X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube_dl%2FInfoExtractors.py;h=282334635079560723bf38562abae0032bf15b96;hb=f380401bbd1f41e00bc2d75a1354aed64bb18c30;hp=105f90e2f1ee849a5e067b7af74908884f0d6af8;hpb=157b864a0122a87b322e8448ff974d3f4917ed21;p=youtube-dl.git diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 105f90e2f..282334635 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -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): @@ -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*)/(.*?)' @@ -4487,54 +4544,87 @@ class HypemIE(InfoExtractor): """Information Extractor for hypem""" _VALID_URL = r'(?:http://)?(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)' - def _real_extract(self,url): + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) if mobj is None: raise ExtractorError(u'Invalid URL: %s' % url) - data = {'ax':1 , - 'ts': time.time() - } - id = mobj.group(1) + track_id = mobj.group(1) + + data = { 'ax': 1, 'ts': time.time() } data_encoded = compat_urllib_parse.urlencode(data) - complete_url = url + "?"+data_encoded + complete_url = url + "?" + data_encoded request = compat_urllib_request.Request(complete_url) - response,urlh = self._download_webpage_handle(request, id, u'Downloading webpage with the url') + response, urlh = self._download_webpage_handle(request, track_id, u'Downloading webpage with the url') cookie = urlh.headers.get('Set-Cookie', '') - track_list = [] - list_data = re.search(r'<script type="application/json" id="displayList-data">\n (.*) </script>',response) - html_tracks = list_data.group(1) - if html_tracks is None: - tracks = track_list + + self.report_extraction(track_id) + mobj = re.search(r'<script type="application/json" id="displayList-data">(.*?)</script>', 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) - tracks = track_list[u'tracks'] + track = track_list[u'tracks'][0] except ValueError: - self.to_screen("Hypemachine contained invalid JSON.") - tracks = track_list - - for track in tracks: - key = track[u"key"] - id = track[u"id"] - artist = track[u"artist"] - title = track[u"song"] - serve_url = "http://hypem.com/serve/source/%s/%s"%(str(id), str(key)) - self.report_extraction(id) + 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) - response = compat_urllib_request.urlopen(request) - song_data_json = response.read() - response.close() - (song_data_json, response) = self._download_webpage_handle(request, id, u'Downloading webpage with the url') - song_data = json.loads(song_data_json) + 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': id, + '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'<title>(.*)', 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. @@ -4589,6 +4679,7 @@ def gen_extractors(): SpiegelIE(), LiveLeakIE(), ARDIE(), + ZDFIE(), TumblrIE(), BandcampIE(), RedTubeIE(), @@ -4599,6 +4690,7 @@ def gen_extractors(): TeamcocoIE(), XHamsterIE(), HypemIE(), + Vbox7IE(), GenericIE() ]