Merge tag 'upstream/2016.08.17'

[youtubedl] / youtube_dl / extractor / clipsyndicate.py

diff --git a/youtube_dl/extractor/clipsyndicate.py b/youtube_dl/extractor/clipsyndicate.py
index d4fc869732a8ae15e60f0963ef3418abac1a9201..0b6ad895fd7841e70b7dc0dd136052ff0459dd3c 100644 (file)
--- a/youtube_dl/extractor/clipsyndicate.py
+++ b/youtube_dl/extractor/clipsyndicate.py
@@ -1,43 +1,45 @@
-import re
-import xml.etree.ElementTree
+from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
     find_xpath_attr,
+    fix_xml_ampersands
 )
 
 
 class ClipsyndicateIE(InfoExtractor):
-    _VALID_URL = r'http://www\.clipsyndicate\.com/video/play(list/\d+)?/(?P<id>\d+)'
-
-    _TEST = {
-        u'url': u'http://www.clipsyndicate.com/video/play/4629301/brick_briscoe',
-        u'md5': u'4d7d549451bad625e0ff3d7bd56d776c',
-        u'info_dict': {
-            u'id': u'4629301',
-            u'ext': u'mp4',
-            u'title': u'Brick Briscoe',
-            u'duration': 612,
+    _VALID_URL = r'https?://(?:chic|www)\.clipsyndicate\.com/video/play(list/\d+)?/(?P<id>\d+)'
+
+    _TESTS = [{
+        'url': 'http://www.clipsyndicate.com/video/play/4629301/brick_briscoe',
+        'md5': '4d7d549451bad625e0ff3d7bd56d776c',
+        'info_dict': {
+            'id': '4629301',
+            'ext': 'mp4',
+            'title': 'Brick Briscoe',
+            'duration': 612,
+            'thumbnail': 're:^https?://.+\.jpg',
         },
-    }
+    }, {
+        'url': 'http://chic.clipsyndicate.com/video/play/5844117/shark_attack',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         js_player = self._download_webpage(
             'http://eplayer.clipsyndicate.com/embed/player.js?va_id=%s' % video_id,
-            video_id, u'Downlaoding player')
+            video_id, 'Downlaoding player')
         # it includes a required token
-        flvars = self._search_regex(r'flvars: "(.*?)"', js_player, u'flvars')
+        flvars = self._search_regex(r'flvars: "(.*?)"', js_player, 'flvars')
 
-        playlist_page = self._download_webpage(
+        pdoc = self._download_xml(
             'http://eplayer.clipsyndicate.com/osmf/playlist?%s' % flvars,
-            video_id, u'Downloading video info') 
-        # Fix broken xml
-        playlist_page = re.sub('&', '&amp;', playlist_page)
-        pdoc = xml.etree.ElementTree.fromstring(playlist_page.encode('utf-8'))
+            video_id, 'Downloading video info',
+            transform_source=fix_xml_ampersands)
 
         track_doc = pdoc.find('trackList/track')
+
         def find_param(name):
             node = find_xpath_attr(track_doc, './/param', 'name', name)
             if node is not None: