youtube_dl/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
   7 from ..utils import ExtractorError
   8
   9
  10 class EroProfileIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?eroprofile\.com/m/videos/view/(?P<id>[^/]+)'
  12     _LOGIN_URL = 'http://www.eroprofile.com/auth/auth.php?'
  13     _NETRC_MACHINE = 'eroprofile'
  14     _TESTS = [{
  15         'url': 'http://www.eroprofile.com/m/videos/view/sexy-babe-softcore',
  16         'md5': 'c26f351332edf23e1ea28ce9ec9de32f',
  17         'info_dict': {
  18             'id': '3733775',
  19             'display_id': 'sexy-babe-softcore',
  20             'ext': 'm4v',
  21             'title': 'sexy babe softcore',
  22             'thumbnail': 're:https?://.*\.jpg',
  23             'age_limit': 18,
  24         }
  25     }, {
  26         'url': 'http://www.eroprofile.com/m/videos/view/Try-It-On-Pee_cut_2-wmv-4shared-com-file-sharing-download-movie-file',
  27         'md5': '1baa9602ede46ce904c431f5418d8916',
  28         'info_dict': {
  29             'id': '1133519',
  30             'ext': 'm4v',
  31             'title': 'Try It On Pee_cut_2.wmv - 4shared.com - file sharing - download movie file',
  32             'thumbnail': 're:https?://.*\.jpg',
  33             'age_limit': 18,
  34         },
  35         'skip': 'Requires login',
  36     }]
  37
  38     def _login(self):
  39         (username, password) = self._get_login_info()
  40         if username is None:
  41             return
  42
  43         query = compat_urllib_parse.urlencode({
  44             'username': username,
  45             'password': password,
  46             'url': 'http://www.eroprofile.com/',
  47         })
  48         login_url = self._LOGIN_URL + query
  49         login_page = self._download_webpage(login_url, None, False)
  50
  51         m = re.search(r'Your username or password was incorrect\.', login_page)
  52         if m:
  53             raise ExtractorError(
  54                 'Wrong username and/or password.', expected=True)
  55
  56         self.report_login()
  57         redirect_url = self._search_regex(
  58             r'<script[^>]+?src="([^"]+)"', login_page, 'login redirect url')
  59         self._download_webpage(redirect_url, None, False)
  60
  61     def _real_initialize(self):
  62         self._login()
  63
  64     def _real_extract(self, url):
  65         display_id = self._match_id(url)
  66
  67         webpage = self._download_webpage(url, display_id)
  68
  69         m = re.search(r'You must be logged in to view this video\.', webpage)
  70         if m:
  71             raise ExtractorError(
  72                 'This video requires login. Please specify a username and password and try again.', expected=True)
  73
  74         video_id = self._search_regex(
  75             [r"glbUpdViews\s*\('\d*','(\d+)'", r'p/report/video/(\d+)'],
  76             webpage, 'video id', default=None)
  77
  78         video_url = self._search_regex(
  79             r'<source src="([^"]+)', webpage, 'video url')
  80         title = self._html_search_regex(
  81             r'Title:</th><td>([^<]+)</td>', webpage, 'title')
  82         thumbnail = self._search_regex(
  83             r'onclick="showVideoPlayer\(\)"><img src="([^"]+)',
  84             webpage, 'thumbnail', fatal=False)
  85
  86         return {
  87             'id': video_id,
  88             'display_id': display_id,
  89             'url': video_url,
  90             'title': title,
  91             'thumbnail': thumbnail,
  92             'age_limit': 18,
  93         }