w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[crunchyroll] Fix extraction (Closes #5855, closes #5881)

Browse source
This commit is contained in:
Sergey M․ 2015-07-05 06:29:36 +06:00
parent d7c9a3e976
commit ede21449c8
1 changed files with 24 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

31
youtube_dl/extractor/crunchyroll.py
View file

@ -27,7 +27,7 @@ from ..aes import (
class CrunchyrollIE(InfoExtractor): class CrunchyrollIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)' _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)'
_NETRC_MACHINE = 'crunchyroll' _NETRC_MACHINE = 'crunchyroll'
_TESTS = [{ _TESTS = [{
'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513', 'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
@ -45,6 +45,22 @@ class CrunchyrollIE(InfoExtractor):
# rtmp # rtmp
'skip_download': True, 'skip_download': True,
}, },
}, {
'url': 'http://www.crunchyroll.com/media-589804/culture-japan-1',
'info_dict': {
'id': '589804',
'ext': 'flv',
'title': 'Culture Japan Episode 1 – Rebuilding Japan after the 3.11',
'description': 'md5:fe2743efedb49d279552926d0bd0cd9e',
'thumbnail': 're:^https?://.*\.jpg$',
'uploader': 'Danny Choo Network',
'upload_date': '20120213',
},
'params': {
# rtmp
'skip_download': True,
},
}, { }, {
'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697', 'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
'only_matching': True, 'only_matching': True,
@ -251,16 +267,17 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
for fmt in re.findall(r'showmedia\.([0-9]{3,4})p', webpage): for fmt in re.findall(r'showmedia\.([0-9]{3,4})p', webpage):
stream_quality, stream_format = self._FORMAT_IDS[fmt] stream_quality, stream_format = self._FORMAT_IDS[fmt]
video_format = fmt + 'p' video_format = fmt + 'p'
streamdata_req = compat_urllib_request.Request('http://www.crunchyroll.com/xml/') streamdata_req = compat_urllib_request.Request(
# urlencode doesn't work! 'http://www.crunchyroll.com/xml/?req=RpcApiVideoPlayer_GetStandardConfig&media_id=%s&video_format=%s&video_quality=%s'
streamdata_req.data = 'req=RpcApiVideoEncode%5FGetStreamInfo&video%5Fencode%5Fquality=' + stream_quality + '&media%5Fid=' + stream_id + '&video%5Fformat=' + stream_format % (stream_id, stream_format, stream_quality),
compat_urllib_parse.urlencode({'current_page': url}).encode('utf-8'))
streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded') 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_xml( streamdata = self._download_xml(
streamdata_req, video_id, streamdata_req, video_id,
note='Downloading media info for %s' % video_format) note='Downloading media info for %s' % video_format)
video_url = streamdata.find('./host').text stream_info = streamdata.find('./{default}preload/stream_info')
video_play_path = streamdata.find('./file').text video_url = stream_info.find('./host').text
video_play_path = stream_info.find('./file').text
formats.append({ formats.append({
'url': video_url, 'url': video_url,
'play_path': video_play_path, 'play_path': video_play_path,