youtube-dl

commit ea1d5bdcddc4b9bdac0ef5555f080484c33467a9
parent 121c09c7be1ac2944f3432122104c1952bfd1f04
Author: Philipp Hagemeister <phihag@phihag.de>
Date:   Sat, 10 Jan 2015 17:57:21 +0100

[rte] Make more robust and add a new testcase (#4015)

Diffstat:
M
youtube_dl/extractor/rte.py
 | 
39
+++++++++++++++++++++------------------

1 file changed, 21 insertions(+), 18 deletions(-)
diff --git a/youtube_dl/extractor/rte.py b/youtube_dl/extractor/rte.py
@@ -9,34 +9,38 @@ from ..utils import (
 
 
 class RteIE(InfoExtractor):
-    _VALID_URL = r'http?://(?:www\.)?rte\.ie/player/in/show/(?P<id>[0-9]+)/'
+    _VALID_URL = r'http?://(?:www\.)?rte\.ie/player/[^/]{2,3}/show/(?P<id>[0-9]+)/'
     _TEST = {
-        'url': 'http://www.rte.ie/player/in/show/10336191/',
+        'url': 'http://www.rte.ie/player/de/show/10363114/',
         'info_dict': {
-            'id': '10336191',
+            'id': '10363114',
             'ext': 'mp4',
-            'title': 'Nine News',
+            'title': 'One News',
             'thumbnail': 're:^https?://.*\.jpg$',
             'description': 'The One O\'Clock News followed by Weather.',
-            'duration': 1622.963,
+            'duration': 436.844,
+        },
+        'params': {
+            'skip_download': 'f4m fails with --test atm'
         }
     }
     
     def _real_extract(self, url):
         video_id = self._match_id(url)
-
         webpage = self._download_webpage(url, video_id)
+
         title = self._og_search_title(webpage)
-        
-        description = self._search_regex(r'<meta name="description" content="(.*?)" />', webpage, 'description')
-        duration = float_or_none(self._html_search_meta('duration', webpage, 'duration'), 1000)
-        
-        thumbnail_id = self._search_regex(r'<meta name="thumbnail" content="uri:irus:(.*?)" />', webpage, 'thumbnail')
-        thumbnail = 'http://img.rasset.ie/' + thumbnail_id + '.jpg' 
-        
+        description = self._html_search_meta('description', webpage, 'description')
+        duration = float_or_none(self._html_search_meta(
+            'duration', webpage, 'duration', fatal=False), 1000)
+
+        thumbnail_id = self._search_regex(
+            r'<meta name="thumbnail" content="uri:irus:(.*?)" />', webpage, 'thumbnail')
+        thumbnail = 'http://img.rasset.ie/' + thumbnail_id + '.jpg'
+
         feeds_url = self._html_search_meta("feeds-prefix", webpage, 'feeds url') + video_id
         json_string = self._download_json(feeds_url, video_id)
-        
+
         # f4m_url = server + relative_url
         f4m_url = json_string['shows'][0]['media:group'][0]['rte:server'] + json_string['shows'][0]['media:group'][0]['url']
         f4m_formats = self._extract_f4m_formats(f4m_url, video_id)
@@ -46,8 +50,8 @@ class RteIE(InfoExtractor):
             'ext': 'mp4',
             'width': f['width'],
             'height': f['height'],
-        } for f in f4m_formats ]
-        
+        } for f in f4m_formats]
+
         return {
             'id': video_id,
             'title': title,
@@ -55,4 +59,4 @@ class RteIE(InfoExtractor):
             'description': description,
             'thumbnail': thumbnail,
             'duration': duration,
-        }-
\ No newline at end of file
+        }