youtube_dl/extractor/openload.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_chr
   6 from ..utils import (
   7     determine_ext,
   8     ExtractorError,
   9 )
  10
  11
  12 class OpenloadIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:openload\.(?:co|io)|oload\.tv)/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'
  14
  15     _TESTS = [{
  16         'url': 'https://openload.co/f/kUEfGclsU9o',
  17         'md5': 'bf1c059b004ebc7a256f89408e65c36e',
  18         'info_dict': {
  19             'id': 'kUEfGclsU9o',
  20             'ext': 'mp4',
  21             'title': 'skyrim_no-audio_1080.mp4',
  22             'thumbnail': r're:^https?://.*\.jpg$',
  23         },
  24     }, {
  25         'url': 'https://openload.co/embed/rjC09fkPLYs',
  26         'info_dict': {
  27             'id': 'rjC09fkPLYs',
  28             'ext': 'mp4',
  29             'title': 'movie.mp4',
  30             'thumbnail': r're:^https?://.*\.jpg$',
  31             'subtitles': {
  32                 'en': [{
  33                     'ext': 'vtt',
  34                 }],
  35             },
  36         },
  37         'params': {
  38             'skip_download': True,  # test subtitles only
  39         },
  40     }, {
  41         'url': 'https://openload.co/embed/kUEfGclsU9o/skyrim_no-audio_1080.mp4',
  42         'only_matching': True,
  43     }, {
  44         'url': 'https://openload.io/f/ZAn6oz-VZGE/',
  45         'only_matching': True,
  46     }, {
  47         'url': 'https://openload.co/f/_-ztPaZtMhM/',
  48         'only_matching': True,
  49     }, {
  50         # unavailable via https://openload.co/f/Sxz5sADo82g/, different layout
  51         # for title and ext
  52         'url': 'https://openload.co/embed/Sxz5sADo82g/',
  53         'only_matching': True,
  54     }, {
  55         'url': 'https://oload.tv/embed/KnG-kKZdcfY/',
  56         'only_matching': True,
  57     }]
  58
  59     def _real_extract(self, url):
  60         video_id = self._match_id(url)
  61         webpage = self._download_webpage('https://openload.co/embed/%s/' % video_id, video_id)
  62
  63         if 'File not found' in webpage or 'deleted by the owner' in webpage:
  64             raise ExtractorError('File not found', expected=True)
  65
  66         ol_id = self._search_regex(
  67             '<span[^>]+id="[a-zA-Z0-9]+x"[^>]*>([0-9]+)</span>',
  68             webpage, 'openload ID')
  69
  70         first_two_chars = int(float(ol_id[0:][:2]))
  71         urlcode = ''
  72         num = 2
  73
  74         while num < len(ol_id):
  75             urlcode += compat_chr(int(float(ol_id[num:][:3])) -
  76                                   first_two_chars * int(float(ol_id[num + 3:][:2])))
  77             num += 5
  78
  79         video_url = 'https://openload.co/stream/' + urlcode
  80
  81         title = self._og_search_title(webpage, default=None) or self._search_regex(
  82             r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage,
  83             'title', default=None) or self._html_search_meta(
  84             'description', webpage, 'title', fatal=True)
  85
  86         entries = self._parse_html5_media_entries(url, webpage, video_id)
  87         subtitles = entries[0]['subtitles'] if entries else None
  88
  89         info_dict = {
  90             'id': video_id,
  91             'title': title,
  92             'thumbnail': self._og_search_thumbnail(webpage, default=None),
  93             'url': video_url,
  94             # Seems all videos have extensions in their titles
  95             'ext': determine_ext(title),
  96             'subtitles': subtitles,
  97         }
  98         return info_dict