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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     js_to_json,
   8     remove_end,
   9     determine_ext,
  10 )
  11
  12
  13 class HellPornoIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?hellporno\.(?:com/videos|net/v)/(?P<id>[^/]+)'
  15     _TESTS = [{
  16         'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/',
  17         'md5': '1fee339c610d2049699ef2aa699439f1',
  18         'info_dict': {
  19             'id': '149116',
  20             'display_id': 'dixie-is-posing-with-naked-ass-very-erotic',
  21             'ext': 'mp4',
  22             'title': 'Dixie is posing with naked ass very erotic',
  23             'thumbnail': r're:https?://.*\.jpg$',
  24             'age_limit': 18,
  25         }
  26     }, {
  27         'url': 'http://hellporno.net/v/186271/',
  28         'only_matching': True,
  29     }]
  30
  31     def _real_extract(self, url):
  32         display_id = self._match_id(url)
  33
  34         webpage = self._download_webpage(url, display_id)
  35
  36         title = remove_end(self._html_search_regex(
  37             r'<title>([^<]+)</title>', webpage, 'title'), ' - Hell Porno')
  38
  39         flashvars = self._parse_json(self._search_regex(
  40             r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flashvars'),
  41             display_id, transform_source=js_to_json)
  42
  43         video_id = flashvars.get('video_id')
  44         thumbnail = flashvars.get('preview_url')
  45         ext = determine_ext(flashvars.get('postfix'), 'mp4')
  46
  47         formats = []
  48         for video_url_key in ['video_url', 'video_alt_url']:
  49             video_url = flashvars.get(video_url_key)
  50             if not video_url:
  51                 continue
  52             video_text = flashvars.get('%s_text' % video_url_key)
  53             fmt = {
  54                 'url': video_url,
  55                 'ext': ext,
  56                 'format_id': video_text,
  57             }
  58             m = re.search(r'^(?P<height>\d+)[pP]', video_text)
  59             if m:
  60                 fmt['height'] = int(m.group('height'))
  61             formats.append(fmt)
  62         self._sort_formats(formats)
  63
  64         categories = self._html_search_meta(
  65             'keywords', webpage, 'categories', default='').split(',')
  66
  67         return {
  68             'id': video_id,
  69             'display_id': display_id,
  70             'title': title,
  71             'thumbnail': thumbnail,
  72             'categories': categories,
  73             'age_limit': 18,
  74             'formats': formats,
  75         }