debian/control: Prefer mplayer to mplayer2 in Recommends.

[youtubedl] / youtube_dl / extractor / dailymotion.py

diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py
index fd4bc75b2a91a1ad115a9152bf85debce7880431..1a41c0db181c43c9c35d24988b9fd118c248f399 100644 (file)
--- a/youtube_dl/extractor/dailymotion.py
+++ b/youtube_dl/extractor/dailymotion.py
@@ -1,4 +1,4 @@
-#coding: utf-8
+# coding: utf-8

 from __future__ import unicode_literals
 
 import re
 from __future__ import unicode_literals
 
 import re


@@ -6,28 +6,30 @@ import json
 import itertools
 
 from .common import InfoExtractor
 import itertools
 
 from .common import InfoExtractor

-from .subtitles import SubtitlesInfoExtractor

 
 

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

     compat_str,
     compat_str,

+    compat_urllib_request,
+)
+from ..utils import (
+    ExtractorError,
+    int_or_none,

     orderedSet,
     str_to_int,
     orderedSet,
     str_to_int,

-    int_or_none,
-    ExtractorError,

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


@@ -43,13 +45,15 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
 
     _TESTS = [
         {
 
     _TESTS = [
         {

-            'url': 'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech',
-            'md5': '392c4b85a60a90dc4792da41ce3144eb',
+            'url': 'https://www.dailymotion.com/video/x2iuewm_steam-machine-models-pricing-listed-on-steam-store-ign-news_videogames',
+            'md5': '2137c41a8e78554bb09225b8eb322406',

             'info_dict': {
             'info_dict': {

-                'id': 'x33vw9',
+                'id': 'x2iuewm',

                 'ext': 'mp4',
                 'ext': 'mp4',

-                'uploader': 'Amphora Alex and Van .',
-                'title': 'Tutoriel de Youtubeur"DL DES VIDEO DE YOUTUBE"',
+                'uploader': 'IGN',
+                'title': 'Steam Machine Models, Pricing Listed on Steam Store - IGN News',
+                'upload_date': '20150306',
+                'duration': 74,

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


@@ -83,7 +87,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)

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


@@ -104,15 +108,16 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
         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,
-                                            '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']


@@ -139,9 +144,6 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
 
         # 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\.,]+)',
 
         view_count = str_to_int(self._search_regex(
             r'video_views_count[^>]+>\s+([\d\.,]+)',


@@ -163,9 +165,10 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
             'thumbnail': info['thumbnail_url'],
             'age_limit': age_limit,
             'view_count': view_count,
             'thumbnail': info['thumbnail_url'],
             'age_limit': age_limit,
             'view_count': view_count,

+            'duration': info['duration']

         }
 
         }
 

-    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,
         try:
             sub_list = self._download_webpage(
                 'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id,


@@ -175,7 +178,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
             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
         self._downloader.report_warning('video doesn\'t have subtitles')
         return {}
             return sub_lang_list
         self._downloader.report_warning('video doesn\'t have subtitles')
         return {}


@@ -190,6 +193,7 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
         'url': 'http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q',
         'info_dict': {
             'title': 'SPORT',
         'url': 'http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q',
         'info_dict': {
             'title': 'SPORT',

+            'id': 'xv4bw_nqtv_sport',

         },
         'playlist_mincount': 20,
     }]
         },
         'playlist_mincount': 20,
     }]


@@ -206,7 +210,7 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
             if re.search(self._MORE_PAGES_INDICATOR, webpage) is None:
                 break
         return [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')
             if re.search(self._MORE_PAGES_INDICATOR, webpage) is None:
                 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)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)


@@ -223,7 +227,7 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
 
 class DailymotionUserIE(DailymotionPlaylistIE):
     IE_NAME = 'dailymotion:user'
 
 class DailymotionUserIE(DailymotionPlaylistIE):
     IE_NAME = 'dailymotion:user'

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

     _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
     _TESTS = [{
         'url': 'https://www.dailymotion.com/user/nqtv',
     _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
     _TESTS = [{
         'url': 'https://www.dailymotion.com/user/nqtv',


@@ -237,7 +241,8 @@ class DailymotionUserIE(DailymotionPlaylistIE):
     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)
+        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'))
         full_user = unescapeHTML(self._html_search_regex(
             r'<a class="nav-image" title="([^"]+)" href="/%s">' % re.escape(user),
             webpage, 'user'))


@@ -248,3 +253,53 @@ class DailymotionUserIE(DailymotionPlaylistIE):
             'title': full_user,
             'entries': self._extract_entries(user),
         }
             'title': full_user,
             'entries': self._extract_entries(user),
         }

+
+
+class DailymotionCloudIE(DailymotionBaseInfoExtractor):
+    _VALID_URL_PREFIX = r'http://api\.dmcloud\.net/(?:player/)?embed/'
+    _VALID_URL = r'%s[^/]+/(?P<id>[^/?]+)' % _VALID_URL_PREFIX
+    _VALID_EMBED_URL = r'%s[^/]+/[^\'"]+' % _VALID_URL_PREFIX
+
+    _TESTS = [{
+        # From http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html
+        # Tested at FranceTvInfo_2
+        'url': 'http://api.dmcloud.net/embed/4e7343f894a6f677b10006b4/556e03339473995ee145930c?auth=1464865870-0-jyhsm84b-ead4c701fb750cf9367bf4447167a3db&autoplay=1',
+        'only_matching': True,
+    }, {
+        # http://www.francetvinfo.fr/societe/larguez-les-amarres-le-cobaturage-se-developpe_980101.html
+        'url': 'http://api.dmcloud.net/player/embed/4e7343f894a6f677b10006b4/559545469473996d31429f06?auth=1467430263-0-90tglw2l-a3a4b64ed41efe48d7fccad85b8b8fda&autoplay=1',
+        'only_matching': True,
+    }]
+
+    @classmethod
+    def _extract_dmcloud_url(self, webpage):
+        mobj = re.search(r'<iframe[^>]+src=[\'"](%s)[\'"]' % self._VALID_EMBED_URL, webpage)
+        if mobj:
+            return mobj.group(1)
+
+        mobj = re.search(
+            r'<input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=[\'"](%s)[\'"]' % self._VALID_EMBED_URL,
+            webpage)
+        if mobj:
+            return mobj.group(1)
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        request = self._build_request(url)
+        webpage = self._download_webpage(request, video_id)
+
+        title = self._html_search_regex(r'<title>([^>]+)</title>', webpage, 'title')
+
+        video_info = self._parse_json(self._search_regex(
+            r'var\s+info\s*=\s*([^;]+);', webpage, 'video info'), video_id)
+
+        # TODO: parse ios_url, which is in fact a manifest
+        video_url = video_info['mp4_url']
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'thumbnail': video_info.get('thumbnail_url'),
+        }