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