Merge pull request #8348 from remitamine/dfxp2srt-text

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

diff --git a/youtube_dl/extractor/senateisvp.py b/youtube_dl/extractor/senateisvp.py
index fa661026142842d8f8ffa0157302bfce77544455..990ea0fa8c762b21cc63fda659a050d69235721b 100644 (file)
--- a/youtube_dl/extractor/senateisvp.py
+++ b/youtube_dl/extractor/senateisvp.py
@@ -48,22 +48,30 @@ class SenateISVPIE(InfoExtractor):
         ["arch", "", "http://ussenate-f.akamaihd.net/"]
     ]
     _IE_NAME = 'senate.gov'
-    _VALID_URL = r'http://www\.senate\.gov/isvp/\?(?P<qs>.+)'
+    _VALID_URL = r'http://www\.senate\.gov/isvp/?\?(?P<qs>.+)'
     _TESTS = [{
         'url': 'http://www.senate.gov/isvp/?comm=judiciary&type=live&stt=&filename=judiciary031715&auto_play=false&wmode=transparent&poster=http%3A%2F%2Fwww.judiciary.senate.gov%2Fthemes%2Fjudiciary%2Fimages%2Fvideo-poster-flash-fit.png',
         'info_dict': {
             'id': 'judiciary031715',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Integrated Senate Video Player',
             'thumbnail': 're:^https?://.*\.(?:jpg|png)$',
-        }
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
     }, {
         'url': 'http://www.senate.gov/isvp/?type=live&comm=commerce&filename=commerce011514.mp4&auto_play=false',
         'info_dict': {
             'id': 'commerce011514',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Integrated Senate Video Player'
-        }
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
     }, {
         'url': 'http://www.senate.gov/isvp/?type=arch&comm=intel&filename=intel090613&hc_location=ufi',
         # checksum differs each time
@@ -72,12 +80,16 @@ class SenateISVPIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Integrated Senate Video Player'
         }
+    }, {
+        # From http://www.c-span.org/video/?96791-1
+        'url': 'http://www.senate.gov/isvp?type=live&comm=banking&filename=banking012715',
+        'only_matching': True,
     }]
 
     @staticmethod
     def _search_iframe_url(webpage):
         mobj = re.search(
-            r"<iframe[^>]+src=['\"](?P<url>http://www\.senate\.gov/isvp/\?[^'\"]+)['\"]",
+            r"<iframe[^>]+src=['\"](?P<url>http://www\.senate\.gov/isvp/?\?[^'\"]+)['\"]",
             webpage)
         if mobj:
             return mobj.group('url')
@@ -117,9 +129,9 @@ class SenateISVPIE(InfoExtractor):
                 'url': compat_urlparse.urljoin(domain, filename) + '?v=3.1.0&fp=&r=&g=',
             }]
         else:
-            hdcore_sign = '?hdcore=3.1.0'
+            hdcore_sign = 'hdcore=3.1.0'
             url_params = (domain, video_id, stream_num)
-            f4m_url = '%s/z/%s_1@%s/manifest.f4m' % url_params + hdcore_sign
+            f4m_url = '%s/z/%s_1@%s/manifest.f4m?' % url_params + hdcore_sign
             m3u8_url = '%s/i/%s_1@%s/master.m3u8' % url_params
             for entry in self._extract_f4m_formats(f4m_url, video_id, f4m_id='f4m'):
                 # URLs without the extra param induce an 404 error
@@ -133,15 +145,9 @@ class SenateISVPIE(InfoExtractor):
 
             self._sort_formats(formats)
 
-        info_dict = {
+        return {
             'id': video_id,
             'title': title,
+            'formats': formats,
             'thumbnail': thumbnail,
         }
-
-        if len(formats) >= 1:
-            info_dict.update({'formats': formats})
-        else:
-            info_dict.update(formats[0])
-
-        return info_dict