X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fnuvid.py;h=ab6bfcd7f485218d19034930607d35d1665e7406;hb=HEAD;hp=2e5198c1ab2e0aede932f63ca050fe4f1d0d9e6f;hpb=b65c3e77e8fa893a41eb058102422f42276ebc11;p=youtube-dl diff --git a/youtube_dl/extractor/nuvid.py b/youtube_dl/extractor/nuvid.py index 2e5198c1a..ab6bfcd7f 100644 --- a/youtube_dl/extractor/nuvid.py +++ b/youtube_dl/extractor/nuvid.py @@ -1,39 +1,71 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor +from ..utils import ( + parse_duration, +) + 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, + 'age_limit': 18, } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - - video_id = mobj.group('videoid') + video_id = self._match_id(url) - # Get webpage content - murl = url.replace('//www.', '//m.') - webpage = self._download_webpage(murl, video_id) + page_url = 'http://m.nuvid.com/video/%s' % video_id + webpage = self._download_webpage( + page_url, video_id, 'Downloading video page') + # When dwnld_speed exists and has a value larger than the MP4 file's + # bitrate, Nuvid returns the MP4 URL + # It's unit is 100bytes/millisecond, see mobile-nuvid-min.js for the algorithm + self._set_cookie('nuvid.com', 'dwnld_speed', '10.0') + mp4_webpage = self._download_webpage( + page_url, video_id, 'Downloading video page for MP4 format') - video_title = self._html_search_regex(r'
\s+]*>([^<]+)', webpage, 'video_title').strip() + html5_video_re = r'(?s)<(?:video|audio)[^<]*(?:>.*?]*)?\s+src=["\'](.*?)["\']', + video_url = self._html_search_regex(html5_video_re, webpage, video_id) + mp4_video_url = self._html_search_regex(html5_video_re, mp4_webpage, video_id) + formats = [{ + 'url': video_url, + }] + if mp4_video_url != video_url: + formats.append({ + 'url': mp4_video_url, + }) - video_url = 'http://m.nuvid.com'+self._html_search_regex(r'href="(/mp4/[^"]+)"[^>]*data-link_type="mp4"', webpage, 'video_url') + title = self._html_search_regex( + [r'', + r'
\s*]*>([^<]+)', + r']+class="title_thumb">([^<]+)'], 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})', + r']+class="view_time">([^<]+)'], webpage, 'duration', fatal=False)) - video_thumb = self._html_search_regex(r'href="(/thumbs/[^"]+)"[^>]*data-link_type="thumbs"', webpage, 'video_thumb') - - info = {'id': video_id, - 'url': video_url, - 'title': video_title, - 'thumbnail': video_thumb, - 'ext': 'mp4', - 'age_limit': 18} - - return [info] + return { + 'id': video_id, + 'title': title, + 'thumbnails': thumbnails, + 'thumbnail': thumbnail, + 'duration': duration, + 'age_limit': 18, + 'formats': formats, + }