result is None: - raise ExtractorError(u'Requested format not available') - return [format] - - - -class PornotubeIE(InfoExtractor): - """Information extractor for pornotube.com.""" - _VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$' - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) - - video_id = mobj.group('videoid') - video_title = mobj.group('title') - - # Get webpage content - webpage = self._download_webpage(url, video_id) - - # Get the video URL - VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",' - video_url = self._search_regex(VIDEO_URL_RE, webpage, u'video url') - video_url = compat_urllib_parse.unquote(video_url) - - #Get the uploaded date - VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by' - upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, u'upload date', fatal=False) - if upload_date: upload_date = unified_strdate(upload_date) - - info = {'id': video_id, - 'url': video_url, - 'uploader': None, - 'upload_date': upload_date, - 'title': video_title, - 'ext': 'flv', - 'format': 'flv'} - - return [info] - -class YouJizzIE(InfoExtractor): - """Information extractor for youjizz.com.""" - _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$' - - 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]+)/.*' - - def _real_extract(self,url): - mobj = re.match(self._VALID_URL, url) - - video_id = mobj.group('id') - mrss_url='http://player.ina.fr/notices/%s.mrss' % video_id - video_extension = 'mp4' - webpage = self._download_webpage(mrss_url, video_id) - - self.report_extraction(video_id) - - video_url = self._html_search_regex(r'<media:player url="(?P<mp4url>http://mp4.ina.fr/[^"]+\.mp4)', - webpage, u'video URL') - - video_title = self._search_regex(r'<title><!\[CDATA\[(?P<titre>.*?)]]>', - webpage, u'title') - - return [{ - 'id': video_id, - 'url': video_url, - 'ext': video_extension, - 'title': video_title, - }] - -class HowcastIE(InfoExtractor): - """Information Extractor for Howcast.com""" - _VALID_URL = r'(?:https?://)?(?:www\.)?howcast\.com/videos/(?P\d+)' - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - - video_id = mobj.group('id') - webpage_url = 'http://www.howcast.com/videos/' + video_id - webpage = self._download_webpage(webpage_url, video_id) - - self.report_extraction(video_id) - - video_url = self._search_regex(r'\'?file\'?: "(http://mobile-media\.howcast\.com/[0-9]+\.mp4)', - webpage, u'video URL') - - video_title = self._html_search_regex(r'\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'.*?

(.+?)

', - 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""" - _VALID_URL = r'(?:https?://)?(?:www\.)?flickr\.com/photos/(?P[\w\-_@]+)/(?P\d+).*' - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - - video_id = mobj.group('id') - video_uploader_id = mobj.group('uploader_id') - webpage_url = 'http://www.flickr.com/photos/' + video_uploader_id + '/' + video_id - webpage = self._download_webpage(webpage_url, video_id) - - secret = self._search_regex(r"photo_secret: '(\w+)'", webpage, u'secret') - - first_url = 'https://secure.flickr.com/apps/video/video_mtl_xml.gne?v=x&photo_id=' + video_id + '&secret=' + secret + '&bitrate=700&target=_self' - first_xml = self._download_webpage(first_url, video_id, 'Downloading first data webpage') - - node_id = self._html_search_regex(r'(\d+-\d+)', - first_xml, u'node_id') - - second_url = 'https://secure.flickr.com/video_playlist.gne?node_id=' + node_id + '&tech=flash&mode=playlist&bitrate=700&secret=' + secret + '&rd=video.yahoo.com&noad=1' - second_xml = self._download_webpage(second_url, video_id, 'Downloading second data webpage') - - self.report_extraction(video_id) - - mobj = re.search(r'.*)' - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) - url_title = mobj.group('url_title') - webpage = self._download_webpage(url, url_title) - - video_id = self._html_search_regex(r'
(.*?)', - data, u'video URL') - - return [{ - 'id': video_id, - 'url': video_url, - 'ext': 'mp4', - 'title': video_title, - 'thumbnail': thumbnail, - 'description': video_description, - }] - -class XHamsterIE(InfoExtractor): - """Information Extractor for xHamster""" - _VALID_URL = r'(?:http://)?(?:www.)?xhamster\.com/movies/(?P[0-9]+)/.*\.html' - - def _real_extract(self,url): - mobj = re.match(self._VALID_URL, url) - - video_id = mobj.group('id') - mrss_url = 'http://xhamster.com/movies/%s/.html' % video_id - webpage = self._download_webpage(mrss_url, video_id) - - mobj = re.search(r'\'srv\': \'(?P[^\']*)\',\s*\'file\': \'(?P[^\']+)\',', webpage) - if mobj is None: - raise ExtractorError(u'Unable to extract media URL') - if len(mobj.group('server')) == 0: - video_url = compat_urllib_parse.unquote(mobj.group('file')) - else: - video_url = mobj.group('server')+'/key='+mobj.group('file') - video_extension = video_url.split('.')[-1] - - video_title = self._html_search_regex(r'(?P<title>.+?) - xHamster\.com', - webpage, u'title') - - # Can't see the description anywhere in the UI - # video_description = self._html_search_regex(r'Description: (?P[^<]+)', - # webpage, u'description', fatal=False) - # if video_description: video_description = unescapeHTML(video_description) - - mobj = re.search(r'hint=\'(?P[0-9]{4})-(?P[0-9]{2})-(?P[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage) - if mobj: - video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d') - else: - video_upload_date = None - self._downloader.report_warning(u'Unable to extract upload date') - - video_uploader_id = self._html_search_regex(r']+>(?P[^<]+)', - webpage, u'uploader id', default=u'anonymous') - - video_thumbnail = self._search_regex(r'\'image\':\'(?P[^\']+)\'', - webpage, u'thumbnail', fatal=False) - - return [{ - 'id': video_id, - 'url': video_url, - 'ext': video_extension, - 'title': video_title, - # 'description': video_description, - 'upload_date': video_upload_date, - 'uploader_id': video_uploader_id, - 'thumbnail': video_thumbnail - }] - -class HypemIE(InfoExtractor): - """Information Extractor for hypem""" - _VALID_URL = r'(?:http://)?(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)' - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) - track_id = mobj.group(1) - - data = { 'ax': 1, 'ts': time.time() } - data_encoded = compat_urllib_parse.urlencode(data) - complete_url = url + "?" + data_encoded - request = compat_urllib_request.Request(complete_url) - response, urlh = self._download_webpage_handle(request, track_id, u'Downloading webpage with the url') - cookie = urlh.headers.get('Set-Cookie', '') - - self.report_extraction(track_id) - - html_tracks = self._html_search_regex(r'', - response, u'tracks', flags=re.MULTILINE|re.DOTALL).strip() - try: - track_list = json.loads(html_tracks) - track = track_list[u'tracks'][0] - except ValueError: - raise ExtractorError(u'Hypemachine contained invalid JSON.') - - key = track[u"key"] - track_id = track[u"id"] - artist = track[u"artist"] - title = track[u"song"] - - serve_url = "http://hypem.com/serve/source/%s/%s" % (compat_str(track_id), compat_str(key)) - request = compat_urllib_request.Request(serve_url, "" , {'Content-Type': 'application/json'}) - request.add_header('cookie', cookie) - song_data_json = self._download_webpage(request, track_id, u'Downloading metadata') - try: - song_data = json.loads(song_data_json) - except ValueError: - raise ExtractorError(u'Hypemachine contained invalid JSON.') - final_url = song_data[u"url"] - - return [{ - 'id': track_id, - 'url': final_url, - 'ext': "mp3", - 'title': title, - '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'(.*)', - 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(): - """ Return a list of an instance of every supported extractor. - The order does matter; the first extractor matched is the one handling the URL. - """ - return [ - YoutubePlaylistIE(), - YoutubeChannelIE(), - YoutubeUserIE(), - YoutubeSearchIE(), - YoutubeIE(), - MetacafeIE(), - DailymotionIE(), - GoogleSearchIE(), - PhotobucketIE(), - YahooIE(), - YahooSearchIE(), - DepositFilesIE(), - FacebookIE(), - BlipTVIE(), - BlipTVUserIE(), - VimeoIE(), - MyVideoIE(), - ComedyCentralIE(), - EscapistIE(), - CollegeHumorIE(), - XVideosIE(), - SoundcloudSetIE(), - SoundcloudIE(), - InfoQIE(), - MixcloudIE(), - StanfordOpenClassroomIE(), - MTVIE(), - YoukuIE(), - XNXXIE(), - YouJizzIE(), - PornotubeIE(), - YouPornIE(), - GooglePlusIE(), - ArteTvIE(), - NBAIE(), - WorldStarHipHopIE(), - JustinTVIE(), - FunnyOrDieIE(), - SteamIE(), - UstreamIE(), - RBMARadioIE(), - EightTracksIE(), - KeekIE(), - TEDIE(), - MySpassIE(), - SpiegelIE(), - LiveLeakIE(), - ARDIE(), - ZDFIE(), - TumblrIE(), - BandcampIE(), - RedTubeIE(), - InaIE(), - HowcastIE(), - VineIE(), - FlickrIE(), - TeamcocoIE(), - XHamsterIE(), - HypemIE(), - Vbox7IE(), - GametrailersIE(), - StatigramIE(), - GenericIE() - ] - -def get_info_extractor(ie_name): - """Returns the info extractor class with the given ie_name""" - return globals()[ie_name+'IE'] +from .extractor import gen_extractors, get_info_extractor