Skip to content

feat: added verify_ssl_cert option to pass to requests for proxy use #9

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
vpol merged 1 commit into from
Nov 30, 2025
Merged

feat: added verify_ssl_cert option to pass to requests for proxy use #9

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions newspaper/configuration.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -72,6 +72,7 @@ def __init__(self):
self.request_timeout = 7
self.proxies = {}
self.number_threads = 10
self.verify_ssl_cert = True

self.verbose = False # for debugging

Expand Down
8 changes: 5 additions & 3 deletions newspaper/network.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@
FAIL_ENCODING = 'ISO-8859-1'


def get_request_kwargs(timeout, useragent, proxies, headers, allow_redirects):
def get_request_kwargs(timeout, useragent, proxies, headers, allow_redirects, verify_ssl_cert):
"""This Wrapper method exists b/c some values in req_kwargs dict
are methods which need to be called every time we make a request
"""
Expand All @@ -30,7 +30,8 @@ def get_request_kwargs(timeout, useragent, proxies, headers, allow_redirects):
'cookies': cj(),
'timeout': timeout,
'allow_redirects': allow_redirects,
'proxies': proxies
'proxies': proxies,
'verify': verify_ssl_cert,
}


Expand All @@ -55,6 +56,7 @@ def get_html_2XX_only(url, config=None, response=None, return_final_url=False):
timeout = config.request_timeout
proxies = config.proxies
headers = config.headers
verify_ssl_cert = config.verify_ssl_cert
allow_redirects = config.allow_redirects

if response is not None:
Expand All @@ -64,7 +66,7 @@ def get_html_2XX_only(url, config=None, response=None, return_final_url=False):
return html

response = requests.get(
url=url, **get_request_kwargs(timeout, useragent, proxies, headers, allow_redirects))
url=url, **get_request_kwargs(timeout, useragent, proxies, headers, allow_redirects, verify_ssl_cert))

html = _get_html_from_response(response, config)
final_url = response.url
Expand Down