X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2FInfoExtractors.py;h=d91221d4d157b5e36036d55a5fa6609094c60dae;hb=7b6d7001d87ba93386c653f6e8c3a08b32f4ba4c;hp=a95b4aafeb4a448e9c1cd329a29c1723e1fcf8cb;hpb=3187e42a23a0bb68799935ed7acc7667e7dfe5c3;p=youtube-dl diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index a95b4aafe..d91221d4d 100644 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -13,6 +13,8 @@ import urllib import urllib2 import email.utils import xml.etree.ElementTree +import random +import math from urlparse import parse_qs try: @@ -95,7 +97,25 @@ class InfoExtractor(object): class YoutubeIE(InfoExtractor): """Information extractor for youtube.com.""" - _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$' + _VALID_URL = r"""^ + ( + (?:https?://)? # http(s):// (optional) + (?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/| + tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains + (?!view_play_list|my_playlists|artist|playlist) # ignore playlist URLs + (?: # the various things that can precede the ID: + (?:(?:v|embed|e)/) # v/ or embed/ or e/ + |(?: # or the v= param in all its forms + (?:watch(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) + (?:\?|\#!?) # the params delimiter ? or # or #! + (?:.+&)? # any other preceding param (like /?s=tuff&v=xxxx) + v= + ) + )? # optional -> youtube.com/xxxx is OK + )? # all until now is optional -> you can pass the naked ID + ([0-9A-Za-z_-]+) # here is it! the YouTube video ID + (?(1).+)? # if we found the ID, everything can follow + $""" _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en' _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' @@ -134,6 +154,10 @@ class YoutubeIE(InfoExtractor): } IE_NAME = u'youtube' + def suitable(self, url): + """Receives a URL and returns True if suitable for this IE.""" + return re.match(self._VALID_URL, url, re.VERBOSE) is not None + def report_lang(self): """Report attempt to set language.""" self._downloader.to_screen(u'[youtube] Setting language') @@ -182,7 +206,7 @@ class YoutubeIE(InfoExtractor): end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000) caption = unescapeHTML(caption) caption = unescapeHTML(caption) # double cycle, intentional - srt += str(n) + '\n' + srt += str(n+1) + '\n' srt += start + ' --> ' + end + '\n' srt += caption + '\n\n' return srt @@ -268,7 +292,7 @@ class YoutubeIE(InfoExtractor): url = 'http://www.youtube.com/' + urllib.unquote(mobj.group(1)).lstrip('/') # Extract video id from URL - mobj = re.match(self._VALID_URL, url) + mobj = re.match(self._VALID_URL, url, re.VERBOSE) if mobj is None: self._downloader.trouble(u'ERROR: invalid URL: %s' % url) return @@ -311,6 +335,11 @@ class YoutubeIE(InfoExtractor): self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason') return + # Check for "rental" videos + if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info: + self._downloader.trouble(u'ERROR: "rental" videos not supported') + return + # Start extracting information self.report_information_extraction(video_id) @@ -361,7 +390,8 @@ class YoutubeIE(InfoExtractor): srt_list = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: raise Trouble(u'WARNING: unable to download video subtitles: %s' % str(err)) - srt_lang_list = re.findall(r'lang_code="([\w\-]+)"', srt_list) + srt_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', srt_list) + srt_lang_list = dict((l[1], l[0]) for l in srt_lang_list) if not srt_lang_list: raise Trouble(u'WARNING: video has no closed captions') if self._downloader.params.get('subtitleslang', False): @@ -369,14 +399,16 @@ class YoutubeIE(InfoExtractor): elif 'en' in srt_lang_list: srt_lang = 'en' else: - srt_lang = srt_lang_list[0] + srt_lang = srt_lang_list.keys()[0] if not srt_lang in srt_lang_list: raise Trouble(u'WARNING: no closed captions found in the specified language') - request = urllib2.Request('http://video.google.com/timedtext?hl=en&lang=%s&v=%s' % (srt_lang, video_id)) + request = urllib2.Request('http://www.youtube.com/api/timedtext?lang=%s&name=%s&v=%s' % (srt_lang, srt_lang_list[srt_lang], video_id)) try: srt_xml = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: raise Trouble(u'WARNING: unable to download video subtitles: %s' % str(err)) + if not srt_xml: + raise Trouble(u'WARNING: unable to download video subtitles') video_subtitles = self._closed_captions_xml_to_srt(srt_xml.decode('utf-8')) except Trouble as trouble: self._downloader.trouble(trouble[0]) @@ -394,7 +426,7 @@ class YoutubeIE(InfoExtractor): url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',') url_data = [parse_qs(uds) for uds in url_data_strs] url_data = filter(lambda ud: 'itag' in ud and 'url' in ud, url_data) - url_map = dict((ud['itag'][0], ud['url'][0]) for ud in url_data) + url_map = dict((ud['itag'][0], ud['url'][0] + '&signature=' + ud['sig'][0]) for ud in url_data) format_limit = self._downloader.params.get('format_limit', None) available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats @@ -607,7 +639,7 @@ class DailymotionIE(InfoExtractor): video_id = mobj.group(1) - video_extension = 'flv' + video_extension = 'mp4' # Retrieve video webpage to extract further information request = urllib2.Request(url) @@ -621,20 +653,23 @@ class DailymotionIE(InfoExtractor): # Extract URL, uploader and title from webpage self.report_extraction(video_id) - mobj = re.search(r'(?i)addVariable\(\"sequence\"\s*,\s*\"([^\"]+?)\"\)', webpage) + mobj = re.search(r'\s*var flashvars = (.*)', webpage) if mobj is None: self._downloader.trouble(u'ERROR: unable to extract media URL') return - sequence = urllib.unquote(mobj.group(1)) - mobj = re.search(r',\"sdURL\"\:\"([^\"]+?)\",', sequence) + flashvars = urllib.unquote(mobj.group(1)) + if 'hqURL' in flashvars: max_quality = 'hqURL' + elif 'sdURL' in flashvars: max_quality = 'sdURL' + else: max_quality = 'ldURL' + mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars) + if mobj is None: + mobj = re.search(r'"video_url":"(.*?)",', urllib.unquote(webpage)) if mobj is None: self._downloader.trouble(u'ERROR: unable to extract media URL') return - mediaURL = urllib.unquote(mobj.group(1)).replace('\\', '') - - # if needed add http://www.dailymotion.com/ if relative URL + video_url = urllib.unquote(mobj.group(1)).replace('\\/', '/') - video_url = mediaURL + # TODO: support choosing qualities mobj = re.search(r'', webpage) if mobj is None: @@ -1227,7 +1262,7 @@ class YoutubeSearchIE(InfoExtractor): InfoExtractor.__init__(self, downloader) def report_download_page(self, query, pagenum): - """Report attempt to download playlist page with given number.""" + """Report attempt to download search page with given number.""" query = query.decode(preferredencoding()) self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum)) @@ -1463,8 +1498,8 @@ class YoutubePlaylistIE(InfoExtractor): _VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL)?([0-9A-Za-z-_]+)(?:/.*?/([0-9A-Za-z_-]+))?.*' _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en' - _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&list=PL%s&' - _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*' + _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&list=.*?%s' + _MORE_PAGES_INDICATOR = r'yt-uix-pager-next' IE_NAME = u'youtube:playlist' def __init__(self, downloader=None): @@ -1618,7 +1653,7 @@ class BlipTVUserIE(InfoExtractor): """Information Extractor for blip.tv users.""" _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$' - _PAGE_SIZE = 10 + _PAGE_SIZE = 12 IE_NAME = u'blip.tv:user' def __init__(self, downloader=None): @@ -1638,31 +1673,31 @@ class BlipTVUserIE(InfoExtractor): username = mobj.group(1) - page_base = None + page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1' request = urllib2.Request(url) try: page = urllib2.urlopen(request).read().decode('utf-8') - mobj = re.search(r'data-source-url="([^"]+)"', page) - page_base = "http://blip.tv" + unescapeHTML(mobj.group(1)) + mobj = re.search(r'data-users-id="([^"]+)"', page) + page_base = page_base % mobj.group(1) except (urllib2.URLError, httplib.HTTPException, socket.error), err: self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) return - # Download video ids using BlipTV Page API. Result size per - # query is limited (currently to 10 videos) so we need to query + # Download video ids using BlipTV Ajax calls. Result size per + # query is limited (currently to 12 videos) so we need to query # page by page until there are no video ids - it means we got # all of them. video_ids = [] - pagenum = 0 + pagenum = 1 while True: self.report_download_page(username, pagenum) - request = urllib2.Request( page_base + "&page=" + str(pagenum+1) ) + request = urllib2.Request( page_base + "&page=" + str(pagenum) ) try: page = urllib2.urlopen(request).read().decode('utf-8') @@ -2062,6 +2097,7 @@ class BlipTVIE(InfoExtractor): self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err)) return + std_headers['User-Agent'] = 'iTunes/10.6.1' return [info] @@ -2280,12 +2316,14 @@ class EscapistIE(InfoExtractor): self.report_extraction(showName) try: - webPageBytes = urllib2.urlopen(url).read() + webPage = urllib2.urlopen(url) + webPageBytes = webPage.read() + m = re.match(r'text/html; charset="?([^"]+)"?', webPage.headers['Content-Type']) + webPage = webPageBytes.decode(m.group(1) if m else 'utf-8') except (urllib2.URLError, httplib.HTTPException, socket.error), err: self._downloader.trouble(u'ERROR: unable to download webpage: ' + unicode(err)) return - webPage = webPageBytes.decode('utf-8') descMatch = re.search('[A-Za-z0-9]+)\.html' + IE_NAME = u'Youku' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_webpage(self, file_id): + """Report webpage download.""" + self._downloader.to_screen(u'[Youku] %s: Downloading webpage' % file_id) + + def report_extraction(self, file_id): + """Report information extraction.""" + self._downloader.to_screen(u'[Youku] %s: Extracting information' % file_id) + + 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: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + video_id = mobj.group('ID') + + info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id + + request = urllib2.Request(info_url, None, std_headers) + try: + self.report_download_webpage(video_id) + jsondata = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) + return + + 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 = 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] + seg_number = len(config['data'][0]['segs'][format]) + + keys=[] + for i in xrange(seg_number): + keys.append(config['data'][0]['segs'][format][i]['k']) + + #TODO check error + #youku only could be viewed from mainland china + except: + self._downloader.trouble(u'ERROR: unable to extract info section') + return + + 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, + 'title': video_title, + 'ext': ext, + 'format': u'NA' + } + files_info.append(info) + + return files_info + + +class XNXXIE(InfoExtractor): + """Information extractor for xnxx.com""" + + _VALID_URL = r'^http://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 report_webpage(self, video_id): + """Report information extraction""" + self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) + + def report_extraction(self, video_id): + """Report information extraction""" + self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + video_id = mobj.group(1).decode('utf-8') + + self.report_webpage(video_id) + + # Get webpage content + try: + webpage = urllib2.urlopen(url).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err) + return + + result = re.search(self.VIDEO_URL_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract video url') + return + video_url = urllib.unquote(result.group(1).decode('utf-8')) + + result = re.search(self.VIDEO_TITLE_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = result.group(1).decode('utf-8') + + result = re.search(self.VIDEO_THUMB_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract video thumbnail') + return + video_thumbnail = result.group(1).decode('utf-8') + + info = {'id': video_id, + 'url': video_url, + 'uploader': None, + 'upload_date': None, + 'title': video_title, + 'ext': 'flv', + 'format': 'flv', + 'thumbnail': video_thumbnail, + 'description': None, + 'player_url': None} + + return [info]