Prepare to upload

[youtubedl] / youtube_dl / extractor / canalplus.py

diff --git a/youtube_dl/extractor/canalplus.py b/youtube_dl/extractor/canalplus.py
index 61463f249f6e4ded3b5f59831d7dba421ef9de9a..d8bf073f40cf171d547992679d295055f82ef386 100644 (file)
--- a/youtube_dl/extractor/canalplus.py
+++ b/youtube_dl/extractor/canalplus.py
@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8

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


@@ -6,11 +6,13 @@ import re
 from .common import InfoExtractor
 from ..compat import compat_urllib_parse_urlparse
 from ..utils import (
 from .common import InfoExtractor
 from ..compat import compat_urllib_parse_urlparse
 from ..utils import (

-    ExtractorError,
-    HEADRequest,
-    unified_strdate,
-    qualities,
+    dict_get,
+    # ExtractorError,
+    # HEADRequest,

     int_or_none,
     int_or_none,

+    qualities,
+    remove_end,
+    unified_strdate,

 )
 
 
 )
 
 


@@ -23,7 +25,9 @@ class CanalplusIE(InfoExtractor):
                                     (?:(?:www|m)\.)?canalplus\.fr|
                                     (?:www\.)?piwiplus\.fr|
                                     (?:www\.)?d8\.tv|
                                     (?:(?:www|m)\.)?canalplus\.fr|
                                     (?:www\.)?piwiplus\.fr|
                                     (?:www\.)?d8\.tv|

+                                    (?:www\.)?c8\.fr|

                                     (?:www\.)?d17\.tv|
                                     (?:www\.)?d17\.tv|

+                                    (?:(?:football|www)\.)?cstar\.fr|

                                     (?:www\.)?itele\.fr
                                 )/(?:(?:[^/]+/)*(?P<display_id>[^/?#&]+))?(?:\?.*\bvid=(?P<vid>\d+))?|
                                 player\.canalplus\.fr/#/(?P<id>\d+)
                                     (?:www\.)?itele\.fr
                                 )/(?:(?:[^/]+/)*(?P<display_id>[^/?#&]+))?(?:\?.*\bvid=(?P<vid>\d+))?|
                                 player\.canalplus\.fr/#/(?P<id>\d+)


@@ -35,50 +39,69 @@ class CanalplusIE(InfoExtractor):
         'canalplus': 'cplus',
         'piwiplus': 'teletoon',
         'd8': 'd8',
         'canalplus': 'cplus',
         'piwiplus': 'teletoon',
         'd8': 'd8',

+        'c8': 'd8',

         'd17': 'd17',
         'd17': 'd17',

+        'cstar': 'd17',

         'itele': 'itele',
     }
 
         'itele': 'itele',
     }
 

+    # Only works for direct mp4 URLs
+    _GEO_COUNTRIES = ['FR']
+

     _TESTS = [{
         'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1192814',
     _TESTS = [{
         'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1192814',

-        'md5': '41f438a4904f7664b91b4ed0dec969dc',

         'info_dict': {
         'info_dict': {

-            'id': '1192814',
+            'id': '1405510',
+            'display_id': 'pid1830-c-zapping',

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

-            'title': "L'Année du Zapping 2014 - L'Année du Zapping 2014",
-            'description': "Toute l'année 2014 dans un Zapping exceptionnel !",
-            'upload_date': '20150105',
+            'title': 'Zapping - 02/07/2016',
+            'description': 'Le meilleur de toutes les chaînes, tous les jours',
+            'upload_date': '20160702',

         },
     }, {
         },
     }, {

+        # geo restricted, bypassed

         'url': 'http://www.piwiplus.fr/videos-piwi/pid1405-le-labyrinthe-boing-super-ranger.html?vid=1108190',
         'info_dict': {
             'id': '1108190',
         'url': 'http://www.piwiplus.fr/videos-piwi/pid1405-le-labyrinthe-boing-super-ranger.html?vid=1108190',
         'info_dict': {
             'id': '1108190',

-            'ext': 'flv',
-            'title': 'Le labyrinthe - Boing super ranger',
+            'display_id': 'pid1405-le-labyrinthe-boing-super-ranger',
+            'ext': 'mp4',
+            'title': 'BOING SUPER RANGER - Ep : Le labyrinthe',

             'description': 'md5:4cea7a37153be42c1ba2c1d3064376ff',
             'upload_date': '20140724',
         },
             'description': 'md5:4cea7a37153be42c1ba2c1d3064376ff',
             'upload_date': '20140724',
         },

-        'skip': 'Only works from France',
+        'expected_warnings': ['HTTP Error 403: Forbidden'],

     }, {
     }, {

-        'url': 'http://www.d8.tv/d8-docs-mags/pid5198-d8-en-quete-d-actualite.html?vid=1390231',
+        # geo restricted, bypassed
+        'url': 'http://www.c8.fr/c8-divertissement/ms-touche-pas-a-mon-poste/pid6318-videos-integrales.html?vid=1443684',
+        'md5': 'bb6f9f343296ab7ebd88c97b660ecf8d',

         'info_dict': {
         'info_dict': {

-            'id': '1390231',
+            'id': '1443684',
+            'display_id': 'pid6318-videos-integrales',

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

-            'title': "Vacances pas chères : prix discount ou grosses dépenses ? - En quête d'actualité",
-            'description': 'md5:edb6cf1cb4a1e807b5dd089e1ac8bfc6',
-            'upload_date': '20160512',
+            'title': 'Guess my iep ! - TPMP - 07/04/2017',
+            'description': 'md5:6f005933f6e06760a9236d9b3b5f17fa',
+            'upload_date': '20170407',

         },
         },

-        'params': {
-            'skip_download': True,
+        'expected_warnings': ['HTTP Error 403: Forbidden'],
+    }, {
+        'url': 'http://www.itele.fr/chroniques/invite-michael-darmon/rachida-dati-nicolas-sarkozy-est-le-plus-en-phase-avec-les-inquietudes-des-francais-171510',
+        'info_dict': {
+            'id': '1420176',
+            'display_id': 'rachida-dati-nicolas-sarkozy-est-le-plus-en-phase-avec-les-inquietudes-des-francais-171510',
+            'ext': 'mp4',
+            'title': 'L\'invité de Michaël Darmon du 14/10/2016 - ',
+            'description': 'Chaque matin du lundi au vendredi, Michaël Darmon reçoit un invité politique à 8h25.',
+            'upload_date': '20161014',

         },
     }, {
         },
     }, {

-        'url': 'http://www.itele.fr/chroniques/invite-bruce-toussaint/thierry-solere-nicolas-sarkozy-officialisera-sa-candidature-a-la-primaire-quand-il-le-voudra-167224',
+        'url': 'http://football.cstar.fr/cstar-minisite-foot/pid7566-feminines-videos.html?vid=1416769',

         'info_dict': {
         'info_dict': {

-            'id': '1398334',
+            'id': '1416769',
+            'display_id': 'pid7566-feminines-videos',

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

-            'title': "L'invité de Bruce Toussaint du 07/06/2016 - ",
-            'description': 'md5:40ac7c9ad0feaeb6f605bad986f61324',
-            'upload_date': '20160607',
+            'title': 'France - Albanie : les temps forts de la soirée - 20/09/2016',
+            'description': 'md5:c3f30f2aaac294c1c969b3294de6904e',
+            'upload_date': '20160921',

         },
         'params': {
             'skip_download': True,
         },
         'params': {
             'skip_download': True,


@@ -93,18 +116,18 @@ class CanalplusIE(InfoExtractor):
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

-        video_id = mobj.groupdict().get('id') or mobj.groupdict().get('vid')

 
         site_id = self._SITE_ID_MAP[compat_urllib_parse_urlparse(url).netloc.rsplit('.', 2)[-2]]
 
         # Beware, some subclasses do not define an id group
 
         site_id = self._SITE_ID_MAP[compat_urllib_parse_urlparse(url).netloc.rsplit('.', 2)[-2]]
 
         # Beware, some subclasses do not define an id group

-        display_id = mobj.group('display_id') or video_id
+        display_id = remove_end(dict_get(mobj.groupdict(), ('display_id', 'id', 'vid')), '.html')

 
 

-        if video_id is None:
-            webpage = self._download_webpage(url, display_id)
-            video_id = self._search_regex(
-                [r'<canal:player[^>]+?videoId=(["\'])(?P<id>\d+)', r'id=["\']canal_video_player(?P<id>\d+)'],
-                webpage, 'video id', group='id')
+        webpage = self._download_webpage(url, display_id)
+        video_id = self._search_regex(
+            [r'<canal:player[^>]+?videoId=(["\'])(?P<id>\d+)',
+             r'id=["\']canal_video_player(?P<id>\d+)',
+             r'data-video=["\'](?P<id>\d+)'],
+            webpage, 'video id', default=mobj.group('vid'), group='id')

 
         info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)
         video_data = self._download_json(info_url, video_id, 'Downloading video JSON')
 
         info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)
         video_data = self._download_json(info_url, video_id, 'Downloading video JSON')


@@ -116,15 +139,15 @@ class CanalplusIE(InfoExtractor):
 
         preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD'])
 
 
         preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD'])
 

-        fmt_url = next(iter(media.get('VIDEOS')))
-        if '/geo' in fmt_url.lower():
-            response = self._request_webpage(
-                HEADRequest(fmt_url), video_id,
-                'Checking if the video is georestricted')
-            if '/blocage' in response.geturl():
-                raise ExtractorError(
-                    'The video is not available in your country',
-                    expected=True)
+        # _, fmt_url = next(iter(media['VIDEOS'].items()))
+        # if '/geo' in fmt_url.lower():
+        #     response = self._request_webpage(
+        #         HEADRequest(fmt_url), video_id,
+        #         'Checking if the video is georestricted')
+        #     if '/blocage' in response.geturl():
+        #         raise ExtractorError(
+        #             'The video is not available in your country',
+        #             expected=True)

 
         formats = []
         for format_id, format_url in media['VIDEOS'].items():
 
         formats = []
         for format_id, format_url in media['VIDEOS'].items():