X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube_dl%2FInfoExtractors.py;h=282334635079560723bf38562abae0032bf15b96;hb=f380401bbd1f41e00bc2d75a1354aed64bb18c30;hp=58d082648a79d52c085aa0ac194cf3f7a0f60141;hpb=c794cbbb19784a2cca88cad53f76fd837e74aa4a;p=youtube-dl.git diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 58d082648..282334635 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -1060,7 +1060,7 @@ class VimeoIE(InfoExtractor): """Information extractor for vimeo.com.""" # _VALID_URL matches Vimeo URLs - _VALID_URL = r'(?Phttps?://)?(?:(?:www|player)\.)?vimeo\.com/(?:(?:groups|album)/[^/]+/)?(?Pplay_redirect_hls\?clip_id=)?(?:videos?/)?(?P[0-9]+)' + _VALID_URL = r'(?Phttps?://)?(?:(?:www|player)\.)?vimeo(?Ppro)?\.com/(?:(?:(?:groups|album)/[^/]+)|(?:.*?)/)?(?Pplay_redirect_hls\?clip_id=)?(?:videos?/)?(?P[0-9]+)' IE_NAME = u'vimeo' def _real_extract(self, url, new_video=True): @@ -1072,7 +1072,7 @@ class VimeoIE(InfoExtractor): video_id = mobj.group('id') if not mobj.group('proto'): url = 'https://' + url - if mobj.group('direct_link'): + if mobj.group('direct_link') or mobj.group('pro'): url = 'https://vimeo.com/' + video_id # Retrieve video webpage to extract further information @@ -1424,7 +1424,6 @@ class YoutubeSearchIE(SearchInfoExtractor): def report_download_page(self, query, pagenum): """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)) def _get_n_results(self, query, n): @@ -3980,7 +3979,7 @@ class SpiegelIE(InfoExtractor): video_id = m.group('videoID') webpage = self._download_webpage(url, video_id) - m = re.search(r'
(.*?)
', webpage) + m = re.search(r'
(.*?)
', webpage) if not m: raise ExtractorError(u'Cannot find title') video_title = unescapeHTML(m.group(1)) @@ -4091,6 +4090,64 @@ class ARDIE(InfoExtractor): info["url"] = stream["video_url"] return [info] +class ZDFIE(InfoExtractor): + _VALID_URL = r'^http://www\.zdf\.de\/ZDFmediathek\/(.*beitrag\/video\/)(?P[^/\?]+)(?:\?.*)?' + _TITLE = r'(?P.*)</h1>' + _MEDIA_STREAM = r'<a href="(?P<video_url>.+(?P<media_type>.streaming).+/zdf/(?P<quality>[^\/]+)/[^"]*)".+class="play".+>' + _MMS_STREAM = r'href="(?P<video_url>mms://[^"]*)"' + _RTSP_STREAM = r'(?P<video_url>rtsp://[^"]*.mp4)' + + 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') + + html = self._download_webpage(url, video_id) + streams = [m.groupdict() for m in re.finditer(self._MEDIA_STREAM, html)] + if streams is None: + raise ExtractorError(u'No media url found.') + + # s['media_type'] == 'wstreaming' -> use 'Windows Media Player' and mms url + # s['media_type'] == 'hstreaming' -> use 'Quicktime' and rtsp url + # choose first/default media type and highest quality for now + for s in streams: #find 300 - dsl1000mbit + if s['quality'] == '300' and s['media_type'] == 'wstreaming': + stream_=s + break + for s in streams: #find veryhigh - dsl2000mbit + if s['quality'] == 'veryhigh' and s['media_type'] == 'wstreaming': # 'hstreaming' - rtsp is not working + stream_=s + break + if stream_ is None: + raise ExtractorError(u'No stream found.') + + media_link = self._download_webpage(stream_['video_url'], video_id,'Get stream URL') + + self.report_extraction(video_id) + mobj = re.search(self._TITLE, html) + if mobj is None: + raise ExtractorError(u'Cannot extract title') + title = unescapeHTML(mobj.group('title')) + + mobj = re.search(self._MMS_STREAM, media_link) + if mobj is None: + mobj = re.search(self._RTSP_STREAM, media_link) + if mobj is None: + raise ExtractorError(u'Cannot extract mms:// or rtsp:// URL') + mms_url = mobj.group('video_url') + + mobj = re.search('(.*)[.](?P<ext>[^.]+)', mms_url) + if mobj is None: + raise ExtractorError(u'Cannot extract extention') + ext = mobj.group('ext') + + return [{'id': video_id, + 'url': mms_url, + 'title': title, + 'ext': ext + }] + class TumblrIE(InfoExtractor): _VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/((post)|(video))/(?P<id>\d*)/(.*?)' @@ -4425,6 +4482,149 @@ class TeamcocoIE(InfoExtractor): 'thumbnail': thumbnail, 'description': description, }] + +class XHamsterIE(InfoExtractor): + """Information Extractor for xHamster""" + _VALID_URL = r'(?:http://)?(?:www.)?xhamster\.com/movies/(?P<id>[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<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', 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] + + mobj = re.search(r'<title>(?P<title>.+?) - xHamster\.com', webpage) + if mobj is None: + raise ExtractorError(u'Unable to extract title') + video_title = unescapeHTML(mobj.group('title')) + + mobj = re.search(r'Description: (?P[^<]+)', webpage) + if mobj is None: + video_description = u'' + else: + video_description = unescapeHTML(mobj.group('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 is None: + raise ExtractorError(u'Unable to extract upload date') + video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d') + + mobj = re.search(r']+>(?P[^>]+)', webpage) + if mobj is None: + video_uploader_id = u'anonymous' + else: + video_uploader_id = mobj.group('uploader_id') + + mobj = re.search(r'\'image\':\'(?P[^\']+)\'', webpage) + if mobj is None: + raise ExtractorError(u'Unable to extract thumbnail URL') + video_thumbnail = mobj.group('thumbnail') + + 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) + mobj = re.search(r'', response, flags=re.MULTILINE|re.DOTALL) + if mobj is None: + raise ExtractorError(u'Unable to extrack tracks') + html_tracks = mobj.group(1).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) + redirect_url = urlh.geturl() + re.search(r'window\.location = \'(.*)\';', redirect_page).group(1) + webpage = self._download_webpage(redirect_url, video_id, u'Downloading redirect page') + + title = re.search(r'(.*)', webpage) + title = (title.group(1)).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. @@ -4479,6 +4679,7 @@ def gen_extractors(): SpiegelIE(), LiveLeakIE(), ARDIE(), + ZDFIE(), TumblrIE(), BandcampIE(), RedTubeIE(), @@ -4487,6 +4688,9 @@ def gen_extractors(): VineIE(), FlickrIE(), TeamcocoIE(), + XHamsterIE(), + HypemIE(), + Vbox7IE(), GenericIE() ]