depau/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-22 02:01:50 +00:00
Code Issues Releases Wiki Activity

[nuvid] Simplify (#2901)

Browse source
This commit is contained in:
Philipp Hagemeister 2014-05-13 10:08:32 +02:00
parent b65c3e77e8
commit 87724af7a8
1 changed files with 31 additions and 22 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

53
youtube_dl/extractor/nuvid.py
View file

@ -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<videoid>\d+)'
_VALID_URL = r'^https?://(?:www|m)\.nuvid\.com/video/(?P<id>[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'<div class="title">\s+<h2[^>]*>([^<]+)</h2>', webpage, 'video_title').strip()
title = self._html_search_regex(
r'<div class="title">\s+<h2[^>]*>([^<]+)</h2>',
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,
}