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