debian/changelog: Annotate bugs to close.

[youtubedl] / youtube_dl / extractor / dailymotion.py

diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py
index 71f5e03eea393b7733bf3bfeb4f2eeea5b21eb85..70aa4333c773c39c4e3be451f8b632045ac85b51 100644 (file)
--- a/youtube_dl/extractor/dailymotion.py
+++ b/youtube_dl/extractor/dailymotion.py
@@ -1,88 +1,92 @@
+# coding: utf-8
+from __future__ import unicode_literals
+

 import re
 import json
 import itertools
 
 from .common import InfoExtractor
 import re
 import json
 import itertools
 
 from .common import InfoExtractor

-from .subtitles import SubtitlesInfoExtractor

 
 

-from ..utils import (
-    compat_urllib_request,
+from ..compat import (

     compat_str,
     compat_str,

-    get_element_by_attribute,
-    get_element_by_id,
-    orderedSet,
-
+    compat_urllib_request,
+)
+from ..utils import (

     ExtractorError,
     ExtractorError,

+    int_or_none,
+    orderedSet,
+    str_to_int,
+    unescapeHTML,

 )
 
 )
 

+

 class DailymotionBaseInfoExtractor(InfoExtractor):
     @staticmethod
     def _build_request(url):
         """Build a request with the family filter disabled"""
         request = compat_urllib_request.Request(url)
 class DailymotionBaseInfoExtractor(InfoExtractor):
     @staticmethod
     def _build_request(url):
         """Build a request with the family filter disabled"""
         request = compat_urllib_request.Request(url)

-        request.add_header('Cookie', 'family_filter=off')
-        request.add_header('Cookie', 'ff=off')
+        request.add_header('Cookie', 'family_filter=off; ff=off')

         return request
 
         return request
 

-class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
+
+class DailymotionIE(DailymotionBaseInfoExtractor):

     """Information Extractor for Dailymotion"""
 
     """Information Extractor for Dailymotion"""
 

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

 
     _FORMATS = [
 
     _FORMATS = [

-        (u'stream_h264_ld_url', u'ld'),
-        (u'stream_h264_url', u'standard'),
-        (u'stream_h264_hq_url', u'hq'),
-        (u'stream_h264_hd_url', u'hd'),
-        (u'stream_h264_hd1080_url', u'hd180'),
+        ('stream_h264_ld_url', 'ld'),
+        ('stream_h264_url', 'standard'),
+        ('stream_h264_hq_url', 'hq'),
+        ('stream_h264_hd_url', 'hd'),
+        ('stream_h264_hd1080_url', 'hd180'),

     ]
 
     _TESTS = [
         {
     ]
 
     _TESTS = [
         {

-            u'url': u'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech',
-            u'file': u'x33vw9.mp4',
-            u'md5': u'392c4b85a60a90dc4792da41ce3144eb',
-            u'info_dict': {
-                u"uploader": u"Amphora Alex and Van .", 
-                u"title": u"Tutoriel de Youtubeur\"DL DES VIDEO DE YOUTUBE\""
+            'url': 'https://www.dailymotion.com/video/x2iuewm_steam-machine-models-pricing-listed-on-steam-store-ign-news_videogames',
+            'md5': '2137c41a8e78554bb09225b8eb322406',
+            'info_dict': {
+                'id': 'x2iuewm',
+                'ext': 'mp4',
+                'uploader': 'IGN',
+                'title': 'Steam Machine Models, Pricing Listed on Steam Store - IGN News',
+                'upload_date': '20150306',

             }
         },
         # Vevo video
         {
             }
         },
         # Vevo video
         {

-            u'url': u'http://www.dailymotion.com/video/x149uew_katy-perry-roar-official_musi',
-            u'file': u'USUV71301934.mp4',
-            u'info_dict': {
-                u'title': u'Roar (Official)',
-                u'uploader': u'Katy Perry',
-                u'upload_date': u'20130905',
+            'url': 'http://www.dailymotion.com/video/x149uew_katy-perry-roar-official_musi',
+            'info_dict': {
+                'title': 'Roar (Official)',
+                'id': 'USUV71301934',
+                'ext': 'mp4',
+                'uploader': 'Katy Perry',
+                'upload_date': '20130905',

             },
             },

-            u'params': {
-                u'skip_download': True,
+            'params': {
+                'skip_download': True,

             },
             },

-            u'skip': u'VEVO is only available in some countries',
+            'skip': 'VEVO is only available in some countries',

         },
         # age-restricted video
         {
         },
         # age-restricted video
         {

-            u'url': u'http://www.dailymotion.com/video/xyh2zz_leanna-decker-cyber-girl-of-the-year-desires-nude-playboy-plus_redband',
-            u'file': u'xyh2zz.mp4',
-            u'md5': u'0d667a7b9cebecc3c89ee93099c4159d',
-            u'info_dict': {
-                u'title': 'Leanna Decker - Cyber Girl Of The Year Desires Nude [Playboy Plus]',
-                u'uploader': 'HotWaves1012',
-                u'age_limit': 18,
+            'url': 'http://www.dailymotion.com/video/xyh2zz_leanna-decker-cyber-girl-of-the-year-desires-nude-playboy-plus_redband',
+            'md5': '0d667a7b9cebecc3c89ee93099c4159d',
+            'info_dict': {
+                'id': 'xyh2zz',
+                'ext': 'mp4',
+                'title': 'Leanna Decker - Cyber Girl Of The Year Desires Nude [Playboy Plus]',
+                'uploader': 'HotWaves1012',
+                'age_limit': 18,

             }
             }

-

         }
     ]
 
     def _real_extract(self, url):
         }
     ]
 
     def _real_extract(self, url):

-        # Extract id and simplified title from URL
-        mobj = re.match(self._VALID_URL, url)
-
-        video_id = mobj.group(1).split('_')[0].split('?')[0]
-
-        url = 'http://www.dailymotion.com/video/%s' % video_id
+        video_id = self._match_id(url)
+        url = 'https://www.dailymotion.com/video/%s' % video_id

 
         # Retrieve video webpage to extract further information
         request = self._build_request(url)
 
         # Retrieve video webpage to extract further information
         request = self._build_request(url)


@@ -93,29 +97,26 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
 
         # It may just embed a vevo video:
         m_vevo = re.search(
 
         # It may just embed a vevo video:
         m_vevo = re.search(

-            r'<link rel="video_src" href="[^"]*?vevo.com[^"]*?videoId=(?P<id>[\w]*)',
+            r'<link rel="video_src" href="[^"]*?vevo.com[^"]*?video=(?P<id>[\w]*)',

             webpage)
         if m_vevo is not None:
             vevo_id = m_vevo.group('id')
             webpage)
         if m_vevo is not None:
             vevo_id = m_vevo.group('id')

-            self.to_screen(u'Vevo video detected: %s' % vevo_id)
-            return self.url_result(u'vevo:%s' % vevo_id, ie='Vevo')
+            self.to_screen('Vevo video detected: %s' % vevo_id)
+            return self.url_result('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

-        mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage)
+        mobj = re.search(r'<meta property="video:release_date" content="([0-9]{4})-([0-9]{2})-([0-9]{2}).+?"/>', webpage)

         if mobj is not None:
         if mobj is not None:

-            video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1)
+            video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3)

 
 

-        embed_url = 'http://www.dailymotion.com/embed/video/%s' % video_id
-        embed_page = self._download_webpage(embed_url, video_id,
-                                            u'Downloading embed page')
+        embed_url = 'https://www.dailymotion.com/embed/video/%s' % video_id
+        embed_request = self._build_request(embed_url)
+        embed_page = self._download_webpage(
+            embed_request, video_id, 'Downloading embed page')

         info = self._search_regex(r'var info = ({.*?}),$', embed_page,
         info = self._search_regex(r'var info = ({.*?}),$', embed_page,

-            'video info', flags=re.MULTILINE)
+                                  'video info', flags=re.MULTILINE)

         info = json.loads(info)
         if info.get('error') is not None:
             msg = 'Couldn\'t get video, Dailymotion says: %s' % info['error']['title']
         info = json.loads(info)
         if info.get('error') is not None:
             msg = 'Couldn\'t get video, Dailymotion says: %s' % info['error']['title']


@@ -127,7 +128,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
             if video_url is not None:
                 m_size = re.search(r'H264-(\d+)x(\d+)', video_url)
                 if m_size is not None:
             if video_url is not None:
                 m_size = re.search(r'H264-(\d+)x(\d+)', video_url)
                 if m_size is not None:

-                    width, height = m_size.group(1), m_size.group(2)
+                    width, height = map(int_or_none, (m_size.group(1), m_size.group(2)))

                 else:
                     width, height = None, None
                 formats.append({
                 else:
                     width, height = None, None
                 formats.append({


@@ -138,87 +139,111 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
                     'height': height,
                 })
         if not formats:
                     'height': height,
                 })
         if not formats:

-            raise ExtractorError(u'Unable to extract video URL')
+            raise ExtractorError('Unable to extract video URL')

 
         # subtitles
         video_subtitles = self.extract_subtitles(video_id, webpage)
 
         # subtitles
         video_subtitles = self.extract_subtitles(video_id, webpage)

-        if self._downloader.params.get('listsubtitles', False):
-            self._list_available_subtitles(video_id, webpage)
-            return
+
+        view_count = str_to_int(self._search_regex(
+            r'video_views_count[^>]+>\s+([\d\.,]+)',
+            webpage, 'view count', fatal=False))
+
+        title = self._og_search_title(webpage, default=None)
+        if title is None:
+            title = self._html_search_regex(
+                r'(?s)<span\s+id="video_title"[^>]*>(.*?)</span>', webpage,
+                'title')

 
         return {
 
         return {

-            'id':       video_id,
+            'id': video_id,

             'formats': formats,
             'formats': formats,

-            'uploader': video_uploader,
-            'upload_date':  video_upload_date,
-            'title':    self._og_search_title(webpage),
-            'subtitles':    video_subtitles,
+            'uploader': info['owner.screenname'],
+            'upload_date': video_upload_date,
+            'title': title,
+            'subtitles': video_subtitles,

             'thumbnail': info['thumbnail_url'],
             'age_limit': age_limit,
             'thumbnail': info['thumbnail_url'],
             'age_limit': age_limit,

+            'view_count': view_count,

         }
 
         }
 

-    def _get_available_subtitles(self, video_id, webpage):
+    def _get_subtitles(self, video_id, webpage):

         try:
             sub_list = self._download_webpage(
                 'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id,
                 video_id, note=False)
         except ExtractorError as err:
         try:
             sub_list = self._download_webpage(
                 'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id,
                 video_id, note=False)
         except ExtractorError as err:

-            self._downloader.report_warning(u'unable to download video subtitles: %s' % compat_str(err))
+            self._downloader.report_warning('unable to download video subtitles: %s' % compat_str(err))

             return {}
         info = json.loads(sub_list)
         if (info['total'] > 0):
             return {}
         info = json.loads(sub_list)
         if (info['total'] > 0):

-            sub_lang_list = dict((l['language'], l['url']) for l in info['list'])
+            sub_lang_list = dict((l['language'], [{'url': l['url'], 'ext': 'srt'}]) for l in info['list'])

             return sub_lang_list
             return sub_lang_list

-        self._downloader.report_warning(u'video doesn\'t have subtitles')
+        self._downloader.report_warning('video doesn\'t have subtitles')

         return {}
 
 
 class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
         return {}
 
 
 class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):

-    IE_NAME = u'dailymotion:playlist'
+    IE_NAME = 'dailymotion:playlist'

     _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/'
     _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/'

-    _MORE_PAGES_INDICATOR = r'<div class="next">.*?<a.*?href="/playlist/.+?".*?>.*?</a>.*?</div>'
+    _MORE_PAGES_INDICATOR = r'(?s)<div class="pages[^"]*">.*?<a\s+class="[^"]*?icon-arrow_right[^"]*?"'

     _PAGE_TEMPLATE = 'https://www.dailymotion.com/playlist/%s/%s'
     _PAGE_TEMPLATE = 'https://www.dailymotion.com/playlist/%s/%s'

+    _TESTS = [{
+        'url': 'http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q',
+        'info_dict': {
+            'title': 'SPORT',
+            'id': 'xv4bw_nqtv_sport',
+        },
+        'playlist_mincount': 20,
+    }]

 
     def _extract_entries(self, id):
         video_ids = []
         for pagenum in itertools.count(1):
             request = self._build_request(self._PAGE_TEMPLATE % (id, pagenum))
             webpage = self._download_webpage(request,
 
     def _extract_entries(self, id):
         video_ids = []
         for pagenum in itertools.count(1):
             request = self._build_request(self._PAGE_TEMPLATE % (id, pagenum))
             webpage = self._download_webpage(request,

-                                             id, u'Downloading page %s' % pagenum)
+                                             id, 'Downloading page %s' % pagenum)

 
 

-            playlist_el = get_element_by_attribute(u'class', u'row video_list', webpage)
-            video_ids.extend(re.findall(r'data-id="(.+?)"', playlist_el))
+            video_ids.extend(re.findall(r'data-xid="(.+?)"', webpage))

 
 

-            if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
+            if re.search(self._MORE_PAGES_INDICATOR, webpage) is None:

                 break
         return [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')
                 break
         return [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')

-                   for video_id in orderedSet(video_ids)]
+                for video_id in orderedSet(video_ids)]

 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         playlist_id = mobj.group('id')
         webpage = self._download_webpage(url, playlist_id)
 
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         playlist_id = mobj.group('id')
         webpage = self._download_webpage(url, playlist_id)
 

-        return {'_type': 'playlist',
-                'id': playlist_id,
-                'title': get_element_by_id(u'playlist_name', webpage),
-                'entries': self._extract_entries(playlist_id),
-                }
+        return {
+            '_type': 'playlist',
+            'id': playlist_id,
+            'title': self._og_search_title(webpage),
+            'entries': self._extract_entries(playlist_id),
+        }

 
 
 class DailymotionUserIE(DailymotionPlaylistIE):
 
 
 class DailymotionUserIE(DailymotionPlaylistIE):

-    IE_NAME = u'dailymotion:user'
-    _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P<user>[^/]+)'
-    _MORE_PAGES_INDICATOR = r'<div class="next">.*?<a.*?href="/user/.+?".*?>.*?</a>.*?</div>'
+    IE_NAME = 'dailymotion:user'
+    _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?:(?:old/)?user/)?(?P<user>[^/]+)$'

     _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
     _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'

+    _TESTS = [{
+        'url': 'https://www.dailymotion.com/user/nqtv',
+        'info_dict': {
+            'id': 'nqtv',
+            'title': 'Rémi Gaillard',
+        },
+        'playlist_mincount': 100,
+    }]

 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         user = mobj.group('user')
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         user = mobj.group('user')

-        webpage = self._download_webpage(url, user)
-        full_user = self._html_search_regex(
-            r'<a class="label" href="/%s".*?>(.*?)</' % re.escape(user),
-            webpage, u'user', flags=re.DOTALL)
+        webpage = self._download_webpage(
+            'https://www.dailymotion.com/user/%s' % user, user)
+        full_user = unescapeHTML(self._html_search_regex(
+            r'<a class="nav-image" title="([^"]+)" href="/%s">' % re.escape(user),
+            webpage, 'user'))

 
         return {
             '_type': 'playlist',
 
         return {
             '_type': 'playlist',