_ Git - youtube-dl/blob - 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     _TEST = {
  21         'url': 'http://veehd.com/video/4686958',
  22         'info_dict': {
  23             'id': '4686958',
  24             'ext': 'mp4',
  25             'title': 'Time Lapse View from Space ( ISS)',
  26             'uploader_id': 'spotted',
  27             'description': 'md5:f0094c4cf3a72e22bc4e4239ef767ad7',
  28         },
  29     }
  30
  31     def _real_extract(self, url):
  32         video_id = self._match_id(url)
  33
  34         # VeeHD seems to send garbage on the first request.
  35         # See https://github.com/rg3/youtube-dl/issues/2102
  36         self._download_webpage(url, video_id, 'Requesting webpage')
  37         webpage = self._download_webpage(url, video_id)
  38
  39         if 'This video has been removed<' in webpage:
  40             raise ExtractorError('Video %s has been removed' % video_id, expected=True)
  41
  42         player_path = self._search_regex(
  43             r'\$\("#playeriframe"\).attr\({src : "(.+?)"',
  44             webpage, 'player path')
  45         player_url = compat_urlparse.urljoin(url, player_path)
  46
  47         self._download_webpage(player_url, video_id, 'Requesting player page')
  48         player_page = self._download_webpage(
  49             player_url, video_id, 'Downloading player page')
  50         config_json = self._search_regex(
  51             r'value=\'config=({.+?})\'', player_page, 'config json')
  52         config = json.loads(config_json)
  53
  54         video_url = compat_urlparse.unquote(config['clip']['url'])
  55         title = clean_html(get_element_by_id('videoName', webpage).rpartition('|')[0])
  56         uploader_id = self._html_search_regex(r'<a href="/profile/\d+">(.+?)</a>',
  57                                               webpage, 'uploader')
  58         thumbnail = self._search_regex(r'<img id="veehdpreview" src="(.+?)"',
  59                                        webpage, 'thumbnail')
  60         description = self._html_search_regex(r'<td class="infodropdown".*?<div>(.*?)<ul',
  61                                               webpage, 'description', flags=re.DOTALL)
  62
  63         return {
  64             '_type': 'video',
  65             'id': video_id,
  66             'title': title,
  67             'url': video_url,
  68             'ext': 'mp4',
  69             'uploader_id': uploader_id,
  70             'thumbnail': thumbnail,
  71             'description': description,
  72         }