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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     compat_urlparse,
   8     determine_ext,
   9     int_or_none,
  10 )
  11
  12
  13 class QuickVidIE(InfoExtractor):
  14     _VALID_URL = r'https?://(www\.)?quickvid\.org/watch\.php\?v=(?P<id>[a-zA-Z_0-9-]+)'
  15     _TEST = {
  16         'url': 'http://quickvid.org/watch.php?v=sUQT3RCG8dx',
  17         'md5': 'c0c72dd473f260c06c808a05d19acdc5',
  18         'info_dict': {
  19             'id': 'sUQT3RCG8dx',
  20             'ext': 'mp4',
  21             'title': 'Nick Offerman\'s Summer Reading Recap',
  22             'thumbnail': 're:^https?://.*\.(?:png|jpg|gif)$',
  23             'view_count': int,
  24         },
  25     }
  26
  27     def _real_extract(self, url):
  28         video_id = self._match_id(url)
  29         webpage = self._download_webpage(url, video_id)
  30
  31         title = self._html_search_regex(r'<h2>(.*?)</h2>', webpage, 'title')
  32         view_count = int_or_none(self._html_search_regex(
  33             r'(?s)<div id="views">(.*?)</div>',
  34             webpage, 'view count', fatal=False))
  35         video_code = self._search_regex(
  36             r'(?s)<video id="video"[^>]*>(.*?)</video>', webpage, 'video code')
  37         formats = [
  38             {
  39                 'url': compat_urlparse.urljoin(url, src),
  40                 'format_id': determine_ext(src, None),
  41             } for src in re.findall('<source\s+src="([^"]+)"', video_code)
  42         ]
  43         self._sort_formats(formats)
  44
  45         return {
  46             'id': video_id,
  47             'title': title,
  48             'formats': formats,
  49             'thumbnail': self._og_search_thumbnail(webpage),
  50             'view_count': view_count,
  51         }