1
0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-23 00:54:31 +01:00

[tumblr] Add support for authentication

This commit is contained in:
Zack Fernandes 2017-12-31 13:55:35 -08:00 committed by Sergey M․
parent 0934c9d4fa
commit c678192af3
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D

View File

@ -4,11 +4,18 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import int_or_none from ..utils import (
ExtractorError,
int_or_none,
sanitized_Request,
urlencode_postdata
)
class TumblrIE(InfoExtractor): class TumblrIE(InfoExtractor):
_VALID_URL = r'https?://(?P<blog_name>[^/?#&]+)\.tumblr\.com/(?:post|video)/(?P<id>[0-9]+)(?:$|[/?#])' _VALID_URL = r'https?://(?P<blog_name>[^/?#&]+)\.tumblr\.com/(?:post|video)/(?P<id>[0-9]+)(?:$|[/?#])'
_NETRC_MACHINE = 'tumblr'
_LOGIN_URL = 'https://www.tumblr.com/login'
_TESTS = [{ _TESTS = [{
'url': 'http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes', 'url': 'http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes',
'md5': '479bb068e5b16462f5176a6828829767', 'md5': '479bb068e5b16462f5176a6828829767',
@ -97,6 +104,31 @@ class TumblrIE(InfoExtractor):
'add_ie': ['Instagram'], 'add_ie': ['Instagram'],
}] }]
def _real_initialize(self):
self._login()
def _login(self):
(username, password) = self._get_login_info()
if username is None:
return
self.report_login()
webpage = self._download_webpage(self._LOGIN_URL, None, False)
form = self._hidden_inputs(webpage)
form.update({
'user[email]': username,
'user[password]': password
})
login_response = self._download_webpage(
sanitized_Request(self._LOGIN_URL, urlencode_postdata(form), {
'Content-Type': 'application/x-www-form-urlencoded',
'Referer': self._LOGIN_URL
}), None, False, 'Wrong login info')
# Check the login response from Tumblr for an error message and fail the extraction if we find one.
login_errors = self._search_regex(r'Tumblr\.RegistrationForm\.errors\s*=\s*\[[\"|\'](.+)[\"|\']\]', login_response, 'login errors', False)
if login_errors:
raise ExtractorError('Error logging in: %s' % login_errors, expected=True)
def _real_extract(self, url): def _real_extract(self, url):
m_url = re.match(self._VALID_URL, url) m_url = re.match(self._VALID_URL, url)
video_id = m_url.group('id') video_id = m_url.group('id')