youtube_dlc/extractor/eporner.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     encode_base_n,
   9     ExtractorError,
  10     int_or_none,
  11     merge_dicts,
  12     parse_duration,
  13     str_to_int,
  14     url_or_none,
  15 )
  16
  17
  18 class EpornerIE(InfoExtractor):
  19     _VALID_URL = r'https?://(?:www\.)?eporner\.com/(?:(?:hd-porn|embed)/|video-)(?P<id>\w+)(?:/(?P<display_id>[\w-]+))?'
  20     _TESTS = [{
  21         'url': 'http://www.eporner.com/hd-porn/95008/Infamous-Tiffany-Teen-Strip-Tease-Video/',
  22         'md5': '39d486f046212d8e1b911c52ab4691f8',
  23         'info_dict': {
  24             'id': 'qlDUmNsj6VS',
  25             'display_id': 'Infamous-Tiffany-Teen-Strip-Tease-Video',
  26             'ext': 'mp4',
  27             'title': 'Infamous Tiffany Teen Strip Tease Video',
  28             'description': 'md5:764f39abf932daafa37485eb46efa152',
  29             'timestamp': 1232520922,
  30             'upload_date': '20090121',
  31             'duration': 1838,
  32             'view_count': int,
  33             'age_limit': 18,
  34         },
  35         'params': {
  36             'proxy': '127.0.0.1:8118'
  37         }
  38     }, {
  39         # New (May 2016) URL layout
  40         'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0/Star-Wars-XXX-Parody/',
  41         'only_matching': True,
  42     }, {
  43         'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0',
  44         'only_matching': True,
  45     }, {
  46         'url': 'http://www.eporner.com/embed/3YRUtzMcWn0',
  47         'only_matching': True,
  48     }, {
  49         'url': 'https://www.eporner.com/video-FJsA19J3Y3H/one-of-the-greats/',
  50         'only_matching': True,
  51     }]
  52
  53     def _real_extract(self, url):
  54         mobj = re.match(self._VALID_URL, url)
  55         video_id = mobj.group('id')
  56         display_id = mobj.group('display_id') or video_id
  57
  58         webpage, urlh = self._download_webpage_handle(url, display_id)
  59
  60         video_id = self._match_id(urlh.geturl())
  61
  62         hash = self._search_regex(
  63             r'hash\s*[:=]\s*["\']([\da-f]{32})', webpage, 'hash')
  64
  65         title = self._og_search_title(webpage, default=None) or self._html_search_regex(
  66             r'<title>(.+?) - EPORNER', webpage, 'title')
  67
  68         # Reverse engineered from vjs.js
  69         def calc_hash(s):
  70             return ''.join((encode_base_n(int(s[lb:lb + 8], 16), 36) for lb in range(0, 32, 8)))
  71
  72         video = self._download_json(
  73             'http://www.eporner.com/xhr/video/%s' % video_id,
  74             display_id, note='Downloading video JSON',
  75             query={
  76                 'hash': calc_hash(hash),
  77                 'device': 'generic',
  78                 'domain': 'www.eporner.com',
  79                 'fallback': 'false',
  80             })
  81
  82         if video.get('available') is False:
  83             raise ExtractorError(
  84                 '%s said: %s' % (self.IE_NAME, video['message']), expected=True)
  85
  86         sources = video['sources']
  87
  88         formats = []
  89         for kind, formats_dict in sources.items():
  90             if not isinstance(formats_dict, dict):
  91                 continue
  92             for format_id, format_dict in formats_dict.items():
  93                 if not isinstance(format_dict, dict):
  94                     continue
  95                 src = url_or_none(format_dict.get('src'))
  96                 if not src or not src.startswith('http'):
  97                     continue
  98                 if kind == 'hls':
  99                     formats.extend(self._extract_m3u8_formats(
 100                         src, display_id, 'mp4', entry_protocol='m3u8_native',
 101                         m3u8_id=kind, fatal=False))
 102                 else:
 103                     height = int_or_none(self._search_regex(
 104                         r'(\d+)[pP]', format_id, 'height', default=None))
 105                     fps = int_or_none(self._search_regex(
 106                         r'(\d+)fps', format_id, 'fps', default=None))
 107
 108                     formats.append({
 109                         'url': src,
 110                         'format_id': format_id,
 111                         'height': height,
 112                         'fps': fps,
 113                     })
 114         self._sort_formats(formats)
 115
 116         json_ld = self._search_json_ld(webpage, display_id, default={})
 117
 118         duration = parse_duration(self._html_search_meta(
 119             'duration', webpage, default=None))
 120         view_count = str_to_int(self._search_regex(
 121             r'id=["\']cinemaviews1["\'][^>]*>\s*([0-9,]+)',
 122             webpage, 'view count', default=None))
 123
 124         return merge_dicts(json_ld, {
 125             'id': video_id,
 126             'display_id': display_id,
 127             'title': title,
 128             'duration': duration,
 129             'view_count': view_count,
 130             'formats': formats,
 131             'age_limit': 18,
 132         })