diff options
author | Philipp Hagemeister <phihag@phihag.de> | 2014-10-26 17:06:35 +0100 |
---|---|---|
committer | Philipp Hagemeister <phihag@phihag.de> | 2014-10-26 17:06:35 +0100 |
commit | 274b12b5a8229242cd750fa95205ab63621c2c40 (patch) | |
tree | 2390cb92083cd2997a1c7d2f9e90e68224592880 /youtube_dl/extractor/crunchyroll.py | |
parent | 23be51d8ce132dbb967f460e1225fdaaa43dff39 (diff) | |
parent | 1b10a011ec7544f49159ed60642128720333b8aa (diff) |
Merge remote-tracking branch 'gabeos/crunchyroll-show-playlist'
Diffstat (limited to 'youtube_dl/extractor/crunchyroll.py')
-rw-r--r-- | youtube_dl/extractor/crunchyroll.py | 36 |
1 files changed, 36 insertions, 0 deletions
diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index e3057d900..2dca52660 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -24,6 +24,7 @@ from ..aes import ( aes_cbc_decrypt, inc, ) +from .common import InfoExtractor class CrunchyrollIE(SubtitlesInfoExtractor): @@ -288,3 +289,38 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text 'subtitles': subtitles, 'formats': formats, } + + +class CrunchyrollShowPlaylistIE(InfoExtractor): + IE_NAME = "crunchyroll:playlist" + _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P<show>[\w\-]+))/?$' + _TITLE_EXTR = r'<span\s+itemprop="name">\s*(?P<showtitle>[\w\s]+)' + + _TESTS = [{ + 'url' : 'http://www.crunchyroll.com/attack-on-titan', + 'info_dict' : { + 'title' : 'Attack on Titan' + }, + 'playlist_count' : 15 + }] + + def _extract_title_entries(self,id,webpage): + _EPISODE_ID_EXTR = r'id="showview_videos_media_(?P<vidid>\d+)".*?href="/{0}/(?P<vidurl>[\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) + return { + '_type' : 'playlist', + 'id' : show_id, + 'title' : title, + 'entries' : entries + }
\ No newline at end of file |