Merge tag 'upstream/2014.01.17.2'

[youtubedl] / youtube_dl / extractor / cspan.py

diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py
index 2246515f2a9205da9a329a78343b759e460bf3df..a2cbd4d8d592fd2dd6899361a3ab8f4bb3b8a8ed 100644 (file)
--- a/youtube_dl/extractor/cspan.py
+++ b/youtube_dl/extractor/cspan.py
@@ -1,44 +1,48 @@
+from __future__ import unicode_literals
+
+import json

 import re
 
 from .common import InfoExtractor
 from ..utils import (
 import re
 
 from .common import InfoExtractor
 from ..utils import (

-    compat_urllib_parse,
+    unescapeHTML,

 )
 
 )
 

+

 class CSpanIE(InfoExtractor):
 class CSpanIE(InfoExtractor):

-    _VALID_URL = r'http://www.c-spanvideo.org/program/(.*)'
+    _VALID_URL = r'http://www\.c-spanvideo\.org/program/(.*)'
+    IE_DESC = 'C-SPAN'
+    _TEST = {
+        'url': 'http://www.c-spanvideo.org/program/HolderonV',
+        'file': '315139.mp4',
+        'md5': '8e44ce11f0f725527daccc453f553eb0',
+        'info_dict': {
+            'title': 'Attorney General Eric Holder on Voting Rights Act Decision',
+            'description': 'Attorney General Eric Holder spoke to reporters following the Supreme Court decision in [Shelby County v. Holder] in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced until Congress established new guidelines for review.',
+        },
+    }

 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         prog_name = mobj.group(1)
         webpage = self._download_webpage(url, prog_name)
         video_id = self._search_regex(r'programid=(.*?)&', webpage, 'video id')
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         prog_name = mobj.group(1)
         webpage = self._download_webpage(url, prog_name)
         video_id = self._search_regex(r'programid=(.*?)&', webpage, 'video id')

-        data = compat_urllib_parse.urlencode({'programid': video_id,
-                                              'dynamic':'1'})
-        info_url = 'http://www.c-spanvideo.org/common/services/flashXml.php?' + data
-        video_info = self._download_webpage(info_url, video_id, u'Downloading video info')
-
-        self.report_extraction(video_id)
-
-        title = self._html_search_regex(r'<string name="title">(.*?)</string>',
-                                        video_info, 'title')
-        description = self._html_search_regex(r'<meta (?:property="og:|name=")description" content="(.*?)"',
-                                              webpage, 'description',
-                                              flags=re.MULTILINE|re.DOTALL)
-        thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.*?)"',
-                                            webpage, 'thumbnail')
-
-        url = self._search_regex(r'<string name="URL">(.*?)</string>',
-                                 video_info, 'video url')
-        url = url.replace('$(protocol)', 'rtmp').replace('$(port)', '443')
-        path = self._search_regex(r'<string name="path">(.*?)</string>',
-                            video_info, 'rtmp play path')
-
-        return {'id': video_id,
-                'title': title,
-                'ext': 'flv',
-                'url': url,
-                'play_path': path,
-                'description': description,
-                'thumbnail': thumbnail,
-                }
+
+        title = self._html_search_regex(
+            r'<!-- title -->\n\s*<h1[^>]*>(.*?)</h1>', webpage, 'title')
+        description = self._og_search_description(webpage)
+
+        info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id
+        data_json = self._download_webpage(
+            info_url, video_id, 'Downloading video info')
+        data = json.loads(data_json)
+
+        url = unescapeHTML(data['video']['files'][0]['path']['#text'])
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': url,
+            'description': description,
+            'thumbnail': self._og_search_thumbnail(webpage),
+        }