X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;ds=sidebyside;f=youtube_dl%2Fextractor%2Fvbox7.py;h=fa7899e6dbd779fa824e1c4cdfdf16b76a8716eb;hb=d2ac04674d0d9085aedec229820c1d07082e5825;hp=5a136a9527613e2fb076c1169b3ef5e90c24eafd;hpb=9fc3bef87a1009eb48f2012f3eab65761a53ba5e;p=youtube-dl
diff --git a/youtube_dl/extractor/vbox7.py b/youtube_dl/extractor/vbox7.py
index 5a136a952..fa7899e6d 100644
--- a/youtube_dl/extractor/vbox7.py
+++ b/youtube_dl/extractor/vbox7.py
@@ -1,54 +1,60 @@
-import re
+# encoding: utf-8
+from __future__ import unicode_literals
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'99f65c0c9ef9b682b97313e052734c3f',
- 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'
(.*)',
- 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:(?P[^/]+)'
+ _TESTS = [{
+ 'url': 'http://vbox7.com/play:0946fff23c',
+ 'md5': 'a60f9ab3a3a2f013ef9a967d5f7be5bf',
+ 'info_dict': {
+ 'id': '0946fff23c',
+ 'ext': 'mp4',
+ 'title': 'ÐоÑиÑов: ÐÑиÑеÑнен ÑÑм за бÑдеÑеÑо на ÐÑлгаÑиÑ',
+ },
+ }, {
+ 'url': 'http://vbox7.com/play:249bb972c2',
+ 'md5': '99f65c0c9ef9b682b97313e052734c3f',
+ 'info_dict': {
+ 'id': '249bb972c2',
+ 'ext': 'mp4',
+ 'title': 'СмÑÑ
! ЧÑдо - ÑиÑÑ Ð·Ð° ÑекÑнди - СкÑиÑа камеÑа',
+ },
+ 'skip': 'georestricted',
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, video_id)
+
+ title = self._html_search_regex(
+ r'(.*)', webpage, 'title').split('/')[0].strip()
+
+ video_url = self._search_regex(
+ r'src\s*:\s*(["\'])(?P.+?.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,
- }]
+ }