paradizelost/youtube-dl
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[chirbit:profile] Fix extraction

Browse Source
This commit is contained in:
Yen Chi Hsuan 2016-10-15 00:01:46 +08:00
parent 62a0b86e4f
commit 2ecbd2ad6f
No known key found for this signature in database
GPG Key ID: 3FDDD575826C5C30
2 changed files with 6 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
ChangeLog
View File

@ -1,6 +1,7 @@
version <unreleased> version <unreleased>
Extractors Extractors
* [chirbit] Fix extraction of user profile pages
* [charambatv] Fix extraction * [charambatv] Fix extraction
* [canalplus] Fix extraction for some videos * [canalplus] Fix extraction for some videos
* [cbsinteractive] Fix extraction for cnet.com * [cbsinteractive] Fix extraction for cnet.com

13
youtube_dl/extractor/chirbit.py
View File

@ -2,6 +2,7 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import base64 import base64
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import parse_duration from ..utils import parse_duration
@ -70,7 +71,6 @@ class ChirbitProfileIE(InfoExtractor):
'url': 'http://chirbit.com/ScarletBeauty', 'url': 'http://chirbit.com/ScarletBeauty',
'info_dict': { 'info_dict': {
'id': 'ScarletBeauty', 'id': 'ScarletBeauty',
'title': 'Chirbits by ScarletBeauty',
}, },
'playlist_mincount': 3, 'playlist_mincount': 3,
} }
@ -78,13 +78,10 @@ class ChirbitProfileIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
profile_id = self._match_id(url) profile_id = self._match_id(url)
rss = self._download_xml( webpage = self._download_webpage(url, profile_id)
'http://chirbit.com/rss/%s' % profile_id, profile_id)
entries = [ entries = [
self.url_result(audio_url.text, 'Chirbit') self.url_result(self._proto_relative_url('//chirb.it/' + video_id))
for audio_url in rss.findall('./channel/item/link')] for _, video_id in re.findall(r'<input[^>]+id=([\'"])copy-btn-(?P<id>[0-9a-zA-Z]+)\1', webpage)]
title = rss.find('./channel/title').text return self.playlist_result(entries, profile_id)
return self.playlist_result(entries, profile_id, title)