X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/feb5020b37d7d3ba4005a8bac6f4efece4ce4b8c..dac1bb85bcc8e3218197a2aaff9aba4a1da896ae:/youtube_dl/extractor/vbox7.py

diff --git a/youtube_dl/extractor/vbox7.py b/youtube_dl/extractor/vbox7.py
index 4f803bc..e179885 100644
--- a/youtube_dl/extractor/vbox7.py
+++ b/youtube_dl/extractor/vbox7.py
@@ -1,54 +1,74 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    compat_urllib_parse,
-    compat_urllib_request,
-
-    ExtractorError,
-)
+from ..utils import urlencode_postdata
 
 
 class Vbox7IE(InfoExtractor):
-    """Information Extractor for Vbox7"""
-    _VALID_URL = r'(?:http://)?(?:www\.)?vbox7\.com/play:([^/]+)'
-    _TEST = {
-        u'url': u'http://vbox7.com/play:249bb972c2',
-        u'file': u'249bb972c2.flv',
-        u'md5': u'9c70d6d956f888bdc08c124acc120cfe',
-        u'info_dict': {
-            u"title": u"\u0421\u043c\u044f\u0445! \u0427\u0443\u0434\u043e - \u0447\u0438\u0441\u0442 \u0437\u0430 \u0441\u0435\u043a\u0443\u043d\u0434\u0438 - \u0421\u043a\u0440\u0438\u0442\u0430 \u043a\u0430\u043c\u0435\u0440\u0430"
-        }
-    }
-
-    def _real_extract(self,url):
-        mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
-        video_id = mobj.group(1)
-
-        redirect_page, urlh = self._download_webpage_handle(url, video_id)
-        new_location = self._search_regex(r'window\.location = \'(.*)\';', redirect_page, u'redirect location')
-        redirect_url = urlh.geturl() + new_location
-        webpage = self._download_webpage(redirect_url, video_id, u'Downloading redirect page')
-
-        title = self._html_search_regex(r'<title>(.*)</title>',
-            webpage, u'title').split('/')[0].strip()
-
-        ext = "flv"
-        info_url = "http://vbox7.com/play/magare.do"
-        data = compat_urllib_parse.urlencode({'as3':'1','vid':video_id})
-        info_request = compat_urllib_request.Request(info_url, data)
-        info_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
-        info_response = self._download_webpage(info_request, video_id, u'Downloading info webpage')
-        if info_response is None:
-            raise ExtractorError(u'Unable to extract the media url')
-        (final_url, thumbnail_url) = map(lambda x: x.split('=')[1], info_response.split('&'))
-
-        return [{
-            'id':        video_id,
-            'url':       final_url,
-            'ext':       ext,
-            'title':     title,
+    _VALID_URL = r'https?://(?:www\.)?vbox7\.com/(?:play:|emb/external\.php\?.*?\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',
+        },
+    }, {
+        'url': 'http://vbox7.com/play:249bb972c2',
+        'md5': '99f65c0c9ef9b682b97313e052734c3f',
+        'info_dict': {
+            'id': '249bb972c2',
+            '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,
+    }]
+
+    @staticmethod
+    def _extract_url(webpage):
+        mobj = re.search(
+            '<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)
+
+        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()
+
+        video_url = self._search_regex(
+            r'src\s*:\s*(["\'])(?P<url>.+?.mp4.*?)\1',
+            webpage, 'video url', default=None, group='url')
+
+        thumbnail_url = self._og_search_thumbnail(webpage)
+
+        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('&'))
+
+        if '/na.mp4' in video_url:
+            self.raise_geo_restricted()
+
+        return {
+            'id': video_id,
+            'url': self._proto_relative_url(video_url, 'http:'),
+            'title': title,
             'thumbnail': thumbnail_url,
-        }]
+        }