Raphaël G. Git Repositories - youtubedl/blob - 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 (
   8     ExtractorError,
   9     unescapeHTML
  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': 're:https?://.*\.jpg',
  26             'age_limit': 18,
  27         }
  28     }, {
  29         'url': 'http://www.eroprofile.com/m/videos/view/Try-It-On-Pee_cut_2-wmv-4shared-com-file-sharing-download-movie-file',
  30         'md5': '1baa9602ede46ce904c431f5418d8916',
  31         'info_dict': {
  32             'id': '1133519',
  33             'ext': 'm4v',
  34             'title': 'Try It On Pee_cut_2.wmv - 4shared.com - file sharing - download movie file',
  35             'thumbnail': 're:https?://.*\.jpg',
  36             'age_limit': 18,
  37         },
  38         'skip': 'Requires login',
  39     }]
  40
  41     def _login(self):
  42         (username, password) = self._get_login_info()
  43         if username is None:
  44             return
  45
  46         query = compat_urllib_parse.urlencode({
  47             'username': username,
  48             'password': password,
  49             'url': 'http://www.eroprofile.com/',
  50         })
  51         login_url = self._LOGIN_URL + query
  52         login_page = self._download_webpage(login_url, None, False)
  53
  54         m = re.search(r'Your username or password was incorrect\.', login_page)
  55         if m:
  56             raise ExtractorError(
  57                 'Wrong username and/or password.', expected=True)
  58
  59         self.report_login()
  60         redirect_url = self._search_regex(
  61             r'<script[^>]+?src="([^"]+)"', login_page, 'login redirect url')
  62         self._download_webpage(redirect_url, None, False)
  63
  64     def _real_initialize(self):
  65         self._login()
  66
  67     def _real_extract(self, url):
  68         display_id = self._match_id(url)
  69
  70         webpage = self._download_webpage(url, display_id)
  71
  72         m = re.search(r'You must be logged in to view this video\.', webpage)
  73         if m:
  74             raise ExtractorError(
  75                 'This video requires login. Please specify a username and password and try again.', expected=True)
  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         video_url = unescapeHTML(self._search_regex(
  82             r'<source src="([^"]+)', webpage, 'video url'))
  83         title = self._html_search_regex(
  84             r'Title:</th><td>([^<]+)</td>', webpage, 'title')
  85         thumbnail = self._search_regex(
  86             r'onclick="showVideoPlayer\(\)"><img src="([^"]+)',
  87             webpage, 'thumbnail', fatal=False)
  88
  89         return {
  90             'id': video_id,
  91             'display_id': display_id,
  92             'url': video_url,
  93             'title': title,
  94             'thumbnail': thumbnail,
  95             'age_limit': 18,
  96         }