Raphaël G. Git Repositories - youtubedl/blob - 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     ExtractorError,
   8     parse_duration,
   9     str_to_int,
  10     urljoin,
  11 )
  12
  13
  14 class VpornIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?vporn\.com/[^/]+/(?P<display_id>[^/]+)/(?P<id>\d+)'
  16     _TESTS = [
  17         {
  18             'url': 'http://www.vporn.com/masturbation/violet-on-her-th-birthday/497944/',
  19             'md5': 'facf37c1b86546fa0208058546842c55',
  20             'info_dict': {
  21                 'id': '497944',
  22                 'display_id': 'violet-on-her-th-birthday',
  23                 'ext': 'mp4',
  24                 'title': 'Violet on her 19th birthday',
  25                 'description': 'Violet dances in front of the camera which is sure to get you horny.',
  26                 'thumbnail': r're:^https?://.*\.jpg$',
  27                 'uploader': 'kileyGrope',
  28                 'categories': ['Masturbation', 'Teen'],
  29                 'duration': 393,
  30                 'age_limit': 18,
  31                 'view_count': int,
  32             },
  33             'skip': 'video removed',
  34         },
  35         {
  36             'url': 'http://www.vporn.com/female/hana-shower/523564/',
  37             'md5': 'ced35a4656198a1664cf2cda1575a25f',
  38             'info_dict': {
  39                 'id': '523564',
  40                 'display_id': 'hana-shower',
  41                 'ext': 'mp4',
  42                 'title': 'Hana Shower',
  43                 'description': 'Hana showers at the bathroom.',
  44                 'thumbnail': r're:^https?://.*\.jpg$',
  45                 'uploader': 'Hmmmmm',
  46                 'categories': ['Big Boobs', 'Erotic', 'Teen', 'Female', '720p'],
  47                 'duration': 588,
  48                 'age_limit': 18,
  49                 'view_count': int,
  50             }
  51         },
  52     ]
  53
  54     def _real_extract(self, url):
  55         mobj = re.match(self._VALID_URL, url)
  56         video_id = mobj.group('id')
  57         display_id = mobj.group('display_id')
  58
  59         webpage = self._download_webpage(url, display_id)
  60
  61         errmsg = 'This video has been deleted due to Copyright Infringement or by the account owner!'
  62         if errmsg in webpage:
  63             raise ExtractorError('%s said: %s' % (self.IE_NAME, errmsg), expected=True)
  64
  65         title = self._html_search_regex(
  66             r'videoname\s*=\s*\'([^\']+)\'', webpage, 'title').strip()
  67         description = self._html_search_regex(
  68             r'class="(?:descr|description_txt)">(.*?)</div>',
  69             webpage, 'description', fatal=False)
  70         thumbnail = urljoin('http://www.vporn.com', self._html_search_regex(
  71             r'flashvars\.imageUrl\s*=\s*"([^"]+)"', webpage, 'description',
  72             default=None))
  73
  74         uploader = self._html_search_regex(
  75             r'(?s)Uploaded by:.*?<a href="/user/[^"]+"[^>]*>(.+?)</a>',
  76             webpage, 'uploader', fatal=False)
  77
  78         categories = re.findall(r'<a href="/cat/[^"]+"[^>]*>([^<]+)</a>', webpage)
  79
  80         duration = parse_duration(self._search_regex(
  81             r'Runtime:\s*</span>\s*(\d+ min \d+ sec)',
  82             webpage, 'duration', fatal=False))
  83
  84         view_count = str_to_int(self._search_regex(
  85             r'class="views">([\d,\.]+) [Vv]iews<',
  86             webpage, 'view count', fatal=False))
  87         comment_count = str_to_int(self._html_search_regex(
  88             r"'Comments \(([\d,\.]+)\)'",
  89             webpage, 'comment count', default=None))
  90
  91         formats = []
  92
  93         for video in re.findall(r'flashvars\.videoUrl([^=]+?)\s*=\s*"(https?://[^"]+)"', webpage):
  94             video_url = video[1]
  95             fmt = {
  96                 'url': video_url,
  97                 'format_id': video[0],
  98             }
  99             m = re.search(r'_(?P<width>\d+)x(?P<height>\d+)_(?P<vbr>\d+)k\.mp4$', video_url)
 100             if m:
 101                 fmt.update({
 102                     'width': int(m.group('width')),
 103                     'height': int(m.group('height')),
 104                     'vbr': int(m.group('vbr')),
 105                 })
 106             formats.append(fmt)
 107
 108         self._sort_formats(formats)
 109
 110         return {
 111             'id': video_id,
 112             'display_id': display_id,
 113             'title': title,
 114             'description': description,
 115             'thumbnail': thumbnail,
 116             'uploader': uploader,
 117             'categories': categories,
 118             'duration': duration,
 119             'view_count': view_count,
 120             'comment_count': comment_count,
 121             'age_limit': 18,
 122             'formats': formats,
 123         }