about summary refs log tree commit diff
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2018-03-19 23:40:19 +0700
committerSergey M․ <dstftw@gmail.com>2018-03-19 23:40:19 +0700
commit38f59e2793dfcb5f493977857304ab50b784e6ee (patch)
tree7ef3d35404afa68fd029dd107b2f8c17bbdea7be
parent9a054fcbbadf06101b081f8be0594b38b654364f (diff)
downloadyoutube-dl-38f59e2793dfcb5f493977857304ab50b784e6ee.tar.gz
youtube-dl-38f59e2793dfcb5f493977857304ab50b784e6ee.tar.xz
youtube-dl-38f59e2793dfcb5f493977857304ab50b784e6ee.zip
[canalc2] Add support for HTML5 videos (closes #15916, closes #15919)
-rw-r--r--youtube_dl/extractor/canalc2.py28
1 files changed, 18 insertions, 10 deletions
diff --git a/youtube_dl/extractor/canalc2.py b/youtube_dl/extractor/canalc2.py
index acd87e371..407cc8084 100644
--- a/youtube_dl/extractor/canalc2.py
+++ b/youtube_dl/extractor/canalc2.py
@@ -31,6 +31,10 @@ class Canalc2IE(InfoExtractor):
         webpage = self._download_webpage(
             'http://www.canalc2.tv/video/%s' % video_id, video_id)
 
+        title = self._html_search_regex(
+            r'(?s)class="[^"]*col_description[^"]*">.*?<h3>(.+?)</h3>',
+            webpage, 'title')
+
         formats = []
         for _, video_url in re.findall(r'file\s*=\s*(["\'])(.+?)\1', webpage):
             if video_url.startswith('rtmp://'):
@@ -49,17 +53,21 @@ class Canalc2IE(InfoExtractor):
                     'url': video_url,
                     'format_id': 'http',
                 })
-        self._sort_formats(formats)
 
-        title = self._html_search_regex(
-            r'(?s)class="[^"]*col_description[^"]*">.*?<h3>(.*?)</h3>', webpage, 'title')
-        duration = parse_duration(self._search_regex(
-            r'id=["\']video_duree["\'][^>]*>([^<]+)',
-            webpage, 'duration', fatal=False))
+        if formats:
+            info = {
+                'formats': formats,
+            }
+        else:
+            info = self._parse_html5_media_entries(url, webpage, url)[0]
+
+        self._sort_formats(info['formats'])
 
-        return {
+        info.update({
             'id': video_id,
             'title': title,
-            'duration': duration,
-            'formats': formats,
-        }
+            'duration': parse_duration(self._search_regex(
+                r'id=["\']video_duree["\'][^>]*>([^<]+)',
+                webpage, 'duration', fatal=False)),
+        })
+        return info