From: Philipp Hagemeister Date: Sun, 26 Oct 2014 16:28:09 +0000 (+0100) Subject: [crunchyroll:playlist] Simplify (#3988) X-Git-Url: http://git.oshgnacknak.de/?a=commitdiff_plain;h=09e5d6a6e564ecaa44a174456882bd1998eacbf8;p=youtube-dl [crunchyroll:playlist] Simplify (#3988) --- diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 2dca52660..05b21e872 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -293,34 +293,36 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text class CrunchyrollShowPlaylistIE(InfoExtractor): IE_NAME = "crunchyroll:playlist" - _VALID_URL = r'https?://(?:(?Pwww|m)\.)?(?Pcrunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P[\w\-]+))/?$' - _TITLE_EXTR = r'\s*(?P[\w\s]+)' + _VALID_URL = r'https?://(?:(?Pwww|m)\.)?(?Pcrunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P[\w\-]+))/?$' _TESTS = [{ - 'url' : 'http://www.crunchyroll.com/attack-on-titan', - 'info_dict' : { - 'title' : 'Attack on Titan' + 'url': 'http://www.crunchyroll.com/a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi', + 'info_dict': { + 'id': 'a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi', + 'title': 'A Bridge to the Starry Skies - Hoshizora e Kakaru Hashi' }, - 'playlist_count' : 15 + 'playlist_count': 13, }] - def _extract_title_entries(self,id,webpage): - _EPISODE_ID_EXTR = r'id="showview_videos_media_(?P\d+)".*?href="/{0}/(?P[\w\-]+-(?P=vidid))"'.format(id) - title = self._html_search_regex(self._TITLE_EXTR,webpage,"title",flags=re.UNICODE|re.MULTILINE) - episode_urls = [self.url_result('http://www.crunchyroll.com/{0}/{1}'.format(id, showmatch[1])) for - showmatch in re.findall(_EPISODE_ID_EXTR, webpage,re.UNICODE|re.MULTILINE|re.DOTALL)] - episode_urls.reverse() - return title, episode_urls - - def _real_extract(self, url): - url_match = re.match(self._VALID_URL,url) - show_id = url_match.group('show') - webpage = self._download_webpage(url,show_id) - (title,entries) = self._extract_title_entries(show_id,webpage) + show_id = self._match_id(url) + + webpage = self._download_webpage(url, show_id) + title = self._html_search_regex( + r'(?s)]*>\s*(.*?)', + webpage, 'title') + episode_paths = re.findall( + r'(?s)
  • ]+>.*?