_ 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 ..compat import (
   7     compat_urllib_request,
   8 )
   9 from ..utils import (
  10     parse_duration,
  11     unified_strdate,
  12 )
  13
  14
  15 class NuvidIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www|m)\.nuvid\.com/video/(?P<id>[0-9]+)'
  17     _TEST = {
  18         'url': 'http://m.nuvid.com/video/1310741/',
  19         'md5': 'eab207b7ac4fccfb4e23c86201f11277',
  20         'info_dict': {
  21             'id': '1310741',
  22             'ext': 'mp4',
  23             'title': 'Horny babes show their awesome bodeis and',
  24             'duration': 129,
  25             'upload_date': '20140508',
  26             'age_limit': 18,
  27         }
  28     }
  29
  30     def _real_extract(self, url):
  31         video_id = self._match_id(url)
  32
  33         formats = []
  34
  35         for dwnld_speed, format_id in [(0, '3gp'), (5, 'mp4')]:
  36             request = compat_urllib_request.Request(
  37                 'http://m.nuvid.com/play/%s' % video_id)
  38             request.add_header('Cookie', 'skip_download_page=1; dwnld_speed=%d; adv_show=1' % dwnld_speed)
  39             webpage = self._download_webpage(
  40                 request, video_id, 'Downloading %s page' % format_id)
  41             video_url = self._html_search_regex(
  42                 r'<a\s+href="([^"]+)"\s+class="b_link">', webpage, '%s video URL' % format_id, fatal=False)
  43             if not video_url:
  44                 continue
  45             formats.append({
  46                 'url': video_url,
  47                 'format_id': format_id,
  48             })
  49
  50         webpage = self._download_webpage(
  51             'http://m.nuvid.com/video/%s' % video_id, video_id, 'Downloading video page')
  52         title = self._html_search_regex(
  53             [r'<span title="([^"]+)">',
  54              r'<div class="thumb-holder video">\s*<h5[^>]*>([^<]+)</h5>'], webpage, 'title').strip()
  55         thumbnails = [
  56             {
  57                 'url': thumb_url,
  58             } for thumb_url in re.findall(r'<img src="([^"]+)" alt="" />', webpage)
  59         ]
  60         thumbnail = thumbnails[0]['url'] if thumbnails else None
  61         duration = parse_duration(self._html_search_regex(
  62             r'<i class="fa fa-clock-o"></i>\s*(\d{2}:\d{2})', webpage, 'duration', fatal=False))
  63         upload_date = unified_strdate(self._html_search_regex(
  64             r'<i class="fa fa-user"></i>\s*(\d{4}-\d{2}-\d{2})', webpage, 'upload date', fatal=False))
  65
  66         return {
  67             'id': video_id,
  68             'title': title,
  69             'thumbnails': thumbnails,
  70             'thumbnail': thumbnail,
  71             'duration': duration,
  72             'upload_date': upload_date,
  73             'age_limit': 18,
  74             'formats': formats,
  75         }