From 87724af7a8a22d00199fbda75c5b99f336386fca Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 13 May 2014 10:08:32 +0200 Subject: [PATCH] [nuvid] Simplify (#2901) --- youtube_dl/extractor/nuvid.py | 53 ++++++++++++++++++++--------------- 1 file changed, 31 insertions(+), 22 deletions(-) diff --git a/youtube_dl/extractor/nuvid.py b/youtube_dl/extractor/nuvid.py index 2e5198c1ab..f0befa1168 100644 --- a/youtube_dl/extractor/nuvid.py +++ b/youtube_dl/extractor/nuvid.py @@ -1,39 +1,48 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor + class NuvidIE(InfoExtractor): - _VALID_URL = r'^https?://(?:www|m)\.nuvid\.com/video/(?P\d+)' + _VALID_URL = r'^https?://(?:www|m)\.nuvid\.com/video/(?P[0-9]+)' _TEST = { - u'url': u'http://m.nuvid.com/video/1310741/', - u'file': u'1310741.mp4', - u'md5': u'eab207b7ac4fccfb4e23c86201f11277', - u'info_dict': { - u"title": u"Horny babes show their awesome bodeis and", - u"age_limit": 18, + 'url': 'http://m.nuvid.com/video/1310741/', + 'md5': 'eab207b7ac4fccfb4e23c86201f11277', + 'info_dict': { + 'id': '1310741', + 'ext': 'mp4', + "title": "Horny babes show their awesome bodeis and", + "age_limit": 18, } } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') - video_id = mobj.group('videoid') - - # Get webpage content - murl = url.replace('//www.', '//m.') + murl = url.replace('://www.', '://m.') webpage = self._download_webpage(murl, video_id) - video_title = self._html_search_regex(r'
\s+]*>([^<]+)', webpage, 'video_title').strip() + title = self._html_search_regex( + r'
\s+]*>([^<]+)', + webpage, 'title').strip() - video_url = 'http://m.nuvid.com'+self._html_search_regex(r'href="(/mp4/[^"]+)"[^>]*data-link_type="mp4"', webpage, 'video_url') + url_end = self._html_search_regex( + r'href="(/mp4/[^"]+)"[^>]*data-link_type="mp4"', + webpage, 'video_url') + video_url = 'http://m.nuvid.com' + url_end - video_thumb = self._html_search_regex(r'href="(/thumbs/[^"]+)"[^>]*data-link_type="thumbs"', webpage, 'video_thumb') + thumbnail = self._html_search_regex( + r'href="(/thumbs/[^"]+)"[^>]*data-link_type="thumbs"', + webpage, 'thumbnail URL', fatal=False) - info = {'id': video_id, - 'url': video_url, - 'title': video_title, - 'thumbnail': video_thumb, - 'ext': 'mp4', - 'age_limit': 18} - - return [info] + return { + 'id': video_id, + 'url': video_url, + 'ext': 'mp4', + 'title': title, + 'thumbnail': thumbnail, + 'age_limit': 18, + }