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_urlparse,
   9 )
  10 from ..utils import (
  11     ExtractorError,
  12     clean_html,
  13     get_element_by_id,
  14 )
  15
  16
  17 class VeeHDIE(InfoExtractor):
  18     _VALID_URL = r'https?://veehd\.com/video/(?P<id>\d+)'
  19
  20     # Seems VeeHD videos have multiple copies on several servers, all of
  21     # whom have different MD5 checksums, so omit md5 field in all tests
  22     _TESTS = [{
  23         'url': 'http://veehd.com/video/4639434_Solar-Sinter',
  24         'info_dict': {
  25             'id': '4639434',
  26             'ext': 'mp4',
  27             'title': 'Solar Sinter',
  28             'uploader_id': 'VideoEyes',
  29             'description': 'md5:46a840e8692ddbaffb5f81d9885cb457',
  30         },
  31         'skip': 'Video deleted',
  32     }, {
  33         'url': 'http://veehd.com/video/4905758_Elysian-Fields-Channeling',
  34         'info_dict': {
  35             'id': '4905758',
  36             'ext': 'mp4',
  37             'title': 'Elysian Fields - Channeling',
  38             'description': 'md5:360e4e95fdab58aefbea0f2a19e5604b',
  39             'uploader_id': 'spotted',
  40         }
  41     }, {
  42         'url': 'http://veehd.com/video/2046729_2012-2009-DivX-Trailer',
  43         'info_dict': {
  44             'id': '2046729',
  45             'ext': 'avi',
  46             'title': '2012 (2009) DivX Trailer',
  47             'description': 'md5:75435ee95255e6a9838ac6f6f3a2396b',
  48             'uploader_id': 'Movie_Trailers',
  49         }
  50     }]
  51
  52     def _real_extract(self, url):
  53         video_id = self._match_id(url)
  54
  55         # VeeHD seems to send garbage on the first request.
  56         # See https://github.com/rg3/youtube-dl/issues/2102
  57         self._download_webpage(url, video_id, 'Requesting webpage')
  58         webpage = self._download_webpage(url, video_id)
  59
  60         if 'This video has been removed<' in webpage:
  61             raise ExtractorError('Video %s has been removed' % video_id, expected=True)
  62
  63         player_path = self._search_regex(
  64             r'\$\("#playeriframe"\).attr\({src : "(.+?)"',
  65             webpage, 'player path')
  66         player_url = compat_urlparse.urljoin(url, player_path)
  67
  68         self._download_webpage(player_url, video_id, 'Requesting player page')
  69         player_page = self._download_webpage(
  70             player_url, video_id, 'Downloading player page')
  71
  72         video_url = None
  73
  74         config_json = self._search_regex(
  75             r'value=\'config=({.+?})\'', player_page, 'config json', default=None)
  76
  77         if config_json:
  78             config = json.loads(config_json)
  79             video_url = compat_urlparse.unquote(config['clip']['url'])
  80
  81         if not video_url:
  82             video_url = self._html_search_regex(
  83                 r'<embed[^>]+type="video/divx"[^>]+src="([^"]+)"',
  84                 player_page, 'video url', default=None)
  85
  86         if not video_url:
  87             iframe_src = self._search_regex(
  88                 r'<iframe[^>]+src="/?([^"]+)"', player_page, 'iframe url')
  89             iframe_url = 'http://veehd.com/%s' % iframe_src
  90
  91             self._download_webpage(iframe_url, video_id, 'Requesting iframe page')
  92             iframe_page = self._download_webpage(
  93                 iframe_url, video_id, 'Downloading iframe page')
  94
  95             video_url = self._search_regex(
  96                 r"file\s*:\s*'([^']+)'", iframe_page, 'video url')
  97
  98         title = clean_html(get_element_by_id('videoName', webpage).rpartition('|')[0])
  99         uploader_id = self._html_search_regex(
 100             r'<a href="/profile/\d+">(.+?)</a>',
 101             webpage, 'uploader')
 102         thumbnail = self._search_regex(
 103             r'<img id="veehdpreview" src="(.+?)"',
 104             webpage, 'thumbnail')
 105         description = self._html_search_regex(
 106             r'<td class="infodropdown".*?<div>(.*?)<ul',
 107             webpage, 'description', flags=re.DOTALL)
 108
 109         return {
 110             '_type': 'video',
 111             'id': video_id,
 112             'title': title,
 113             'url': video_url,
 114             'uploader_id': uploader_id,
 115             'thumbnail': thumbnail,
 116             'description': description,
 117         }