From: Sergey M․ <dstftw@gmail.com>
Date: Sun, 11 Oct 2015 14:35:22 +0000 (+0600)
Subject: [chaturbate] Improve and capture error message
X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=commitdiff_plain;h=0f61db4469db4c17712b8a3f9e527e845ec96ed4;p=youtube-dl

[chaturbate] Improve and capture error message
---

diff --git a/youtube_dl/extractor/chaturbate.py b/youtube_dl/extractor/chaturbate.py
index 5e24e1e4f..0b67ba67d 100644
--- a/youtube_dl/extractor/chaturbate.py
+++ b/youtube_dl/extractor/chaturbate.py
@@ -1,24 +1,50 @@
-# encoding: utf-8
+from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..utils import ExtractorError
 
 
 class ChaturbateIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?chaturbate\.com/(?P<id>[^/]+)/?$'
+    _VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?P<id>[^/?#]+)'
+    _TESTS = [{
+        'url': 'https://www.chaturbate.com/siswet19/',
+        'info_dict': {
+            'id': 'siswet19',
+            'ext': 'mp4',
+            'title': 're:^siswet19 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'age_limit': 18,
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        'url': 'https://en.chaturbate.com/siswet19/',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
+
         webpage = self._download_webpage(url, video_id)
 
-        m3u8_url = self._search_regex(r"'(https?://.*?\.m3u8)'", webpage, 'playlist')
+        m3u8_url = self._search_regex(
+            r'src=(["\'])(?P<url>http.+?\.m3u8.*?)\1', webpage,
+            'playlist', default=None, group='url')
+
+        if not m3u8_url:
+            error = self._search_regex(
+                r'<span[^>]+class=(["\'])desc_span\1[^>]*>(?P<error>[^<]+)</span>',
+                webpage, 'error', group='error')
+            raise ExtractorError(error, expected=True)
 
         formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
 
         return {
             'id': video_id,
             'title': self._live_title(video_id),
-            'description': self._html_search_meta('description', webpage, 'description'),
+            'thumbnail': 'https://cdn-s.highwebmedia.com/uHK3McUtGCG3SMFcd4ZJsRv8/roomimage/%s.jpg' % video_id,
+            'age_limit': self._rta_search(webpage),
             'is_live': True,
-            'thumbnail': 'https://cdn-s.highwebmedia.com/uHK3McUtGCG3SMFcd4ZJsRv8/roomimage/%s.jpg' % (video_id,),
             'formats': formats,
         }