Initiate new release.

[youtubedl] / youtube_dl / extractor / canalplus.py

diff --git a/youtube_dl/extractor/canalplus.py b/youtube_dl/extractor/canalplus.py
index 1f02519a0149ad85aad3886bf0a01e5c986064c0..1b14471e57198c2a04833089c174c0c6c3108ab8 100644 (file)
--- a/youtube_dl/extractor/canalplus.py
+++ b/youtube_dl/extractor/canalplus.py
@@ -1,46 +1,138 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+

 import re
 import re

-import xml.etree.ElementTree

 
 from .common import InfoExtractor
 
 from .common import InfoExtractor

-from ..utils import unified_strdate
+from ..utils import (
+    ExtractorError,
+    HEADRequest,
+    unified_strdate,
+    url_basename,
+    qualities,
+)
+

 
 class CanalplusIE(InfoExtractor):
 
 class CanalplusIE(InfoExtractor):

-    _VALID_URL = r'https?://(www\.canalplus\.fr/.*?\?vid=|player\.canalplus\.fr/#/)(?P<id>\d+)'
-    _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/cplus/%s'
-    IE_NAME = u'canalplus.fr'
-
-    _TEST = {
-        u'url': u'http://www.canalplus.fr/c-divertissement/pid3351-c-le-petit-journal.html?vid=889861',
-        u'file': u'889861.flv',
-        u'md5': u'590a888158b5f0d6832f84001fbf3e99',
-        u'info_dict': {
-            u'title': u'Le Petit Journal 20/06/13 - La guerre des drone',
-            u'upload_date': u'20130620',
-        },
-        u'skip': u'Requires rtmpdump'
+    IE_DESC = 'canalplus.fr, piwiplus.fr and d8.tv'
+    _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'
+    _SITE_ID_MAP = {
+        'canalplus.fr': 'cplus',
+        'piwiplus.fr': 'teletoon',
+        'd8.tv': 'd8',
+        'itele.fr': 'itele',

     }
 
     }
 

+    _TESTS = [{
+        'url': 'http://www.canalplus.fr/c-infos-documentaires/pid1830-c-zapping.html?vid=922470',
+        'md5': '3db39fb48b9685438ecf33a1078023e4',
+        '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',
+        },
+    }, {
+        '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',
+            'description': 'md5:4cea7a37153be42c1ba2c1d3064376ff',
+            'upload_date': '20140724',
+        },
+        'skip': 'Only works from France',
+    }, {
+        'url': 'http://www.d8.tv/d8-docs-mags/pid6589-d8-campagne-intime.html',
+        'info_dict': {
+            'id': '966289',
+            'ext': 'flv',
+            'title': 'Campagne intime - Documentaire exceptionnel',
+            'description': 'md5:d2643b799fb190846ae09c61e59a859f',
+            'upload_date': '20131108',
+        },
+        'skip': 'videos get deleted after a while',
+    }, {
+        'url': 'http://www.itele.fr/france/video/aubervilliers-un-lycee-en-colere-111559',
+        'md5': '65aa83ad62fe107ce29e564bb8712580',
+        'info_dict': {
+            'id': '1213714',
+            'ext': 'flv',
+            'title': 'Aubervilliers : un lycée en colère - Le 11/02/2015 à 06h45',
+            'description': 'md5:8216206ec53426ea6321321f3b3c16db',
+            'upload_date': '20150211',
+        },
+    }]
+

     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.group('id')
-        info_url = self._VIDEO_INFO_TEMPLATE % video_id
-        info_page = self._download_webpage(info_url,video_id, 
-                                           u'Downloading video info')
+        video_id = mobj.groupdict().get('id')
+
+        site_id = self._SITE_ID_MAP[mobj.group('site') or 'canal']
+
+        # Beware, some subclasses do not define an id group
+        display_id = url_basename(mobj.group('path'))
+
+        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')
+
+        info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)
+        doc = self._download_xml(info_url, video_id, 'Downloading video XML')

 
 

-        self.report_extraction(video_id)
-        doc = xml.etree.ElementTree.fromstring(info_page.encode('utf-8'))

         video_info = [video for video in doc if video.find('ID').text == video_id][0]
         video_info = [video for video in doc if video.find('ID').text == video_id][0]

-        infos = video_info.find('INFOS')

         media = video_info.find('MEDIA')
         media = video_info.find('MEDIA')

-        formats = [media.find('VIDEOS/%s' % format)
-            for format in ['BAS_DEBIT', 'HAUT_DEBIT', 'HD']]
-        video_url = [format.text for format in formats if format is not None][-1]
-
-        return {'id': video_id,
-                'title': u'%s - %s' % (infos.find('TITRAGE/TITRE').text,
-                                       infos.find('TITRAGE/SOUS_TITRE').text),
-                'url': video_url,
-                'ext': 'flv',
-                'upload_date': unified_strdate(infos.find('PUBLICATION/DATE').text),
-                'thumbnail': media.find('IMAGES/GRAND').text,
-                }
+        infos = video_info.find('INFOS')
+
+        preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD', 'HLS', 'HDS'])
+
+        fmt_url = next(iter(media.find('VIDEOS'))).text
+        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 fmt in media.find('VIDEOS'):
+            format_url = fmt.text
+            if not format_url:
+                continue
+            format_id = fmt.tag
+            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)
+            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)
+            else:
+                formats.append({
+                    'url': format_url,
+                    'format_id': format_id,
+                    'preference': preference(format_id),
+                })
+        self._sort_formats(formats)
+
+        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),
+            'formats': formats,
+        }