diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 50500ce0e0..197ab95319 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -72,6 +72,7 @@ from .kaltura import KalturaIE from .eagleplatform import EaglePlatformIE from .facebook import FacebookIE from .soundcloud import SoundcloudIE +from .vbox7 import Vbox7IE class GenericIE(InfoExtractor): @@ -1373,6 +1374,18 @@ class GenericIE(InfoExtractor): }, 'add_ie': [ArkenaIE.ie_key()], }, + { + 'url': 'http://nova.bg/news/view/2016/08/16/156543/%D0%BD%D0%B0-%D0%BA%D0%BE%D1%81%D1%8A%D0%BC-%D0%BE%D1%82-%D0%B2%D0%B7%D1%80%D0%B8%D0%B2-%D0%BE%D1%82%D1%86%D0%B5%D0%BF%D0%B8%D1%85%D0%B0-%D1%86%D1%8F%D0%BB-%D0%BA%D0%B2%D0%B0%D1%80%D1%82%D0%B0%D0%BB-%D0%B7%D0%B0%D1%80%D0%B0%D0%B4%D0%B8-%D0%B8%D0%B7%D1%82%D0%B8%D1%87%D0%B0%D0%BD%D0%B5-%D0%BD%D0%B0-%D0%B3%D0%B0%D0%B7-%D0%B2-%D0%BF%D0%BB%D0%BE%D0%B2%D0%B4%D0%B8%D0%B2/', + 'info_dict': { + 'id': '1c7141f46c', + 'ext': 'mp4', + 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив', + }, + 'params': { + 'skip_download': True, + }, + 'add_ie': [Vbox7IE.ie_key()], + }, # { # # TODO: find another test # # http://schema.org/VideoObject @@ -2239,6 +2252,11 @@ class GenericIE(InfoExtractor): 'uploader': video_uploader, } + # Look for VBOX7 embeds + vbox7_url = Vbox7IE._extract_url(webpage) + if vbox7_url: + return self.url_result(vbox7_url, Vbox7IE.ie_key()) + # Looking for http://schema.org/VideoObject json_ld = self._search_json_ld( webpage, video_id, default={}, expected_type='VideoObject') diff --git a/youtube_dl/extractor/vbox7.py b/youtube_dl/extractor/vbox7.py index 8e6d7efe72..e179885736 100644 --- a/youtube_dl/extractor/vbox7.py +++ b/youtube_dl/extractor/vbox7.py @@ -1,6 +1,8 @@ # encoding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..utils import urlencode_postdata @@ -29,6 +31,14 @@ class Vbox7IE(InfoExtractor): 'only_matching': True, }] + @staticmethod + def _extract_url(webpage): + mobj = re.search( + ']+src=(?P["\'])(?P(?: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)