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     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     _TESTS = [
  15         {
  16             'url': 'http://www.vporn.com/masturbation/violet-on-her-th-birthday/497944/',
  17             'md5': 'facf37c1b86546fa0208058546842c55',
  18             'info_dict': {
  19                 'id': '497944',
  20                 'display_id': 'violet-on-her-th-birthday',
  21                 'ext': 'mp4',
  22                 'title': 'Violet on her 19th birthday',
  23                 'description': 'Violet dances in front of the camera which is sure to get you horny.',
  24                 'thumbnail': 're:^https?://.*\.jpg$',
  25                 'uploader': 'kileyGrope',
  26                 'categories': ['Masturbation', 'Teen'],
  27                 'duration': 393,
  28                 'age_limit': 18,
  29                 'view_count': int,
  30                 'like_count': int,
  31                 'dislike_count': int,
  32                 'comment_count': int,
  33             }
  34         },
  35         {
  36             'url': 'http://www.vporn.com/female/hana-shower/523564/',
  37             'md5': 'ced35a4656198a1664cf2cda1575a25f',
  38             'info_dict': {
  39                 'id': '523564',
  40                 'display_id': 'hana-shower',
  41                 'ext': 'mp4',
  42                 'title': 'Hana Shower',
  43                 'description': 'Hana showers at the bathroom.',
  44                 'thumbnail': 're:^https?://.*\.jpg$',
  45                 'uploader': 'Hmmmmm',
  46                 'categories': ['Big Boobs', 'Erotic', 'Teen', 'Female'],
  47                 'duration': 588,
  48                 'age_limit': 18,
  49                 'view_count': int,
  50                 'like_count': int,
  51                 'dislike_count': int,
  52                 'comment_count': int,
  53             }
  54         },
  55     ]
  56
  57     def _real_extract(self, url):
  58         mobj = re.match(self._VALID_URL, url)
  59         video_id = mobj.group('id')
  60         display_id = mobj.group('display_id')
  61
  62         webpage = self._download_webpage(url, display_id)
  63
  64         title = self._html_search_regex(
  65             r'videoname\s*=\s*\'([^\']+)\'', webpage, 'title').strip()
  66         description = self._html_search_regex(
  67             r'<div class="description_txt">(.*?)</div>', webpage, 'description', fatal=False)
  68         thumbnail = self._html_search_regex(
  69             r'flashvars\.imageUrl\s*=\s*"([^"]+)"', webpage, 'description', fatal=False, default=None)
  70         if thumbnail:
  71             thumbnail = 'http://www.vporn.com' + thumbnail
  72
  73         uploader = self._html_search_regex(
  74             r'(?s)UPLOADED BY.*?<a href="/user/[^"]+">([^<]+)</a>',
  75             webpage, 'uploader', fatal=False)
  76
  77         categories = re.findall(r'<a href="/cat/[^"]+">([^<]+)</a>', webpage)
  78
  79         duration = parse_duration(self._search_regex(
  80             r'duration (\d+ min \d+ sec)', webpage, 'duration', fatal=False))
  81
  82         view_count = str_to_int(self._html_search_regex(
  83             r'<span>([\d,\.]+) VIEWS</span>', webpage, 'view count', fatal=False))
  84         like_count = str_to_int(self._html_search_regex(
  85             r'<span id="like" class="n">([\d,\.]+)</span>', webpage, 'like count', fatal=False))
  86         dislike_count = str_to_int(self._html_search_regex(
  87             r'<span id="dislike" class="n">([\d,\.]+)</span>', webpage, 'dislike count', fatal=False))
  88         comment_count = str_to_int(self._html_search_regex(
  89             r'<h4>Comments \(<b>([\d,\.]+)</b>\)</h4>', webpage, 'comment count', fatal=False))
  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             'like_count': like_count,
 121             'dislike_count': dislike_count,
 122             'comment_count': comment_count,
 123             'age_limit': 18,
 124             'formats': formats,
 125         }