ArteTVDDCIE,
ArteTVEmbedIE,
)
+from .audiomack import AudiomackIE
from .auengine import AUEngineIE
from .bambuser import BambuserIE, BambuserChannelIE
from .bandcamp import BandcampIE, BandcampAlbumIE
from .bbccouk import BBCCoUkIE
from .beeg import BeegIE
from .behindkink import BehindKinkIE
+from .bild import BildIE
from .bilibili import BiliBiliIE
from .blinkx import BlinkxIE
from .bliptv import BlipTVIE, BlipTVUserIE
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 (
from .gametrailers import GametrailersIE
from .gdcvault import GDCVaultIE
from .generic import GenericIE
+from .glide import GlideIE
from .globo import GloboIE
from .godtube import GodTubeIE
from .golem import GolemIE
from .teamcoco import TeamcocoIE
from .techtalks import TechTalksIE
from .ted import TEDIE
+from .telecinco import TelecincoIE
from .telemb import TeleMBIE
from .tenplay import TenPlayIE
from .testurl import TestURLIE
from .videott import VideoTtIE
from .videoweed import VideoWeedIE
from .vidme import VidmeIE
+from .vidzi import VidziIE
from .vimeo import (
VimeoIE,
VimeoAlbumIE,
from .vk import VKIE
from .vodlocker import VodlockerIE
from .vporn import VpornIE
+from .vrt import VRTIE
from .vube import VubeIE
from .vuclip import VuClipIE
from .vulture import VultureIE
YoutubeUserIE,
YoutubeWatchLaterIE,
)
-
from .zdf import ZDFIE
-
_ALL_CLASSES = [
klass
for name, klass in globals().items()
aes_cbc_decrypt,
inc,
)
+ from .common import InfoExtractor
class CrunchyrollIE(SubtitlesInfoExtractor):
'thumbnail': 'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg',
'uploader': 'Yomiuri Telecasting Corporation (YTV)',
'upload_date': '20131013',
+ 'url': 're:(?!.*&)',
},
'params': {
# rtmp
streamdata_req.data = 'req=RpcApiVideoEncode%5FGetStreamInfo&video%5Fencode%5Fquality='+stream_quality+'&media%5Fid='+stream_id+'&video%5Fformat='+stream_format
streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
streamdata_req.add_header('Content-Length', str(len(streamdata_req.data)))
- streamdata = self._download_webpage(streamdata_req, video_id, note='Downloading media info for '+video_format)
- video_url = self._search_regex(r'<host>([^<]+)', streamdata, 'video_url')
- video_play_path = self._search_regex(r'<file>([^<]+)', streamdata, 'video_play_path')
+ streamdata = self._download_xml(
+ streamdata_req, video_id,
+ note='Downloading media info for %s' % video_format)
+ video_url = streamdata.find('.//host').text
+ video_play_path = streamdata.find('.//file').text
formats.append({
'url': video_url,
- 'play_path': video_play_path,
+ 'play_path': video_play_path,
'ext': 'flv',
'format': video_format,
'format_id': video_format,
'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
+ }