From: Ismael Mejia Date: Thu, 22 Aug 2013 21:29:36 +0000 (+0200) Subject: Merge branch 'master' into subtitles_rework X-Git-Url: https://git.cielonegro.org/gitweb.cgi?a=commitdiff_plain;h=18b4e04f1c663e0ea695f6501b860f85af9d7ca1;p=youtube-dl.git Merge branch 'master' into subtitles_rework --- 18b4e04f1c663e0ea695f6501b860f85af9d7ca1 diff --cc youtube_dl/extractor/dailymotion.py index 8fab16005,fa8c630d0..f54ecc569 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@@ -82,12 -60,12 +82,12 @@@ class DailymotionIE(DailyMotionSubtitle # TODO: support choosing qualities - for key in ['stream_h264_hd1080_url', 'stream_h264_hd_url', - 'stream_h264_hq_url', 'stream_h264_url', + for key in ['stream_h264_hd1080_url','stream_h264_hd_url', + 'stream_h264_hq_url','stream_h264_url', 'stream_h264_ld_url']: - if info.get(key):#key in info and info[key]: + if info.get(key): # key in info and info[key]: max_quality = key - self.to_screen(u'Using %s' % key) + self.to_screen(u'%s: Using %s' % (video_id, key)) break else: raise ExtractorError(u'Unable to extract video URL') @@@ -113,6 -78,33 +113,34 @@@ 'upload_date': video_upload_date, 'title': self._og_search_title(webpage), 'ext': video_extension, + 'subtitles': video_subtitles, 'thumbnail': info['thumbnail_url'] }] + + + class DailymotionPlaylistIE(InfoExtractor): + _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P.+?)/' + _MORE_PAGES_INDICATOR = r'' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + playlist_id = mobj.group('id') + video_ids = [] + + for pagenum in itertools.count(1): + webpage = self._download_webpage('https://www.dailymotion.com/playlist/%s/%s' % (playlist_id, pagenum), + playlist_id, u'Downloading page %s' % pagenum) + + playlist_el = get_element_by_attribute(u'class', u'video_list', webpage) + video_ids.extend(re.findall(r'data-id="(.+?)" data-ext-id', playlist_el)) + + if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None: + break + + entries = [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion') + for video_id in video_ids] + return {'_type': 'playlist', + 'id': playlist_id, + 'title': get_element_by_id(u'playlist_name', webpage), + 'entries': entries, + }