Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/openfilm.py

   1 from __future__ import unicode_literals
   2
   3 import json
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     parse_iso8601,
   8     compat_urllib_parse,
   9     parse_age_limit,
  10     int_or_none,
  11 )
  12
  13
  14 class OpenFilmIE(InfoExtractor):
  15     _VALID_URL = r'http://(?:www\.)openfilm\.com/videos/(?P<id>.+)'
  16     _TEST = {
  17         'url': 'http://www.openfilm.com/videos/human-resources-remastered',
  18         'md5': '42bcd88c2f3ec13b65edf0f8ad1cac37',
  19         'info_dict': {
  20             'id': '32736',
  21             'display_id': 'human-resources-remastered',
  22             'ext': 'mp4',
  23             'title': 'Human Resources (Remastered)',
  24             'description': 'Social Engineering in the 20th Century.',
  25             'thumbnail': 're:^https?://.*\.jpg$',
  26             'duration': 7164,
  27             'timestamp': 1334756988,
  28             'upload_date': '20120418',
  29             'uploader_id': '41117',
  30             'view_count': int,
  31             'age_limit': 0,
  32         },
  33     }
  34
  35     def _real_extract(self, url):
  36         display_id = self._match_id(url)
  37
  38         webpage = self._download_webpage(url, display_id)
  39
  40         player = compat_urllib_parse.unquote_plus(
  41             self._og_search_video_url(webpage))
  42
  43         video = json.loads(self._search_regex(
  44             r'\bp=({.+?})(?:&|$)', player, 'video JSON'))
  45
  46         video_url = '%s1.mp4' % video['location']
  47         video_id = video.get('video_id')
  48         display_id = video.get('alias') or display_id
  49         title = video.get('title')
  50         description = video.get('description')
  51         thumbnail = video.get('main_thumb')
  52         duration = int_or_none(video.get('duration'))
  53         timestamp = parse_iso8601(video.get('dt_published'), ' ')
  54         uploader_id = video.get('user_id')
  55         view_count = int_or_none(video.get('views_count'))
  56         age_limit = parse_age_limit(video.get('age_limit'))
  57
  58         return {
  59             'id': video_id,
  60             'display_id': display_id,
  61             'url': video_url,
  62             'title': title,
  63             'description': description,
  64             'thumbnail': thumbnail,
  65             'duration': duration,
  66             'timestamp': timestamp,
  67             'uploader_id': uploader_id,
  68             'view_count': view_count,
  69             'age_limit': age_limit,
  70         }