_ Git - youtube-dl/blob - youtube_dl/extractor/openload.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     determine_ext,
   9     ExtractorError,
  10     get_element_by_id,
  11     PhantomJSwrapper,
  12 )
  13
  14
  15 class OpenloadIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:openload\.(?:co|io)|oload\.tv)/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'
  17
  18     _TESTS = [{
  19         'url': 'https://openload.co/f/kUEfGclsU9o',
  20         'md5': 'bf1c059b004ebc7a256f89408e65c36e',
  21         'info_dict': {
  22             'id': 'kUEfGclsU9o',
  23             'ext': 'mp4',
  24             'title': 'skyrim_no-audio_1080.mp4',
  25             'thumbnail': r're:^https?://.*\.jpg$',
  26         },
  27     }, {
  28         'url': 'https://openload.co/embed/rjC09fkPLYs',
  29         'info_dict': {
  30             'id': 'rjC09fkPLYs',
  31             'ext': 'mp4',
  32             'title': 'movie.mp4',
  33             'thumbnail': r're:^https?://.*\.jpg$',
  34             'subtitles': {
  35                 'en': [{
  36                     'ext': 'vtt',
  37                 }],
  38             },
  39         },
  40         'params': {
  41             'skip_download': True,  # test subtitles only
  42         },
  43     }, {
  44         'url': 'https://openload.co/embed/kUEfGclsU9o/skyrim_no-audio_1080.mp4',
  45         'only_matching': True,
  46     }, {
  47         'url': 'https://openload.io/f/ZAn6oz-VZGE/',
  48         'only_matching': True,
  49     }, {
  50         'url': 'https://openload.co/f/_-ztPaZtMhM/',
  51         'only_matching': True,
  52     }, {
  53         # unavailable via https://openload.co/f/Sxz5sADo82g/, different layout
  54         # for title and ext
  55         'url': 'https://openload.co/embed/Sxz5sADo82g/',
  56         'only_matching': True,
  57     }, {
  58         'url': 'https://oload.tv/embed/KnG-kKZdcfY/',
  59         'only_matching': True,
  60     }]
  61
  62     _USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'
  63
  64     @staticmethod
  65     def _extract_urls(webpage):
  66         return re.findall(
  67             r'<iframe[^>]+src=["\']((?:https?://)?(?:openload\.(?:co|io)|oload\.tv)/embed/[a-zA-Z0-9-_]+)',
  68             webpage)
  69
  70     def _real_extract(self, url):
  71         video_id = self._match_id(url)
  72         url = 'https://openload.co/embed/%s/' % video_id
  73         headers = {
  74             'User-Agent': self._USER_AGENT,
  75         }
  76
  77         webpage = self._download_webpage(url, video_id, headers=headers)
  78
  79         if 'File not found' in webpage or 'deleted by the owner' in webpage:
  80             raise ExtractorError('File not found', expected=True, video_id=video_id)
  81
  82         phantom = PhantomJSwrapper(self, required_version='2.0')
  83         webpage, _ = phantom.get(url, html=webpage, video_id=video_id, headers=headers)
  84
  85         decoded_id = get_element_by_id('streamurl', webpage)
  86
  87         video_url = 'https://openload.co/stream/%s?mime=true' % decoded_id
  88
  89         title = self._og_search_title(webpage, default=None) or self._search_regex(
  90             r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage,
  91             'title', default=None) or self._html_search_meta(
  92             'description', webpage, 'title', fatal=True)
  93
  94         entries = self._parse_html5_media_entries(url, webpage, video_id)
  95         entry = entries[0] if entries else {}
  96         subtitles = entry.get('subtitles')
  97
  98         info_dict = {
  99             'id': video_id,
 100             'title': title,
 101             'thumbnail': entry.get('thumbnail') or self._og_search_thumbnail(webpage, default=None),
 102             'url': video_url,
 103             # Seems all videos have extensions in their titles
 104             'ext': determine_ext(title, 'mp4'),
 105             'subtitles': subtitles,
 106             'http_headers': headers,
 107         }
 108         return info_dict