Merge tag 'upstream/2017.02.07'

[youtubedl] / youtube_dl / extractor / vbox7.py

diff --git a/youtube_dl/extractor/vbox7.py b/youtube_dl/extractor/vbox7.py
index dff1bb70281b9a1cd69d9507b963e4c622a29044..bef6394626d4eca25785d35199c1092f69f45b54 100644 (file)
--- a/youtube_dl/extractor/vbox7.py
+++ b/youtube_dl/extractor/vbox7.py
@@ -1,18 +1,42 @@
-# encoding: utf-8
+# coding: utf-8

 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

+import re
+

 from .common import InfoExtractor
 from .common import InfoExtractor

-from ..compat import compat_urlparse
-from ..utils import (
-    ExtractorError,
-    sanitized_Request,
-    urlencode_postdata,
-)
+from ..utils import ExtractorError

 
 
 class Vbox7IE(InfoExtractor):
 
 
 class Vbox7IE(InfoExtractor):

-    _VALID_URL = r'https?://(?:www\.)?vbox7\.com/play:(?P<id>[^/]+)'
-    _TEST = {
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:[^/]+\.)?vbox7\.com/
+                        (?:
+                            play:|
+                            (?:
+                                emb/external\.php|
+                                player/ext\.swf
+                            )\?.*?\bvid=
+                        )
+                        (?P<id>[\da-fA-F]+)
+                    '''
+    _TESTS = [{
+        'url': 'http://vbox7.com/play:0946fff23c',
+        'md5': 'a60f9ab3a3a2f013ef9a967d5f7be5bf',
+        'info_dict': {
+            'id': '0946fff23c',
+            'ext': 'mp4',
+            'title': 'Борисов: Притеснен съм за бъдещето на България',
+            'description': 'По думите му е опасно страната ни да бъде обявена за "сигурна"',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'timestamp': 1470982814,
+            'upload_date': '20160812',
+            'uploader': 'zdraveibulgaria',
+        },
+        'params': {
+            'proxy': '127.0.0.1:8118',
+        },
+    }, {

         'url': 'http://vbox7.com/play:249bb972c2',
         'md5': '99f65c0c9ef9b682b97313e052734c3f',
         'info_dict': {
         'url': 'http://vbox7.com/play:249bb972c2',
         'md5': '99f65c0c9ef9b682b97313e052734c3f',
         'info_dict': {


@@ -20,43 +44,61 @@ class Vbox7IE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Смях! Чудо - чист за секунди - Скрита камера',
         },
             'ext': 'mp4',
             'title': 'Смях! Чудо - чист за секунди - Скрита камера',
         },

-    }
+        'skip': 'georestricted',
+    }, {
+        'url': 'http://vbox7.com/emb/external.php?vid=a240d20f9c&autoplay=1',
+        'only_matching': True,
+    }, {
+        'url': 'http://i49.vbox7.com/player/ext.swf?vid=0946fff23c&autoplay=1',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _extract_url(webpage):
+        mobj = re.search(
+            r'<iframe[^>]+src=(?P<q>["\'])(?P<url>(?:https?:)?//vbox7\.com/emb/external\.php.+?)(?P=q)',
+            webpage)
+        if mobj:
+            return mobj.group('url')

 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 

-        # need to get the page 3 times for the correct jsSecretToken cookie
-        # which is necessary for the correct title
-        def get_session_id():
-            redirect_page = self._download_webpage(url, video_id)
-            session_id_url = self._search_regex(
-                r'var\s*url\s*=\s*\'([^\']+)\';', redirect_page,
-                'session id url')
-            self._download_webpage(
-                compat_urlparse.urljoin(url, session_id_url), video_id,
-                'Getting session id')
-
-        get_session_id()
-        get_session_id()
-
-        webpage = self._download_webpage(url, video_id,
-                                         'Downloading redirect page')
-
-        title = self._html_search_regex(r'<title>(.*)</title>',
-                                        webpage, 'title').split('/')[0].strip()
-
-        info_url = 'http://vbox7.com/play/magare.do'
-        data = urlencode_postdata({'as3': '1', 'vid': video_id})
-        info_request = sanitized_Request(info_url, data)
-        info_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
-        info_response = self._download_webpage(info_request, video_id, 'Downloading info webpage')
-        if info_response is None:
-            raise ExtractorError('Unable to extract the media url')
-        (final_url, thumbnail_url) = map(lambda x: x.split('=')[1], info_response.split('&'))
-
-        return {
+        response = self._download_json(
+            'https://www.vbox7.com/ajax/video/nextvideo.php?vid=%s' % video_id,
+            video_id)
+
+        if 'error' in response:
+            raise ExtractorError(
+                '%s said: %s' % (self.IE_NAME, response['error']), expected=True)
+
+        video = response['options']
+
+        title = video['title']
+        video_url = video['src']
+
+        if '/na.mp4' in video_url:
+            self.raise_geo_restricted()
+
+        uploader = video.get('uploader')
+
+        webpage = self._download_webpage(
+            'http://vbox7.com/play:%s' % video_id, video_id, fatal=None)
+
+        info = {}
+
+        if webpage:
+            info = self._search_json_ld(
+                webpage.replace('"/*@context"', '"@context"'), video_id,
+                fatal=False)
+
+        info.update({

             'id': video_id,
             'id': video_id,

-            'url': final_url,

             'title': title,
             'title': title,

-            'thumbnail': thumbnail_url,
-        }
+            'url': video_url,
+            'uploader': uploader,
+            'thumbnail': self._proto_relative_url(
+                info.get('thumbnail') or self._og_search_thumbnail(webpage),
+                'http:'),
+        })
+        return info