yt-dlp/youtube_dl/extractor/nuvid.py

49 lines
1.4 KiB
Python
Raw Normal View History

2014-05-13 04:08:32 -04:00
from __future__ import unicode_literals
2014-05-12 06:48:40 -04:00
import re
from .common import InfoExtractor
2014-05-13 04:08:32 -04:00
2014-05-12 06:48:40 -04:00
class NuvidIE(InfoExtractor):
2014-05-13 04:08:32 -04:00
_VALID_URL = r'^https?://(?:www|m)\.nuvid\.com/video/(?P<id>[0-9]+)'
2014-05-12 06:48:40 -04:00
_TEST = {
2014-05-13 04:08:32 -04:00
'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,
2014-05-12 06:48:40 -04:00
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
2014-05-13 04:08:32 -04:00
video_id = mobj.group('id')
2014-05-12 06:48:40 -04:00
2014-05-13 04:08:32 -04:00
murl = url.replace('://www.', '://m.')
2014-05-12 06:48:40 -04:00
webpage = self._download_webpage(murl, video_id)
2014-05-13 04:08:32 -04:00
title = self._html_search_regex(
r'<div class="title">\s+<h2[^>]*>([^<]+)</h2>',
webpage, 'title').strip()
url_end = self._html_search_regex(
2014-05-27 07:46:30 -04:00
r'href="(/[^"]+)"[^>]*data-link_type="mp4"',
2014-05-13 04:08:32 -04:00
webpage, 'video_url')
video_url = 'http://m.nuvid.com' + url_end
thumbnail = self._html_search_regex(
r'href="(/thumbs/[^"]+)"[^>]*data-link_type="thumbs"',
webpage, 'thumbnail URL', fatal=False)
return {
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': title,
'thumbnail': thumbnail,
'age_limit': 18,
}