Added extractor for crunchyroll 'playlists' i.e. series. so that one can, e.g. download all episodes of a series

This commit is contained in:
Gabriel Schubiner 2014-10-19 22:47:05 -07:00
parent cc98a3f096
commit 8230018c20
2 changed files with 39 additions and 1 deletions

View file

@ -60,7 +60,10 @@
from .condenast import CondeNastIE
from .cracked import CrackedIE
from .criterion import CriterionIE
from .crunchyroll import CrunchyrollIE
from .crunchyroll import (
CrunchyrollIE,
CrunchyrollShowPlaylistIE
)
from .cspan import CSpanIE
from .d8 import D8IE
from .dailymotion import (

View file

@ -24,6 +24,7 @@
aes_cbc_decrypt,
inc,
)
from .common import InfoExtractor
class CrunchyrollIE(SubtitlesInfoExtractor):
@ -285,3 +286,37 @@ def _real_extract(self,url):
'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)]
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
}