yt-dlp/youtube_dlc/extractor/eroprofile.py

96 lines
3.1 KiB
Python
Raw Normal View History

2014-12-26 09:15:34 -07:00
from __future__ import unicode_literals
2015-03-26 15:24:15 -06:00
import re
2014-12-26 09:15:34 -07:00
from .common import InfoExtractor
from ..compat import compat_urllib_parse_urlencode
from ..utils import (
ExtractorError,
unescapeHTML
)
2014-12-26 09:15:34 -07:00
2014-12-26 10:32:41 -07:00
2014-12-26 09:15:34 -07:00
class EroProfileIE(InfoExtractor):
2014-12-26 10:32:41 -07:00
_VALID_URL = r'https?://(?:www\.)?eroprofile\.com/m/videos/view/(?P<id>[^/]+)'
2015-03-26 15:24:15 -06:00
_LOGIN_URL = 'http://www.eroprofile.com/auth/auth.php?'
_NETRC_MACHINE = 'eroprofile'
_TESTS = [{
2014-12-26 09:15:34 -07:00
'url': 'http://www.eroprofile.com/m/videos/view/sexy-babe-softcore',
'md5': 'c26f351332edf23e1ea28ce9ec9de32f',
'info_dict': {
'id': '3733775',
2014-12-26 10:32:41 -07:00
'display_id': 'sexy-babe-softcore',
2014-12-26 09:15:34 -07:00
'ext': 'm4v',
2014-12-26 10:32:41 -07:00
'title': 'sexy babe softcore',
'thumbnail': r're:https?://.*\.jpg',
2014-12-26 09:15:34 -07:00
'age_limit': 18,
}
2015-03-26 15:24:15 -06:00
}, {
'url': 'http://www.eroprofile.com/m/videos/view/Try-It-On-Pee_cut_2-wmv-4shared-com-file-sharing-download-movie-file',
'md5': '1baa9602ede46ce904c431f5418d8916',
'info_dict': {
'id': '1133519',
'ext': 'm4v',
'title': 'Try It On Pee_cut_2.wmv - 4shared.com - file sharing - download movie file',
'thumbnail': r're:https?://.*\.jpg',
2015-03-26 15:24:15 -06:00
'age_limit': 18,
},
'skip': 'Requires login',
}]
def _login(self):
(username, password) = self._get_login_info()
if username is None:
return
query = compat_urllib_parse_urlencode({
2015-03-26 15:24:15 -06:00
'username': username,
'password': password,
'url': 'http://www.eroprofile.com/',
})
login_url = self._LOGIN_URL + query
login_page = self._download_webpage(login_url, None, False)
m = re.search(r'Your username or password was incorrect\.', login_page)
if m:
raise ExtractorError(
'Wrong username and/or password.', expected=True)
self.report_login()
redirect_url = self._search_regex(
r'<script[^>]+?src="([^"]+)"', login_page, 'login redirect url')
self._download_webpage(redirect_url, None, False)
def _real_initialize(self):
self._login()
2014-12-26 09:15:34 -07:00
def _real_extract(self, url):
2014-12-26 10:32:41 -07:00
display_id = self._match_id(url)
2014-12-26 09:15:34 -07:00
2014-12-26 10:32:41 -07:00
webpage = self._download_webpage(url, display_id)
2014-12-26 09:15:34 -07:00
2015-03-26 15:24:15 -06:00
m = re.search(r'You must be logged in to view this video\.', webpage)
if m:
2015-08-26 09:25:37 -06:00
self.raise_login_required('This video requires login')
2015-03-26 15:24:15 -06:00
2014-12-26 10:32:41 -07:00
video_id = self._search_regex(
[r"glbUpdViews\s*\('\d*','(\d+)'", r'p/report/video/(\d+)'],
webpage, 'video id', default=None)
2014-12-26 09:15:34 -07:00
video_url = unescapeHTML(self._search_regex(
r'<source src="([^"]+)', webpage, 'video url'))
2014-12-26 09:15:34 -07:00
title = self._html_search_regex(
2014-12-26 10:32:41 -07:00
r'Title:</th><td>([^<]+)</td>', webpage, 'title')
thumbnail = self._search_regex(
r'onclick="showVideoPlayer\(\)"><img src="([^"]+)',
webpage, 'thumbnail', fatal=False)
2014-12-26 09:15:34 -07:00
return {
'id': video_id,
2014-12-26 10:32:41 -07:00
'display_id': display_id,
2014-12-26 09:15:34 -07:00
'url': video_url,
'title': title,
'thumbnail': thumbnail,
'age_limit': 18,
}