youtube_dl/extractor/vporn.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     parse_duration,
   8     str_to_int,
   9 )
  10
  11
  12 class VpornIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?vporn\.com/[^/]+/(?P<display_id>[^/]+)/(?P<id>\d+)'
  14     _TEST = {
  15         'url': 'http://www.vporn.com/masturbation/violet-on-her-th-birthday/497944/',
  16         'md5': 'facf37c1b86546fa0208058546842c55',
  17         'info_dict': {
  18             'id': '497944',
  19             'display_id': 'violet-on-her-th-birthday',
  20             'ext': 'mp4',
  21             'title': 'Violet on her 19th birthday',
  22             'description': 'Violet dances in front of the camera which is sure to get you horny.',
  23             'thumbnail': 're:^https?://.*\.jpg$',
  24             'uploader': 'kileyGrope',
  25             'categories': ['Masturbation', 'Teen'],
  26             'duration': 393,
  27             'age_limit': 18,
  28         }
  29     }
  30
  31     def _real_extract(self, url):
  32         mobj = re.match(self._VALID_URL, url)
  33         video_id = mobj.group('id')
  34         display_id = mobj.group('display_id')
  35
  36         webpage = self._download_webpage(url, display_id)
  37
  38         title = self._html_search_regex(
  39             r'videoname\s*=\s*\'([^\']+)\'', webpage, 'title').strip()
  40         description = self._html_search_regex(
  41             r'<div class="description_txt">(.*?)</div>', webpage, 'description', fatal=False)
  42         thumbnail = self._html_search_regex(
  43             r'flashvars\.imageUrl\s*=\s*"([^"]+)"', webpage, 'description', fatal=False, default=None)
  44         if thumbnail:
  45             thumbnail = 'http://www.vporn.com' + thumbnail
  46
  47         uploader = self._html_search_regex(
  48             r'(?s)UPLOADED BY.*?<a href="/user/[^"]+">([^<]+)</a>',
  49             webpage, 'uploader', fatal=False)
  50
  51         categories = re.findall(r'<a href="/cat/[^"]+">([^<]+)</a>', webpage)
  52
  53         duration = parse_duration(self._search_regex(
  54             r'duration (\d+ min \d+ sec)', webpage, 'duration', fatal=False))
  55
  56         view_count = str_to_int(self._html_search_regex(
  57             r'<span>([\d,\.]+) VIEWS</span>', webpage, 'view count', fatal=False))
  58         like_count = str_to_int(self._html_search_regex(
  59             r'<span id="like" class="n">([\d,\.]+)</span>', webpage, 'like count', fatal=False))
  60         dislike_count = str_to_int(self._html_search_regex(
  61             r'<span id="dislike" class="n">([\d,\.]+)</span>', webpage, 'dislike count', fatal=False))
  62         comment_count = str_to_int(self._html_search_regex(
  63             r'<h4>Comments \(<b>([\d,\.]+)</b>\)</h4>', webpage, 'comment count', fatal=False))
  64
  65         formats = []
  66
  67         for video in re.findall(r'flashvars\.videoUrl([^=]+?)\s*=\s*"([^"]+)"', webpage):
  68             video_url = video[1]
  69             fmt = {
  70                 'url': video_url,
  71                 'format_id': video[0],
  72             }
  73             m = re.search(r'_(?P<width>\d+)x(?P<height>\d+)_(?P<vbr>\d+)k\.mp4$', video_url)
  74             if m:
  75                 fmt.update({
  76                     'width': int(m.group('width')),
  77                     'height': int(m.group('height')),
  78                     'vbr': int(m.group('vbr')),
  79                 })
  80             formats.append(fmt)
  81
  82         self._sort_formats(formats)
  83
  84         return {
  85             'id': video_id,
  86             'display_id': display_id,
  87             'title': title,
  88             'description': description,
  89             'thumbnail': thumbnail,
  90             'uploader': uploader,
  91             'categories': categories,
  92             'duration': duration,
  93             'view_count': view_count,
  94             'like_count': like_count,
  95             'dislike_count': dislike_count,
  96             'comment_count': comment_count,
  97             'age_limit': 18,
  98             'formats': formats,
  99         }