youtube-dl

commit 3d6761ba92b96934bdbf1792dfacd0368d7b236c
parent f59d1146c0ca523ec03a4c7df8987e82ee5054b2
Author: Sergey M․ <dstftw@gmail.com>
Date:   Tue, 20 Dec 2016 21:51:11 +0700

[vbox7] Fix extraction (closes #11494)

Diffstat:
M
youtube_dl/extractor/vbox7.py
 | 
75
++++++++++++++++++++++++++++++++++++++++++++++++++++-----------------------

1 file changed, 52 insertions(+), 23 deletions(-)
diff --git a/youtube_dl/extractor/vbox7.py b/youtube_dl/extractor/vbox7.py
@@ -4,11 +4,22 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import urlencode_postdata
+from ..utils import ExtractorError
 
 
 class Vbox7IE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?vbox7\.com/(?:play:|emb/external\.php\?.*?\bvid=)(?P<id>[\da-fA-F]+)'
+    _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',
@@ -16,6 +27,14 @@ class Vbox7IE(InfoExtractor):
             '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': 're:^https?://.*\.jpg$',
+            'timestamp': 1470982814,
+            'upload_date': '20160812',
+            'uploader': 'zdraveibulgaria',
+        },
+        'params': {
+            'proxy': '127.0.0.1:8118',
         },
     }, {
         'url': 'http://vbox7.com/play:249bb972c2',
@@ -29,6 +48,9 @@ class Vbox7IE(InfoExtractor):
     }, {
         '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
@@ -42,33 +64,40 @@ class Vbox7IE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        webpage = self._download_webpage(
-            'http://vbox7.com/play:%s' % video_id, video_id)
-
-        title = self._html_search_regex(
-            r'<title>(.+?)</title>', webpage, 'title').split('/')[0].strip()
+        response = self._download_json(
+            'https://www.vbox7.com/ajax/video/nextvideo.php?vid=%s' % video_id,
+            video_id)
 
-        video_url = self._search_regex(
-            r'src\s*:\s*(["\'])(?P<url>.+?.mp4.*?)\1',
-            webpage, 'video url', default=None, group='url')
+        if 'error' in response:
+            raise ExtractorError(
+                '%s said: %s' % (self.IE_NAME, response['error']), expected=True)
 
-        thumbnail_url = self._og_search_thumbnail(webpage)
+        video = response['options']
 
-        if not video_url:
-            info_response = self._download_webpage(
-                'http://vbox7.com/play/magare.do', video_id,
-                'Downloading info webpage',
-                data=urlencode_postdata({'as3': '1', 'vid': video_id}),
-                headers={'Content-Type': 'application/x-www-form-urlencoded'})
-            final_url, thumbnail_url = map(
-                lambda x: x.split('=')[1], info_response.split('&'))
+        title = video['title']
+        video_url = video['src']
 
         if '/na.mp4' in video_url:
             self.raise_geo_restricted()
 
-        return {
+        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)
+
+        info.update({
             'id': video_id,
-            'url': self._proto_relative_url(video_url, 'http:'),
             '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