yt_dlp/extractor/eroprofile.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_urllib_parse_urlencode
   7 from ..utils import (
   8     ExtractorError,
   9     merge_dicts,
  10 )
  11
  12
  13 class EroProfileIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?eroprofile\.com/m/videos/view/(?P<id>[^/]+)'
  15     _LOGIN_URL = 'http://www.eroprofile.com/auth/auth.php?'
  16     _NETRC_MACHINE = 'eroprofile'
  17     _TESTS = [{
  18         'url': 'http://www.eroprofile.com/m/videos/view/sexy-babe-softcore',
  19         'md5': 'c26f351332edf23e1ea28ce9ec9de32f',
  20         'info_dict': {
  21             'id': '3733775',
  22             'display_id': 'sexy-babe-softcore',
  23             'ext': 'm4v',
  24             'title': 'sexy babe softcore',
  25             'thumbnail': r're:https?://.*\.jpg',
  26             'age_limit': 18,
  27         },
  28         'skip': 'Video not found',
  29     }, {
  30         'url': 'http://www.eroprofile.com/m/videos/view/Try-It-On-Pee_cut_2-wmv-4shared-com-file-sharing-download-movie-file',
  31         'md5': '1baa9602ede46ce904c431f5418d8916',
  32         'info_dict': {
  33             'id': '1133519',
  34             'ext': 'm4v',
  35             'title': 'Try It On Pee_cut_2.wmv - 4shared.com - file sharing - download movie file',
  36             'thumbnail': r're:https?://.*\.jpg',
  37             'age_limit': 18,
  38         },
  39         'skip': 'Requires login',
  40     }]
  41
  42     def _login(self):
  43         (username, password) = self._get_login_info()
  44         if username is None:
  45             return
  46
  47         query = compat_urllib_parse_urlencode({
  48             'username': username,
  49             'password': password,
  50             'url': 'http://www.eroprofile.com/',
  51         })
  52         login_url = self._LOGIN_URL + query
  53         login_page = self._download_webpage(login_url, None, False)
  54
  55         m = re.search(r'Your username or password was incorrect\.', login_page)
  56         if m:
  57             raise ExtractorError(
  58                 'Wrong username and/or password.', expected=True)
  59
  60         self.report_login()
  61         redirect_url = self._search_regex(
  62             r'<script[^>]+?src="([^"]+)"', login_page, 'login redirect url')
  63         self._download_webpage(redirect_url, None, False)
  64
  65     def _real_initialize(self):
  66         self._login()
  67
  68     def _real_extract(self, url):
  69         display_id = self._match_id(url)
  70
  71         webpage = self._download_webpage(url, display_id)
  72
  73         m = re.search(r'You must be logged in to view this video\.', webpage)
  74         if m:
  75             self.raise_login_required('This video requires login')
  76
  77         video_id = self._search_regex(
  78             [r"glbUpdViews\s*\('\d*','(\d+)'", r'p/report/video/(\d+)'],
  79             webpage, 'video id', default=None)
  80
  81         title = self._html_search_regex(
  82             (r'Title:</th><td>([^<]+)</td>', r'<h1[^>]*>(.+?)</h1>'),
  83             webpage, 'title')
  84
  85         info = self._parse_html5_media_entries(url, webpage, video_id)[0]
  86
  87         return merge_dicts(info, {
  88             'id': video_id,
  89             'display_id': display_id,
  90             'title': title,
  91             'age_limit': 18,
  92         })