Merge tag 'upstream/2016.02.22'

[youtubedl] / youtube_dl / extractor / franceinter.py

diff --git a/youtube_dl/extractor/franceinter.py b/youtube_dl/extractor/franceinter.py
index deb1b0b9dc55244874029af3c47412184c2c1e50..0388ba00c2a7ab5bfa4cf622c359c697615daec4 100644 (file)
--- a/youtube_dl/extractor/franceinter.py
+++ b/youtube_dl/extractor/franceinter.py
@@ -1,38 +1,49 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
 # coding: utf-8
 from __future__ import unicode_literals
 

-import re
-

 from .common import InfoExtractor
 from .common import InfoExtractor

+from ..utils import int_or_none

 
 
 class FranceInterIE(InfoExtractor):
 
 
 class FranceInterIE(InfoExtractor):

-    _VALID_URL = r'http://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]{6})'
+    _VALID_URL = r'http://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]+)'

     _TEST = {
         'url': 'http://www.franceinter.fr/player/reecouter?play=793962',
     _TEST = {
         'url': 'http://www.franceinter.fr/player/reecouter?play=793962',

-        'file': '793962.mp3',

         'md5': '4764932e466e6f6c79c317d2e74f6884',
         'md5': '4764932e466e6f6c79c317d2e74f6884',

-        "info_dict": {
-            "title": "L’Histoire dans les jeux vidéo",
+        '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):
         },
     }
 
     def _real_extract(self, url):

-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)

 
         webpage = self._download_webpage(url, video_id)
 
         webpage = self._download_webpage(url, video_id)

-        title = self._html_search_regex(
-            r'<span class="roll_overflow">(.*?)</span></h1>', webpage, 'title')
+

         path = self._search_regex(
         path = self._search_regex(

-            r'&urlAOD=(.*?)&startTime', webpage, 'video url')
+            r'<a id="player".+?href="([^"]+)"', webpage, 'video url')

         video_url = 'http://www.franceinter.fr/' + path
 
         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,
         return {
             'id': video_id,

+            'title': title,
+            'description': description,
+            'timestamp': timestamp,

             'formats': [{
                 'url': video_url,
                 'vcodec': 'none',
             }],
             'formats': [{
                 'url': video_url,
                 'vcodec': 'none',
             }],

-            'title': title,

         }
         }