midgard/youtube-dl
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[tumblr] Improve authentication (closes #15133)

Browse source
This commit is contained in:
Sergey M․ 2018-05-26 19:53:32 +07:00
parent c678192af3
commit 56cd31f320
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 26 additions and 13 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

39
youtube_dl/extractor/tumblr.py
View file

@ -7,7 +7,6 @@ from .common import InfoExtractor
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
int_or_none, int_or_none,
sanitized_Request,
urlencode_postdata urlencode_postdata
) )
@ -111,23 +110,37 @@ class TumblrIE(InfoExtractor):
(username, password) = self._get_login_info() (username, password) = self._get_login_info()
if username is None: if username is None:
return return
self.report_login()
webpage = self._download_webpage(self._LOGIN_URL, None, False) login_page = self._download_webpage(
form = self._hidden_inputs(webpage) self._LOGIN_URL, None, 'Downloading login page')
form.update({
login_form = self._hidden_inputs(login_page)
login_form.update({
'user[email]': username, 'user[email]': username,
'user[password]': password '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. response, urlh = self._download_webpage_handle(
login_errors = self._search_regex(r'Tumblr\.RegistrationForm\.errors\s*=\s*\[[\"|\'](.+)[\"|\']\]', login_response, 'login errors', False) self._LOGIN_URL, None, 'Logging in',
data=urlencode_postdata(login_form), headers={
'Content-Type': 'application/x-www-form-urlencoded',
'Referer': self._LOGIN_URL,
})
# Successful login
if '/dashboard' in urlh.geturl():
return
login_errors = self._parse_json(
self._search_regex(
r'RegistrationForm\.errors\s*=\s*(\[.+?\])\s*;', response,
'login errors', default='[]'),
None, fatal=False)
if login_errors: if login_errors:
raise ExtractorError('Error logging in: %s' % login_errors, expected=True) raise ExtractorError(
'Unable to login: %s' % login_errors[0], expected=True)
self.report_warning('Login has probably failed')
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)