Merge pull request #7045 from remitamine/ign

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

diff --git a/youtube_dl/extractor/franceinter.py b/youtube_dl/extractor/franceinter.py
index 932a1f161794a8b89487e2d7483f651c0c3b1551..fdc51f44fe3fde67f5d9d847994fb94ab383a3e1 100644 (file)
--- a/youtube_dl/extractor/franceinter.py
+++ b/youtube_dl/extractor/franceinter.py
@@ -1,31 +1,49 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
+from ..utils import int_or_none
+
+
 class FranceInterIE(InfoExtractor):
-    
-    _VALID_URL=r'http://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]{6})'
-    _TEST={
-           u'url':u'http://www.franceinter.fr/player/reecouter?play=793962',
-           u'file':u'793962.mp3'
-                  
-           }
-           
-   
-        
-   
-    def _real_extract(self,url):
-
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        
-        webpage=self._download_webpage(url,video_id)
-        
-        title=self._search_regex(u'(?<=<span class="roll_overflow">)(.*)(?=</span></h1>)', webpage, u'title')
-        
-        video_url='http://www.franceinter.fr/'+self._search_regex(u'(?<=&urlAOD=)(.*)(?=&startTime)', webpage, u'video url')
-        
-        return{'id': video_id,u'url': video_url,u'title': title}
-        
-        
\ No newline at end of file
+    _VALID_URL = r'http://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.franceinter.fr/player/reecouter?play=793962',
+        'md5': '4764932e466e6f6c79c317d2e74f6884',
+        "info_dict": {
+            'id': '793962',
+            'ext': 'mp3',
+            'title': 'L’Histoire dans les jeux vidéo',
+            'description': 'md5:7e93ddb4451e7530022792240a3049c7',
+            'timestamp': 1387369800,
+            'upload_date': '20131218',
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        path = self._search_regex(
+            r'<a id="player".+?href="([^"]+)"', webpage, 'video url')
+        video_url = 'http://www.franceinter.fr/' + path
+
+        title = self._html_search_regex(
+            r'<span class="title-diffusion">(.+?)</span>', webpage, 'title')
+        description = self._html_search_regex(
+            r'<span class="description">(.*?)</span>',
+            webpage, 'description', fatal=False)
+        timestamp = int_or_none(self._search_regex(
+            r'data-date="(\d+)"', webpage, 'upload date', fatal=False))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'timestamp': timestamp,
+            'formats': [{
+                'url': video_url,
+                'vcodec': 'none',
+            }],
+        }