youtube_dl/extractor/veehd.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4 import json
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_urllib_parse_unquote,
   9     compat_urlparse,
  10 )
  11 from ..utils import (
  12     ExtractorError,
  13     clean_html,
  14     get_element_by_id,
  15 )
  16
  17
  18 class VeeHDIE(InfoExtractor):
  19     _VALID_URL = r'https?://veehd\.com/video/(?P<id>\d+)'
  20
  21     # Seems VeeHD videos have multiple copies on several servers, all of
  22     # whom have different MD5 checksums, so omit md5 field in all tests
  23     _TESTS = [{
  24         'url': 'http://veehd.com/video/4639434_Solar-Sinter',
  25         'info_dict': {
  26             'id': '4639434',
  27             'ext': 'mp4',
  28             'title': 'Solar Sinter',
  29             'uploader_id': 'VideoEyes',
  30             'description': 'md5:46a840e8692ddbaffb5f81d9885cb457',
  31         },
  32         'skip': 'Video deleted',
  33     }, {
  34         'url': 'http://veehd.com/video/4905758_Elysian-Fields-Channeling',
  35         'info_dict': {
  36             'id': '4905758',
  37             'ext': 'mp4',
  38             'title': 'Elysian Fields - Channeling',
  39             'description': 'md5:360e4e95fdab58aefbea0f2a19e5604b',
  40             'uploader_id': 'spotted',
  41         }
  42     }, {
  43         'url': 'http://veehd.com/video/2046729_2012-2009-DivX-Trailer',
  44         'info_dict': {
  45             'id': '2046729',
  46             'ext': 'avi',
  47             'title': '2012 (2009) DivX Trailer',
  48             'description': 'md5:75435ee95255e6a9838ac6f6f3a2396b',
  49             'uploader_id': 'Movie_Trailers',
  50         }
  51     }]
  52
  53     def _real_extract(self, url):
  54         video_id = self._match_id(url)
  55
  56         # VeeHD seems to send garbage on the first request.
  57         # See https://github.com/ytdl-org/youtube-dl/issues/2102
  58         self._download_webpage(url, video_id, 'Requesting webpage')
  59         webpage = self._download_webpage(url, video_id)
  60
  61         if 'This video has been removed<' in webpage:
  62             raise ExtractorError('Video %s has been removed' % video_id, expected=True)
  63
  64         player_path = self._search_regex(
  65             r'\$\("#playeriframe"\).attr\({src : "(.+?)"',
  66             webpage, 'player path')
  67         player_url = compat_urlparse.urljoin(url, player_path)
  68
  69         self._download_webpage(player_url, video_id, 'Requesting player page')
  70         player_page = self._download_webpage(
  71             player_url, video_id, 'Downloading player page')
  72
  73         video_url = None
  74
  75         config_json = self._search_regex(
  76             r'value=\'config=({.+?})\'', player_page, 'config json', default=None)
  77
  78         if config_json:
  79             config = json.loads(config_json)
  80             video_url = compat_urllib_parse_unquote(config['clip']['url'])
  81
  82         if not video_url:
  83             video_url = self._html_search_regex(
  84                 r'<embed[^>]+type="video/divx"[^>]+src="([^"]+)"',
  85                 player_page, 'video url', default=None)
  86
  87         if not video_url:
  88             iframe_src = self._search_regex(
  89                 r'<iframe[^>]+src="/?([^"]+)"', player_page, 'iframe url')
  90             iframe_url = 'http://veehd.com/%s' % iframe_src
  91
  92             self._download_webpage(iframe_url, video_id, 'Requesting iframe page')
  93             iframe_page = self._download_webpage(
  94                 iframe_url, video_id, 'Downloading iframe page')
  95
  96             video_url = self._search_regex(
  97                 r"file\s*:\s*'([^']+)'", iframe_page, 'video url')
  98
  99         title = clean_html(get_element_by_id('videoName', webpage).rpartition('|')[0])
 100         uploader_id = self._html_search_regex(
 101             r'<a href="/profile/\d+">(.+?)</a>',
 102             webpage, 'uploader')
 103         thumbnail = self._search_regex(
 104             r'<img id="veehdpreview" src="(.+?)"',
 105             webpage, 'thumbnail')
 106         description = self._html_search_regex(
 107             r'<td class="infodropdown".*?<div>(.*?)<ul',
 108             webpage, 'description', flags=re.DOTALL)
 109
 110         return {
 111             '_type': 'video',
 112             'id': video_id,
 113             'title': title,
 114             'url': video_url,
 115             'uploader_id': uploader_id,
 116             'thumbnail': thumbnail,
 117             'description': description,
 118         }