aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2019-05-18 03:23:40 +0700
committerSergey M․ <dstftw@gmail.com>2019-05-18 03:33:40 +0700
commita9e03736dfb2038d6a569e6305f4ac727a8ac71b (patch)
tree310a16cd828290b96ccd8ea530141196316aeda2
parente3c1266f492d710e2acbf0d80f44f7f805eb5187 (diff)
downloadyoutube-dl-a9e03736dfb2038d6a569e6305f4ac727a8ac71b.tar.xz
[safari] Fix authentication (closes #21090)
-rw-r--r--youtube_dl/extractor/safari.py87
1 files changed, 52 insertions, 35 deletions
diff --git a/youtube_dl/extractor/safari.py b/youtube_dl/extractor/safari.py
index c0d32a1b9..8d4806794 100644
--- a/youtube_dl/extractor/safari.py
+++ b/youtube_dl/extractor/safari.py
@@ -1,15 +1,18 @@
# coding: utf-8
from __future__ import unicode_literals
+import json
import re
from .common import InfoExtractor
+from ..compat import (
+ compat_parse_qs,
+ compat_str,
+ compat_urlparse,
+)
from ..utils import (
ExtractorError,
- sanitized_Request,
- std_headers,
- urlencode_postdata,
update_url_query,
)
@@ -31,44 +34,52 @@ class SafariBaseIE(InfoExtractor):
if username is None:
return
- headers = std_headers.copy()
- if 'Referer' not in headers:
- headers['Referer'] = self._LOGIN_URL
-
- login_page = self._download_webpage(
- self._LOGIN_URL, None, 'Downloading login form', headers=headers)
+ _, urlh = self._download_webpage_handle(
+ 'https://learning.oreilly.com/accounts/login-check/', None,
+ 'Downloading login page')
- def is_logged(webpage):
- return any(re.search(p, webpage) for p in (
- r'href=["\']/accounts/logout/', r'>Sign Out<'))
+ def is_logged(urlh):
+ return 'learning.oreilly.com/home/' in compat_str(urlh.geturl())
- if is_logged(login_page):
+ if is_logged(urlh):
self.LOGGED_IN = True
return
- csrf = self._html_search_regex(
- r"name='csrfmiddlewaretoken'\s+value='([^']+)'",
- login_page, 'csrf token')
+ redirect_url = compat_str(urlh.geturl())
+ parsed_url = compat_urlparse.urlparse(redirect_url)
+ qs = compat_parse_qs(parsed_url.query)
+ next_uri = compat_urlparse.urljoin(
+ 'https://api.oreilly.com', qs['next'][0])
+
+ auth, urlh = self._download_json_handle(
+ 'https://www.oreilly.com/member/auth/login/', None, 'Logging in',
+ data=json.dumps({
+ 'email': username,
+ 'password': password,
+ 'redirect_uri': next_uri,
+ }).encode(), headers={
+ 'Content-Type': 'application/json',
+ 'Referer': redirect_url,
+ }, expected_status=400)
+
+ credentials = auth.get('credentials')
+ if (not auth.get('logged_in') and not auth.get('redirect_uri')
+ and credentials):
+ raise ExtractorError(
+ 'Unable to login: %s' % credentials, expected=True)
- login_form = {
- 'csrfmiddlewaretoken': csrf,
- 'email': username,
- 'password1': password,
- 'login': 'Sign In',
- 'next': '',
- }
+ # oreilly serves two same groot_sessionid cookies in Set-Cookie header
+ # and expects first one to be actually set
+ self._apply_first_set_cookie_header(urlh, 'groot_sessionid')
- request = sanitized_Request(
- self._LOGIN_URL, urlencode_postdata(login_form), headers=headers)
- login_page = self._download_webpage(
- request, None, 'Logging in')
+ _, urlh = self._download_webpage_handle(
+ auth.get('redirect_uri') or next_uri, None, 'Completing login',)
- if not is_logged(login_page):
- raise ExtractorError(
- 'Login failed; make sure your credentials are correct and try again.',
- expected=True)
+ if is_logged(urlh):
+ self.LOGGED_IN = True
+ return
- self.LOGGED_IN = True
+ raise ExtractorError('Unable to log in')
class SafariIE(SafariBaseIE):
@@ -76,7 +87,7 @@ class SafariIE(SafariBaseIE):
IE_DESC = 'safaribooksonline.com online video'
_VALID_URL = r'''(?x)
https?://
- (?:www\.)?(?:safaribooksonline|learning\.oreilly)\.com/
+ (?:www\.)?(?:safaribooksonline|(?:learning\.)?oreilly)\.com/
(?:
library/view/[^/]+/(?P<course_id>[^/]+)/(?P<part>[^/?\#&]+)\.html|
videos/[^/]+/[^/]+/(?P<reference_id>[^-]+-[^/?\#&]+)
@@ -107,6 +118,9 @@ class SafariIE(SafariBaseIE):
}, {
'url': 'https://learning.oreilly.com/videos/hadoop-fundamentals-livelessons/9780133392838/9780133392838-00_SeriesIntro',
'only_matching': True,
+ }, {
+ 'url': 'https://www.oreilly.com/library/view/hadoop-fundamentals-livelessons/9780133392838/00_SeriesIntro.html',
+ 'only_matching': True,
}]
_PARTNER_ID = '1926081'
@@ -163,7 +177,7 @@ class SafariIE(SafariBaseIE):
class SafariApiIE(SafariBaseIE):
IE_NAME = 'safari:api'
- _VALID_URL = r'https?://(?:www\.)?(?:safaribooksonline|learning\.oreilly)\.com/api/v1/book/(?P<course_id>[^/]+)/chapter(?:-content)?/(?P<part>[^/?#&]+)\.html'
+ _VALID_URL = r'https?://(?:www\.)?(?:safaribooksonline|(?:learning\.)?oreilly)\.com/api/v1/book/(?P<course_id>[^/]+)/chapter(?:-content)?/(?P<part>[^/?#&]+)\.html'
_TESTS = [{
'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
@@ -188,7 +202,7 @@ class SafariCourseIE(SafariBaseIE):
_VALID_URL = r'''(?x)
https?://
(?:
- (?:www\.)?(?:safaribooksonline|learning\.oreilly)\.com/
+ (?:www\.)?(?:safaribooksonline|(?:learning\.)?oreilly)\.com/
(?:
library/view/[^/]+|
api/v1/book|
@@ -219,6 +233,9 @@ class SafariCourseIE(SafariBaseIE):
}, {
'url': 'https://learning.oreilly.com/videos/hadoop-fundamentals-livelessons/9780133392838',
'only_matching': True,
+ }, {
+ 'url': 'https://www.oreilly.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
+ 'only_matching': True,
}]
@classmethod