Raphaël G. Git Repositories - youtubedl/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\s+href="([^"]+)"\s+class="b_link">', 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'<span title="([^"]+)">',
  53              r'<div class="thumb-holder video">\s*<h5[^>]*>([^<]+)</h5>'], webpage, 'title').strip()
  54         thumbnails = [
  55             {
  56                 'url': thumb_url,
  57             } for thumb_url in re.findall(r'<img src="([^"]+)" alt="" />', webpage)
  58         ]
  59         thumbnail = thumbnails[0]['url'] if thumbnails else None
  60         duration = parse_duration(self._html_search_regex(
  61             r'<i class="fa fa-clock-o"></i>\s*(\d{2}:\d{2})', webpage, 'duration', fatal=False))
  62         upload_date = unified_strdate(self._html_search_regex(
  63             r'<i class="fa fa-user"></i>\s*(\d{4}-\d{2}-\d{2})', webpage, 'upload date', fatal=False))
  64
  65         return {
  66             'id': video_id,
  67             'title': title,
  68             'thumbnails': thumbnails,
  69             'thumbnail': thumbnail,
  70             'duration': duration,
  71             'upload_date': upload_date,
  72             'age_limit': 18,
  73             'formats': formats,
  74         }