X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fnuvid.py;h=9fa7cefadc79ef1d8bda971dc52483a0b8d998eb;hb=3047121c639428235191ff5f7afbda7ecda38779;hp=2e5198c1ab2e0aede932f63ca050fe4f1d0d9e6f;hpb=749fe60c1eaa157db4360edf55cf41a10489f349;p=youtube-dl diff --git a/youtube_dl/extractor/nuvid.py b/youtube_dl/extractor/nuvid.py index 2e5198c1a..9fa7cefad 100644 --- a/youtube_dl/extractor/nuvid.py +++ b/youtube_dl/extractor/nuvid.py @@ -1,39 +1,73 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor +from ..utils import ( + parse_duration, + sanitized_Request, + unified_strdate, +) + 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', + 'duration': 129, + 'upload_date': '20140508', + 'age_limit': 18, } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - - video_id = mobj.group('videoid') - - # Get webpage content - murl = url.replace('//www.', '//m.') - webpage = self._download_webpage(murl, video_id) + video_id = self._match_id(url) - video_title = self._html_search_regex(r'
\s+]*>([^<]+)', webpage, 'video_title').strip() + formats = [] - video_url = 'http://m.nuvid.com'+self._html_search_regex(r'href="(/mp4/[^"]+)"[^>]*data-link_type="mp4"', webpage, 'video_url') - - video_thumb = self._html_search_regex(r'href="(/thumbs/[^"]+)"[^>]*data-link_type="thumbs"', webpage, 'video_thumb') - - info = {'id': video_id, + for dwnld_speed, format_id in [(0, '3gp'), (5, 'mp4')]: + request = sanitized_Request( + 'http://m.nuvid.com/play/%s' % video_id) + request.add_header('Cookie', 'skip_download_page=1; dwnld_speed=%d; adv_show=1' % dwnld_speed) + webpage = self._download_webpage( + request, video_id, 'Downloading %s page' % format_id) + video_url = self._html_search_regex( + r'', webpage, '%s video URL' % format_id, fatal=False) + if not video_url: + continue + formats.append({ 'url': video_url, - 'title': video_title, - 'thumbnail': video_thumb, - 'ext': 'mp4', - 'age_limit': 18} + 'format_id': format_id, + }) - return [info] + webpage = self._download_webpage( + 'http://m.nuvid.com/video/%s' % video_id, video_id, 'Downloading video page') + title = self._html_search_regex( + [r'', + r'
\s*]*>([^<]+)'], webpage, 'title').strip() + thumbnails = [ + { + 'url': thumb_url, + } for thumb_url in re.findall(r'', webpage) + ] + thumbnail = thumbnails[0]['url'] if thumbnails else None + duration = parse_duration(self._html_search_regex( + r'\s*(\d{2}:\d{2})', webpage, 'duration', fatal=False)) + upload_date = unified_strdate(self._html_search_regex( + r'\s*(\d{4}-\d{2}-\d{2})', webpage, 'upload date', fatal=False)) + + return { + 'id': video_id, + 'title': title, + 'thumbnails': thumbnails, + 'thumbnail': thumbnail, + 'duration': duration, + 'upload_date': upload_date, + 'age_limit': 18, + 'formats': formats, + }