youtube-dl

commit 2ecbd2ad6fa8bb2d623b8c15e7aaa000a0feb28a
parent 62a0b86e4f1aa3f0b4debdd4939c14f8fb8b5bef
Author: Yen Chi Hsuan <yan12125@gmail.com>
Date:   Sat, 15 Oct 2016 00:01:46 +0800

[chirbit:profile] Fix extraction

Diffstat:
M
ChangeLog
 | 
1
+
M
youtube_dl/extractor/chirbit.py
 | 
13
+++++--------

2 files changed, 6 insertions(+), 8 deletions(-)
diff --git a/ChangeLog b/ChangeLog
@@ -1,6 +1,7 @@
 version <unreleased>
 
 Extractors
+* [chirbit] Fix extraction of user profile pages
 * [charambatv] Fix extraction
 * [canalplus] Fix extraction for some videos
 * [cbsinteractive] Fix extraction for cnet.com
diff --git a/youtube_dl/extractor/chirbit.py b/youtube_dl/extractor/chirbit.py
@@ -2,6 +2,7 @@
 from __future__ import unicode_literals
 
 import base64
+import re
 
 from .common import InfoExtractor
 from ..utils import parse_duration
@@ -70,7 +71,6 @@ class ChirbitProfileIE(InfoExtractor):
         'url': 'http://chirbit.com/ScarletBeauty',
         'info_dict': {
             'id': 'ScarletBeauty',
-            'title': 'Chirbits by ScarletBeauty',
         },
         'playlist_mincount': 3,
     }
@@ -78,13 +78,10 @@ class ChirbitProfileIE(InfoExtractor):
     def _real_extract(self, url):
         profile_id = self._match_id(url)
 
-        rss = self._download_xml(
-            'http://chirbit.com/rss/%s' % profile_id, profile_id)
+        webpage = self._download_webpage(url, profile_id)
 
         entries = [
-            self.url_result(audio_url.text, 'Chirbit')
-            for audio_url in rss.findall('./channel/item/link')]
+            self.url_result(self._proto_relative_url('//chirb.it/' + video_id))
+            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, title)
+        return self.playlist_result(entries, profile_id)