yt_dlp/extractor/veehd.py

   1 import re
   2 import json
   3
   4 from .common import InfoExtractor
   5 from ..compat import (
   6     compat_urllib_parse_unquote,
   7     compat_urlparse,
   8 )
   9 from ..utils import (
  10     ExtractorError,
  11     clean_html,
  12     get_element_by_id,
  13 )
  14
  15
  16 class VeeHDIE(InfoExtractor):
  17     _VALID_URL = r'https?://veehd\.com/video/(?P<id>\d+)'
  18
  19     # Seems VeeHD videos have multiple copies on several servers, all of
  20     # whom have different MD5 checksums, so omit md5 field in all tests
  21     _TESTS = [{
  22         'url': 'http://veehd.com/video/4639434_Solar-Sinter',
  23         'info_dict': {
  24             'id': '4639434',
  25             'ext': 'mp4',
  26             'title': 'Solar Sinter',
  27             'uploader_id': 'VideoEyes',
  28             'description': 'md5:46a840e8692ddbaffb5f81d9885cb457',
  29         },
  30         'skip': 'Video deleted',
  31     }, {
  32         'url': 'http://veehd.com/video/4905758_Elysian-Fields-Channeling',
  33         'info_dict': {
  34             'id': '4905758',
  35             'ext': 'mp4',
  36             'title': 'Elysian Fields - Channeling',
  37             'description': 'md5:360e4e95fdab58aefbea0f2a19e5604b',
  38             'uploader_id': 'spotted',
  39         }
  40     }, {
  41         'url': 'http://veehd.com/video/2046729_2012-2009-DivX-Trailer',
  42         'info_dict': {
  43             'id': '2046729',
  44             'ext': 'avi',
  45             'title': '2012 (2009) DivX Trailer',
  46             'description': 'md5:75435ee95255e6a9838ac6f6f3a2396b',
  47             'uploader_id': 'Movie_Trailers',
  48         }
  49     }]
  50
  51     def _real_extract(self, url):
  52         video_id = self._match_id(url)
  53
  54         # VeeHD seems to send garbage on the first request.
  55         # See https://github.com/ytdl-org/youtube-dl/issues/2102
  56         self._download_webpage(url, video_id, 'Requesting webpage')
  57         webpage = self._download_webpage(url, video_id)
  58
  59         if 'This video has been removed<' in webpage:
  60             raise ExtractorError('Video %s has been removed' % video_id, expected=True)
  61
  62         player_path = self._search_regex(
  63             r'\$\("#playeriframe"\).attr\({src : "(.+?)"',
  64             webpage, 'player path')
  65         player_url = compat_urlparse.urljoin(url, player_path)
  66
  67         self._download_webpage(player_url, video_id, 'Requesting player page')
  68         player_page = self._download_webpage(
  69             player_url, video_id, 'Downloading player page')
  70
  71         video_url = None
  72
  73         config_json = self._search_regex(
  74             r'value=\'config=({.+?})\'', player_page, 'config json', default=None)
  75
  76         if config_json:
  77             config = json.loads(config_json)
  78             video_url = compat_urllib_parse_unquote(config['clip']['url'])
  79
  80         if not video_url:
  81             video_url = self._html_search_regex(
  82                 r'<embed[^>]+type="video/divx"[^>]+src="([^"]+)"',
  83                 player_page, 'video url', default=None)
  84
  85         if not video_url:
  86             iframe_src = self._search_regex(
  87                 r'<iframe[^>]+src="/?([^"]+)"', player_page, 'iframe url')
  88             iframe_url = 'http://veehd.com/%s' % iframe_src
  89
  90             self._download_webpage(iframe_url, video_id, 'Requesting iframe page')
  91             iframe_page = self._download_webpage(
  92                 iframe_url, video_id, 'Downloading iframe page')
  93
  94             video_url = self._search_regex(
  95                 r"file\s*:\s*'([^']+)'", iframe_page, 'video url')
  96
  97         title = clean_html(get_element_by_id('videoName', webpage).rpartition('|')[0])
  98         uploader_id = self._html_search_regex(
  99             r'<a href="/profile/\d+">(.+?)</a>',
 100             webpage, 'uploader')
 101         thumbnail = self._search_regex(
 102             r'<img id="veehdpreview" src="(.+?)"',
 103             webpage, 'thumbnail')
 104         description = self._html_search_regex(
 105             r'<td class="infodropdown".*?<div>(.*?)<ul',
 106             webpage, 'description', flags=re.DOTALL)
 107
 108         return {
 109             '_type': 'video',
 110             'id': video_id,
 111             'title': title,
 112             'url': video_url,
 113             'uploader_id': uploader_id,
 114             'thumbnail': thumbnail,
 115             'description': description,
 116         }