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     sanitized_Request,
   9     unified_strdate,
  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         video_id = self._match_id(url)
  30
  31         formats = []
  32
  33         for dwnld_speed, format_id in [(0, '3gp'), (5, 'mp4')]:
  34             request = sanitized_Request(
  35                 'http://m.nuvid.com/play/%s' % video_id)
  36             request.add_header('Cookie', 'skip_download_page=1; dwnld_speed=%d; adv_show=1' % dwnld_speed)
  37             webpage = self._download_webpage(
  38                 request, video_id, 'Downloading %s page' % format_id)
  39             video_url = self._html_search_regex(
  40                 r'<a\s+href="([^"]+)"\s+class="b_link">', webpage, '%s video URL' % format_id, fatal=False)
  41             if not video_url:
  42                 continue
  43             formats.append({
  44                 'url': video_url,
  45                 'format_id': format_id,
  46             })
  47
  48         webpage = self._download_webpage(
  49             'http://m.nuvid.com/video/%s' % video_id, video_id, 'Downloading video page')
  50         title = self._html_search_regex(
  51             [r'<span title="([^"]+)">',
  52              r'<div class="thumb-holder video">\s*<h5[^>]*>([^<]+)</h5>'], webpage, 'title').strip()
  53         thumbnails = [
  54             {
  55                 'url': thumb_url,
  56             } for thumb_url in re.findall(r'<img src="([^"]+)" alt="" />', webpage)
  57         ]
  58         thumbnail = thumbnails[0]['url'] if thumbnails else None
  59         duration = parse_duration(self._html_search_regex(
  60             r'<i class="fa fa-clock-o"></i>\s*(\d{2}:\d{2})', webpage, 'duration', fatal=False))
  61         upload_date = unified_strdate(self._html_search_regex(
  62             r'<i class="fa fa-user"></i>\s*(\d{4}-\d{2}-\d{2})', webpage, 'upload date', fatal=False))
  63
  64         return {
  65             'id': video_id,
  66             'title': title,
  67             'thumbnails': thumbnails,
  68             'thumbnail': thumbnail,
  69             'duration': duration,
  70             'upload_date': upload_date,
  71             'age_limit': 18,
  72             'formats': formats,
  73         }