_ Git - youtube-dl/blob - youtube_dl/extractor/nuvid.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     parse_duration,
   8     unified_strdate,
   9     compat_urllib_request,
  10 )
  11
  12
  13 class NuvidIE(InfoExtractor):
  14     _VALID_URL = r'^https?://(?:www|m)\.nuvid\.com/video/(?P<id>[0-9]+)'
  15     _TEST = {
  16         'url': 'http://m.nuvid.com/video/1310741/',
  17         'md5': 'eab207b7ac4fccfb4e23c86201f11277',
  18         'info_dict': {
  19             'id': '1310741',
  20             'ext': 'mp4',
  21             'title': 'Horny babes show their awesome bodeis and',
  22             'duration': 129,
  23             'upload_date': '20140508',
  24             'age_limit': 18,
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         mobj = re.match(self._VALID_URL, url)
  30         video_id = mobj.group('id')
  31
  32         formats = []
  33
  34         for dwnld_speed, format_id in [(0, '3gp'), (5, 'mp4')]:
  35             request = compat_urllib_request.Request(
  36                 'http://m.nuvid.com/play/%s' % video_id)
  37             request.add_header('Cookie', 'skip_download_page=1; dwnld_speed=%d; adv_show=1' % dwnld_speed)
  38             webpage = self._download_webpage(
  39                 request, video_id, 'Downloading %s page' % format_id)
  40             video_url = self._html_search_regex(
  41                 r'<a href="([^"]+)"\s*>Continue to watch video', webpage, '%s video URL' % format_id, fatal=False)
  42             if not video_url:
  43                 continue
  44             formats.append({
  45                 'url': video_url,
  46                 'format_id': format_id,
  47             })
  48
  49         webpage = self._download_webpage(
  50             'http://m.nuvid.com/video/%s' % video_id, video_id, 'Downloading video page')
  51         title = self._html_search_regex(
  52             r'<div class="title">\s+<h2[^>]*>([^<]+)</h2>', webpage, 'title').strip()
  53         thumbnail = self._html_search_regex(
  54             r'href="(/thumbs/[^"]+)"[^>]*data-link_type="thumbs"',
  55             webpage, 'thumbnail URL', fatal=False)
  56         duration = parse_duration(self._html_search_regex(
  57             r'Length:\s*<span>(\d{2}:\d{2})</span>',webpage, 'duration', fatal=False))
  58         upload_date = unified_strdate(self._html_search_regex(
  59             r'Added:\s*<span>(\d{4}-\d{2}-\d{2})</span>', webpage, 'upload date', fatal=False))
  60
  61         return {
  62             'id': video_id,
  63             'title': title,
  64             'thumbnail': 'http://m.nuvid.com%s' % thumbnail,
  65             'duration': duration,
  66             'upload_date': upload_date,
  67             'age_limit': 18,
  68             'formats': formats,
  69         }