Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/manyvids.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import int_or_none
   6
   7
   8 class ManyVidsIE(InfoExtractor):
   9     _VALID_URL = r'(?i)https?://(?:www\.)?manyvids\.com/video/(?P<id>\d+)'
  10     _TEST = {
  11         'url': 'https://www.manyvids.com/Video/133957/everthing-about-me/',
  12         'md5': '03f11bb21c52dd12a05be21a5c7dcc97',
  13         'info_dict': {
  14             'id': '133957',
  15             'ext': 'mp4',
  16             'title': 'everthing about me (Preview)',
  17             'view_count': int,
  18             'like_count': int,
  19         },
  20     }
  21
  22     def _real_extract(self, url):
  23         video_id = self._match_id(url)
  24
  25         webpage = self._download_webpage(url, video_id)
  26
  27         video_url = self._search_regex(
  28             r'data-(?:video-filepath|meta-video)\s*=s*(["\'])(?P<url>(?:(?!\1).)+)\1',
  29             webpage, 'video URL', group='url')
  30
  31         title = '%s (Preview)' % self._html_search_regex(
  32             r'<h2[^>]+class="m-a-0"[^>]*>([^<]+)', webpage, 'title')
  33
  34         like_count = int_or_none(self._search_regex(
  35             r'data-likes=["\'](\d+)', webpage, 'like count', default=None))
  36         view_count = int_or_none(self._html_search_regex(
  37             r'(?s)<span[^>]+class="views-wrapper"[^>]*>(.+?)</span', webpage,
  38             'view count', default=None))
  39
  40         return {
  41             'id': video_id,
  42             'title': title,
  43             'view_count': view_count,
  44             'like_count': like_count,
  45             'formats': [{
  46                 'url': video_url,
  47             }],
  48         }