debian/watch: Skip pgpsigurlmangle for the moment.

[youtubedl] / youtube_dl / extractor / canalplus.py

diff --git a/youtube_dl/extractor/canalplus.py b/youtube_dl/extractor/canalplus.py
index dddeaa59c4427470fb1511990f443fd38fe804cf..25b2d4efe5d54e1c3264f906a3105ad05dd2ca3f 100644 (file)
--- a/youtube_dl/extractor/canalplus.py
+++ b/youtube_dl/extractor/canalplus.py
@@ -5,31 +5,35 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
 
 from .common import InfoExtractor
 from ..utils import (

+    ExtractorError,
+    HEADRequest,

     unified_strdate,
     url_basename,
     qualities,
     unified_strdate,
     url_basename,
     qualities,

+    int_or_none,

 )
 
 
 class CanalplusIE(InfoExtractor):
     IE_DESC = 'canalplus.fr, piwiplus.fr and d8.tv'
 )
 
 
 class CanalplusIE(InfoExtractor):
     IE_DESC = 'canalplus.fr, piwiplus.fr and d8.tv'

-    _VALID_URL = r'https?://(?:www\.(?P<site>canalplus\.fr|piwiplus\.fr|d8\.tv)/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))'
-    _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s'
+    _VALID_URL = r'https?://(?:www\.(?P<site>canalplus\.fr|piwiplus\.fr|d8\.tv|itele\.fr)/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))'
+    _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s?format=json'

     _SITE_ID_MAP = {
         'canalplus.fr': 'cplus',
         'piwiplus.fr': 'teletoon',
         'd8.tv': 'd8',
     _SITE_ID_MAP = {
         'canalplus.fr': 'cplus',
         'piwiplus.fr': 'teletoon',
         'd8.tv': 'd8',

+        'itele.fr': 'itele',

     }
 
     _TESTS = [{
     }
 
     _TESTS = [{

-        'url': 'http://www.canalplus.fr/c-infos-documentaires/pid1830-c-zapping.html?vid=922470',
-        'md5': '3db39fb48b9685438ecf33a1078023e4',
+        'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1263092',
+        'md5': '12164a6f14ff6df8bd628e8ba9b10b78',

         'info_dict': {
         'info_dict': {

-            'id': '922470',
-            'ext': 'flv',
-            'title': 'Zapping - 26/08/13',
-            'description': 'Le meilleur de toutes les chaînes, tous les jours.\nEmission du 26 août 2013',
-            'upload_date': '20130826',
+            'id': '1263092',
+            'ext': 'mp4',
+            'title': 'Le Zapping - 13/05/15',
+            'description': 'md5:09738c0d06be4b5d06a0940edb0da73f',
+            'upload_date': '20150513',

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


@@ -51,6 +55,16 @@ class CanalplusIE(InfoExtractor):
             'upload_date': '20131108',
         },
         'skip': 'videos get deleted after a while',
             'upload_date': '20131108',
         },
         'skip': 'videos get deleted after a while',

+    }, {
+        'url': 'http://www.itele.fr/france/video/aubervilliers-un-lycee-en-colere-111559',
+        'md5': '38b8f7934def74f0d6f3ba6c036a5f82',
+        'info_dict': {
+            'id': '1213714',
+            'ext': 'mp4',
+            'title': 'Aubervilliers : un lycée en colère - Le 11/02/2015 à 06h45',
+            'description': 'md5:8216206ec53426ea6321321f3b3c16db',
+            'upload_date': '20150211',
+        },

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


@@ -65,51 +79,66 @@ class CanalplusIE(InfoExtractor):
         if video_id is None:
             webpage = self._download_webpage(url, display_id)
             video_id = self._search_regex(
         if video_id is None:
             webpage = self._download_webpage(url, display_id)
             video_id = self._search_regex(

-                r'<canal:player[^>]+?videoId="(\d+)"', webpage, 'video id')
+                [r'<canal:player[^>]+?videoId=(["\'])(?P<id>\d+)', r'id=["\']canal_video_player(?P<id>\d+)'],
+                webpage, 'video id', group='id')

 
         info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)
 
         info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)

-        doc = self._download_xml(info_url, video_id, 'Downloading video XML')
+        video_data = self._download_json(info_url, video_id, 'Downloading video JSON')

 
 

-        video_info = [video for video in doc if video.find('ID').text == video_id][0]
-        media = video_info.find('MEDIA')
-        infos = video_info.find('INFOS')
+        if isinstance(video_data, list):
+            video_data = [video for video in video_data if video.get('ID') == video_id][0]
+        media = video_data['MEDIA']
+        infos = video_data['INFOS']

 
 

-        preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD', 'HLS', 'HDS'])
+        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)

 
         formats = []
 
         formats = []

-        for fmt in media.find('VIDEOS'):
-            format_url = fmt.text
+        for format_id, format_url in media['VIDEOS'].items():

             if not format_url:
                 continue
             if not format_url:
                 continue

-            format_id = fmt.tag

             if format_id == 'HLS':
             if format_id == 'HLS':

-                hls_formats = self._extract_m3u8_formats(format_url, video_id, 'flv')
-                for fmt in hls_formats:
-                    fmt['preference'] = preference(format_id)
-                formats.extend(hls_formats)
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, video_id, 'mp4', 'm3u8_native', m3u8_id=format_id, fatal=False))

             elif format_id == 'HDS':
             elif format_id == 'HDS':

-                hds_formats = self._extract_f4m_formats(format_url + '?hdcore=2.11.3', video_id)
-                for fmt in hds_formats:
-                    fmt['preference'] = preference(format_id)
-                formats.extend(hds_formats)
+                formats.extend(self._extract_f4m_formats(
+                    format_url + '?hdcore=2.11.3', video_id, f4m_id=format_id, fatal=False))

             else:
                 formats.append({
             else:
                 formats.append({

-                    'url': format_url,
+                    # the secret extracted ya function in http://player.canalplus.fr/common/js/canalPlayer.js
+                    'url': format_url + '?secret=pqzerjlsmdkjfoiuerhsdlfknaes',

                     'format_id': format_id,
                     'preference': preference(format_id),
                 })
         self._sort_formats(formats)
 
                     'format_id': format_id,
                     'preference': preference(format_id),
                 })
         self._sort_formats(formats)
 

+        thumbnails = [{
+            'id': image_id,
+            'url': image_url,
+        } for image_id, image_url in media.get('images', {}).items()]
+
+        titrage = infos['TITRAGE']
+

         return {
             'id': video_id,
             'display_id': display_id,
         return {
             'id': video_id,
             'display_id': display_id,

-            'title': '%s - %s' % (infos.find('TITRAGE/TITRE').text,
-                                  infos.find('TITRAGE/SOUS_TITRE').text),
-            'upload_date': unified_strdate(infos.find('PUBLICATION/DATE').text),
-            'thumbnail': media.find('IMAGES/GRAND').text,
-            'description': infos.find('DESCRIPTION').text,
-            'view_count': int(infos.find('NB_VUES').text),
-            'like_count': int(infos.find('NB_LIKES').text),
-            'comment_count': int(infos.find('NB_COMMENTS').text),
+            'title': '%s - %s' % (titrage['TITRE'],
+                                  titrage['SOUS_TITRE']),
+            'upload_date': unified_strdate(infos.get('PUBLICATION', {}).get('DATE')),
+            'thumbnails': thumbnails,
+            'description': infos.get('DESCRIPTION'),
+            'duration': int_or_none(infos.get('DURATION')),
+            'view_count': int_or_none(infos.get('NB_VUES')),
+            'like_count': int_or_none(infos.get('NB_LIKES')),
+            'comment_count': int_or_none(infos.get('NB_COMMENTS')),

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

-        }
\ No newline at end of file
+        }