debian/NEWS: Write news about new behavior of youtube-dl.

[youtubedl] / youtube_dl / extractor / dailymotion.py

diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py
index 71f5e03eea393b7733bf3bfeb4f2eeea5b21eb85..6685c94a3d6b283e0b7f2240ebfcf35ce462edc2 100644 (file)
--- a/youtube_dl/extractor/dailymotion.py
+++ b/youtube_dl/extractor/dailymotion.py
@@ -11,6 +11,7 @@ from ..utils import (
     get_element_by_attribute,
     get_element_by_id,
     orderedSet,
     get_element_by_attribute,
     get_element_by_id,
     orderedSet,

+    str_to_int,

 
     ExtractorError,
 )
 
     ExtractorError,
 )


@@ -27,7 +28,7 @@ class DailymotionBaseInfoExtractor(InfoExtractor):
 class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
     """Information Extractor for Dailymotion"""
 
 class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
     """Information Extractor for Dailymotion"""
 

-    _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/(?:embed/)?video/([^/]+)'
+    _VALID_URL = r'(?i)(?:https?://)?(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(embed|#)/)?video/(?P<id>[^/?_]+)'

     IE_NAME = u'dailymotion'
 
     _FORMATS = [
     IE_NAME = u'dailymotion'
 
     _FORMATS = [


@@ -80,7 +81,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
         # Extract id and simplified title from URL
         mobj = re.match(self._VALID_URL, url)
 
         # Extract id and simplified title from URL
         mobj = re.match(self._VALID_URL, url)
 

-        video_id = mobj.group(1).split('_')[0].split('?')[0]
+        video_id = mobj.group('id')

 
         url = 'http://www.dailymotion.com/video/%s' % video_id
 
 
         url = 'http://www.dailymotion.com/video/%s' % video_id
 


@@ -100,10 +101,6 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
             self.to_screen(u'Vevo video detected: %s' % vevo_id)
             return self.url_result(u'vevo:%s' % vevo_id, ie='Vevo')
 
             self.to_screen(u'Vevo video detected: %s' % vevo_id)
             return self.url_result(u'vevo:%s' % vevo_id, ie='Vevo')
 

-        video_uploader = self._search_regex([r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>',
-                                             # Looking for official user
-                                             r'<(?:span|a) .*?rel="author".*?>([^<]+?)</'],
-                                            webpage, 'video uploader', fatal=False)

         age_limit = self._rta_search(webpage)
 
         video_upload_date = None
         age_limit = self._rta_search(webpage)
 
         video_upload_date = None


@@ -146,15 +143,21 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
             self._list_available_subtitles(video_id, webpage)
             return
 
             self._list_available_subtitles(video_id, webpage)
             return
 

+        view_count = self._search_regex(
+            r'video_views_count[^>]+>\s+([\d\.,]+)', webpage, u'view count', fatal=False)
+        if view_count is not None:
+            view_count = str_to_int(view_count)
+

         return {
             'id':       video_id,
             'formats': formats,
         return {
             'id':       video_id,
             'formats': formats,

-            'uploader': video_uploader,
+            'uploader': info['owner_screenname'],

             'upload_date':  video_upload_date,
             'title':    self._og_search_title(webpage),
             'subtitles':    video_subtitles,
             'thumbnail': info['thumbnail_url'],
             'age_limit': age_limit,
             'upload_date':  video_upload_date,
             'title':    self._og_search_title(webpage),
             'subtitles':    video_subtitles,
             'thumbnail': info['thumbnail_url'],
             'age_limit': age_limit,

+            'view_count': view_count,

         }
 
     def _get_available_subtitles(self, video_id, webpage):
         }
 
     def _get_available_subtitles(self, video_id, webpage):