[CSpan] Add detection for Senate ISVP. Closes #5302

[youtube-dl] / youtube_dl / extractor / cspan.py

diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py
index d65046f588d0bf4481ec6f8d8de7e031e6bdb2f9..7377ac7b9a143c0587c5a715e0e89c99f1c5480b 100644 (file)
--- a/youtube_dl/extractor/cspan.py
+++ b/youtube_dl/extractor/cspan.py
@@ -4,15 +4,18 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    int_or_none,
     unescapeHTML,
     find_xpath_attr,
+    smuggle_url,
 )
+from .senateisvp import SenateISVPIE
 
 
 class CSpanIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?c-span\.org/video/\?(?P<id>\d+)'
+    _VALID_URL = r'http://(?:www\.)?c-span\.org/video/\?(?P<id>[0-9a-f]+)'
     IE_DESC = 'C-SPAN'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.c-span.org/video/?313572-1/HolderonV',
         'md5': '8e44ce11f0f725527daccc453f553eb0',
         'info_dict': {
@@ -22,13 +25,39 @@ class CSpanIE(InfoExtractor):
             '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.',
         },
         'skip': 'Regularly fails on travis, for unknown reasons',
-    }
+    }, {
+        'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models',
+        # For whatever reason, the served video alternates between
+        # two different ones
+        'info_dict': {
+            'id': '340723',
+            'ext': 'mp4',
+            'title': 'International Health Care Models',
+            'description': 'md5:7a985a2d595dba00af3d9c9f0783c967',
+        }
+    }, {
+        'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall',
+        'info_dict': {
+            'id': '342759',
+            'title': 'General Motors Ignition Switch Recall',
+        },
+        'playlist_duration_sum': 14855,
+    }, {
+        # Video from senate.gov
+        'url': 'http://www.c-span.org/video/?104517-1/immigration-reforms-needed-protect-skilled-american-workers',
+        'md5': '7314c4b96dad66dd8e63dc3518ceaa6f',
+        'info_dict': {
+            'id': 'judiciary031715',
+            'ext': 'flv',
+            'title': 'Immigration Reforms Needed to Protect Skilled American Workers',
+        }
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         page_id = mobj.group('id')
         webpage = self._download_webpage(url, page_id)
-        video_id = self._search_regex(r'data-progid=\'(\d+)\'>', webpage, 'video id')
+        video_id = self._search_regex(r'progid=\'?([0-9]+)\'?>', webpage, 'video id')
 
         description = self._html_search_regex(
             [
@@ -38,23 +67,39 @@ class CSpanIE(InfoExtractor):
                 # present, otherwise this is a stripped version
                 r'<p class=\'initial\'>(.*?)</p>'
             ],
-            webpage, 'description', flags=re.DOTALL)
+            webpage, 'description', flags=re.DOTALL, default=None)
 
         info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id
         data = self._download_json(info_url, video_id)
 
-        url = unescapeHTML(data['video']['files'][0]['path']['#text'])
-
-        doc = self._download_xml('http://www.c-span.org/common/services/flashXml.php?programid=' + video_id,
+        doc = self._download_xml(
+            'http://www.c-span.org/common/services/flashXml.php?programid=' + video_id,
             video_id)
 
-        def find_string(s):
-            return find_xpath_attr(doc, './/string', 'name', s).text
+        title = find_xpath_attr(doc, './/string', 'name', 'title').text
+        thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text
+
+        senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
+        if senate_isvp_url:
+            surl = smuggle_url(senate_isvp_url, {'force_title': title})
+            return self.url_result(surl, 'SenateISVP', video_id, title)
+
+        files = data['video']['files']
+
+        entries = [{
+            'id': '%s_%d' % (video_id, partnum + 1),
+            'title': (
+                title if len(files) == 1 else
+                '%s part %d' % (title, partnum + 1)),
+            'url': unescapeHTML(f['path']['#text']),
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': int_or_none(f.get('length', {}).get('#text')),
+        } for partnum, f in enumerate(files)]
 
         return {
+            '_type': 'playlist',
+            'entries': entries,
+            'title': title,
             'id': video_id,
-            'title': find_string('title'),
-            'url': url,
-            'description': description,
-            'thumbnail': find_string('poster'),
         }