youtube_dl/extractor/vidme.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     int_or_none,
   6     float_or_none,
   7     str_to_int,
   8 )
   9
  10
  11 class VidmeIE(InfoExtractor):
  12     _VALID_URL = r'https?://vid\.me/(?:e/)?(?P<id>[\da-zA-Z]+)'
  13     _TESTS = [{
  14         'url': 'https://vid.me/QNB',
  15         'md5': 'f42d05e7149aeaec5c037b17e5d3dc82',
  16         'info_dict': {
  17             'id': 'QNB',
  18             'ext': 'mp4',
  19             'title': 'Fishing for piranha - the easy way',
  20             'description': 'source: https://www.facebook.com/photo.php?v=312276045600871',
  21             'duration': 119.92,
  22             'timestamp': 1406313244,
  23             'upload_date': '20140725',
  24             'thumbnail': 're:^https?://.*\.jpg',
  25             'view_count': int,
  26             'like_count': int,
  27         },
  28     }, {
  29         # tests uploader field
  30         'url': 'https://vid.me/4Iib',
  31         'info_dict': {
  32             'id': '4Iib',
  33             'ext': 'mp4',
  34             'title': 'The Carver',
  35             'description': 'md5:e9c24870018ae8113be936645b93ba3c',
  36             'duration': 97.859999999999999,
  37             'timestamp': 1433203629,
  38             'upload_date': '20150602',
  39             'uploader': 'Thomas',
  40             'thumbnail': 're:^https?://.*\.jpg',
  41             'view_count': int,
  42             'like_count': int,
  43         },
  44         'params': {
  45             'skip_download': True,
  46         },
  47     }, {
  48         # From http://naked-yogi.tumblr.com/post/118312946248/naked-smoking-stretching
  49         'url': 'https://vid.me/e/Wmur',
  50         'only_matching': True,
  51     }]
  52
  53     def _real_extract(self, url):
  54         url = url.replace('vid.me/e/', 'vid.me/')
  55         video_id = self._match_id(url)
  56         webpage = self._download_webpage(url, video_id)
  57
  58         video_url = self._html_search_regex(
  59             r'<source src="([^"]+)"', webpage, 'video URL')
  60
  61         title = self._og_search_title(webpage)
  62         description = self._og_search_description(webpage, default='')
  63         thumbnail = self._og_search_thumbnail(webpage)
  64         timestamp = int_or_none(self._og_search_property(
  65             'updated_time', webpage, fatal=False))
  66         width = int_or_none(self._og_search_property(
  67             'video:width', webpage, fatal=False))
  68         height = int_or_none(self._og_search_property(
  69             'video:height', webpage, fatal=False))
  70         duration = float_or_none(self._html_search_regex(
  71             r'data-duration="([^"]+)"', webpage, 'duration', fatal=False))
  72         view_count = str_to_int(self._html_search_regex(
  73             r'<(?:li|span) class="video_views">\s*([\d,\.]+)\s*plays?',
  74             webpage, 'view count', fatal=False))
  75         like_count = str_to_int(self._html_search_regex(
  76             r'class="score js-video-vote-score"[^>]+data-score="([\d,\.\s]+)">',
  77             webpage, 'like count', fatal=False))
  78         uploader = self._html_search_regex(
  79             'class="video_author_username"[^>]*>([^<]+)',
  80             webpage, 'uploader', default=None)
  81
  82         return {
  83             'id': video_id,
  84             'url': video_url,
  85             'title': title,
  86             'description': description,
  87             'thumbnail': thumbnail,
  88             'timestamp': timestamp,
  89             'width': width,
  90             'height': height,
  91             'duration': duration,
  92             'view_count': view_count,
  93             'like_count': like_count,
  94             'uploader': uploader,
  95         }