[jukebox] remove extractor and handle it using generic extractor

youtube_dl/extractor/__init__.py

@@ -262,7 +262,6 @@ from .izlesene import IzleseneIE
 from .jadorecettepub import JadoreCettePubIE
 from .jeuxvideo import JeuxVideoIE
 from .jove import JoveIE
-from .jukebox import JukeboxIE
 from .jpopsukitv import JpopsukiIE
 from .kaltura import KalturaIE
 from .kanalplay import KanalPlayIE

youtube_dl/extractor/generic.py

@@ -50,6 +50,7 @@ from .dailymotion import DailymotionCloudIE
 from .onionstudios import OnionStudiosIE
 from .snagfilms import SnagFilmsEmbedIE
 from .screenwavemedia import ScreenwaveMediaIE
+from .ultimedia import UltimediaIE
 
 
 class GenericIE(InfoExtractor):
@@ -1029,6 +1030,21 @@ class GenericIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'cinemasnob',
             },
+        },
+        # Ultimedia embed
+        {
+            'url': 'http://www.jukebox.es/kosheen/videoclip,pride,r303r.html',
+            'md5': '25551df6e7c7ab8096ceeeae048c5f64',
+            'info_dict': {
+                'id': 'r303r',
+                'ext': 'mp4',
+                'title': 'Kosheen - Pride (live)',
+                'thumbnail': 're:^https?://.*\.jpg',
+                'duration': 293,
+                'upload_date': '20081103',
+                'timestamp': 1225733392,
+                'uploader_id': '33m03',
+            },
         }
     ]
 
@@ -1751,6 +1767,11 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
 
+        # Look for Ulltimedia embeds
+        ultimedia_url = UltimediaIE._extract_url(webpage)
+        if ultimedia_url:
+            return self.url_result(self._proto_relative_url(ultimedia_url), 'Ultimedia')
+
         # Look for AdobeTVVideo embeds
         mobj = re.search(
             r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',

youtube_dl/extractor/jukebox.py

@@ -1,59 +0,0 @@
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    RegexNotFoundError,
-    unescapeHTML,
-)
-
-
-class JukeboxIE(InfoExtractor):
-    _VALID_URL = r'^http://www\.jukebox?\..+?\/.+[,](?P<id>[a-z0-9\-]+)\.html'
-    _TEST = {
-        'url': 'http://www.jukebox.es/kosheen/videoclip,pride,r303r.html',
-        'info_dict': {
-            'id': 'r303r',
-            'ext': 'flv',
-            'title': 'Kosheen-En Vivo Pride',
-            'uploader': 'Kosheen',
-        },
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        html = self._download_webpage(url, video_id)
-        iframe_url = unescapeHTML(self._search_regex(r'<iframe .*src="([^"]*)"', html, 'iframe url'))
-
-        iframe_html = self._download_webpage(iframe_url, video_id, 'Downloading iframe')
-        if re.search(r'class="jkb_waiting"', iframe_html) is not None:
-            raise ExtractorError('Video is not available(in your country?)!')
-
-        self.report_extraction(video_id)
-
-        try:
-            video_url = self._search_regex(r'"config":{"file":"(?P<video_url>http:[^"]+\?mdtk=[0-9]+)"',
-                                           iframe_html, 'video url')
-            video_url = unescapeHTML(video_url).replace('\/', '/')
-        except RegexNotFoundError:
-            youtube_url = self._search_regex(
-                r'config":{"file":"(http:\\/\\/www\.youtube\.com\\/watch\?v=[^"]+)"',
-                iframe_html, 'youtube url')
-            youtube_url = unescapeHTML(youtube_url).replace('\/', '/')
-            self.to_screen('Youtube video detected')
-            return self.url_result(youtube_url, ie='Youtube')
-
-        title = self._html_search_regex(r'<h1 class="inline">([^<]+)</h1>',
-                                        html, 'title')
-        artist = self._html_search_regex(r'<span id="infos_article_artist">([^<]+)</span>',
-                                         html, 'artist')
-
-        return {
-            'id': video_id,
-            'url': video_url,
-            'title': artist + '-' + title,
-            'uploader': artist,
-        }

youtube_dl/extractor/ultimedia.py

@@ -4,102 +4,83 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse_urlparse
-from ..utils import (
-    ExtractorError,
-    qualities,
-    unified_strdate,
-    clean_html,
-)
+from ..utils import int_or_none
 
 
 class UltimediaIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?ultimedia\.com/default/index/video[^/]+/id/(?P<id>[\d+a-z]+)'
+    _VALID_URL = r'https?://(?:www\.)?ultimedia\.com/deliver/(?P<type>generic|musique)(?:/[^/]+)*/(?:src|article)/(?P<id>[\d+a-z]+)'
     _TESTS = [{
         # news
-        'url': 'https://www.ultimedia.com/default/index/videogeneric/id/s8uk0r',
+        'url': 'https://www.ultimedia.com/deliver/generic/iframe/mdtk/01601930/zone/1/src/s8uk0r/autoplay/yes/ad/no/width/714/height/435',
         'md5': '276a0e49de58c7e85d32b057837952a2',
         'info_dict': {
             'id': 's8uk0r',
             'ext': 'mp4',
             'title': 'Loi sur la fin de vie: le texte prévoit un renforcement des directives anticipées',
-            'description': 'md5:3e5c8fd65791487333dda5db8aed32af',
             'thumbnail': 're:^https?://.*\.jpg',
+            'duration': 74,
             'upload_date': '20150317',
+            'timestamp': 1426604939,
+            'uploader_id': '3fszv',
         },
     }, {
         # music
-        'url': 'https://www.ultimedia.com/default/index/videomusic/id/xvpfp8',
+        'url': 'https://www.ultimedia.com/deliver/musique/iframe/mdtk/01601930/zone/1/article/xvpfp8/autoplay/yes/ad/no/width/714/height/435',
         'md5': '2ea3513813cf230605c7e2ffe7eca61c',
         'info_dict': {
             'id': 'xvpfp8',
             'ext': 'mp4',
-            'title': "Two - C'est la vie (Clip)",
-            'description': 'Two',
+            'title': 'Two - C\'est La Vie (clip)',
             'thumbnail': 're:^https?://.*\.jpg',
+            'duration': 233,
             'upload_date': '20150224',
+            'timestamp': 1424760500,
+            'uploader_id': '3rfzk',
         },
     }]
 
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+    @staticmethod
+    def _extract_url(webpage):
+        mobj = re.search(
+            r'<(?:iframe|script)[^>]+src=["\'](?P<url>(?:https?:)?//(?:www\.)?ultimedia\.com/deliver/(?:generic|musique)(?:/[^/]+)*/(?:src|article)/[\d+a-z]+)',
+            webpage)
+        if mobj:
+            return mobj.group('url')
 
-        deliver_url = self._proto_relative_url(self._search_regex(
-            r'<iframe[^>]+src="((?:https?:)?//(?:www\.)?ultimedia\.com/deliver/[^"]+)"',
-            webpage, 'deliver URL'), compat_urllib_parse_urlparse(url).scheme + ':')
+    def _real_extract(self, url):
+        video_type, video_id = re.match(self._VALID_URL, url).groups()
 
-        deliver_page = self._download_webpage(
-            deliver_url, video_id, 'Downloading iframe page')
+        deliver_info = self._download_json(
+            'http://www.ultimedia.com/deliver/video?video=%s&topic=%s' % (video_id, video_type),
+            video_id)
 
-        if '>This video is currently not available' in deliver_page:
-            raise ExtractorError(
-                'Video %s is currently not available' % video_id, expected=True)
+        yt_id = deliver_info.get('yt_id')
+        if yt_id:
+            return self.url_result(yt_id, 'Youtube')
 
-        player = self._parse_json(
-            self._search_regex(
-                r"jwplayer\('player(?:_temp)?'\)\.setup\(({.+?})\)\.on",
-                deliver_page, 'player'),
-            video_id)
+        jwconf = deliver_info['jwconf']
 
-        quality = qualities(['flash', 'html5'])
         formats = []
-        for mode in player['modes']:
-            video_url = mode.get('config', {}).get('file')
-            if not video_url:
-                continue
-            if re.match(r'https?://www\.youtube\.com/.+?', video_url):
-                return self.url_result(video_url, 'Youtube')
+        for source in jwconf['playlist'][0]['sources']:
             formats.append({
-                'url': video_url,
-                'format_id': mode.get('type'),
-                'quality': quality(mode.get('type')),
+                'url': source['file'],
+                'format_id': source.get('label'),
             })
-        self._sort_formats(formats)
-
-        thumbnail = player.get('image')
 
-        title = clean_html((
-            self._html_search_regex(
-                r'(?s)<div\s+id="catArticle">.+?</div>(.+?)</h1>',
-                webpage, 'title', default=None) or
-            self._search_regex(
-                r"var\s+nameVideo\s*=\s*'([^']+)'",
-                deliver_page, 'title')))
-
-        description = clean_html(self._html_search_regex(
-            r'(?s)<span>Description</span>(.+?)</p>', webpage,
-            'description', fatal=False))
+        self._sort_formats(formats)
 
-        upload_date = unified_strdate(self._search_regex(
-            r'Ajouté le\s*<span>([^<]+)', webpage,
-            'upload date', fatal=False))
+        title = deliver_info['title']
+        thumbnail = jwconf.get('image')
+        duration = int_or_none(deliver_info.get('duration'))
+        timestamp = int_or_none(deliver_info.get('release_time'))
+        uploader_id = deliver_info.get('owner_id')
 
         return {
             'id': video_id,
             'title': title,
-            'description': description,
             'thumbnail': thumbnail,
-            'upload_date': upload_date,
+            'duration': duration,
+            'timestamp': timestamp,
+            'uploader_id': uploader_id,
             'formats': formats,
         }