Remove unused url.get_content()

This commit is contained in:
Chris Mayo 2020-08-18 19:57:46 +01:00
parent e4ba9c84ce
commit e372657fb8
2 changed files with 1 additions and 53 deletions

View file

@ -21,10 +21,6 @@ import os
import re
import urllib.parse
import requests
from . import log, LOG_CHECK
for scheme in ('ldap', 'irc'):
if scheme not in urllib.parse.uses_netloc:
urllib.parse.uses_netloc.append(scheme)
@ -479,50 +475,6 @@ def splitport(host, port=0):
return host, port
def get_content(url, user=None, password=None, proxy=None, data=None, addheaders=None):
"""Get URL content and info.
@return: (decoded text content of URL, headers) or
(None, errmsg) on error.
@rtype: tuple (String, dict) or (None, String)
"""
from . import configuration
headers = {
'User-Agent': configuration.UserAgent,
}
if addheaders:
headers.update(addheaders)
method = 'GET'
kwargs = dict(headers=headers)
if user and password:
kwargs['auth'] = (user, password)
if data:
kwargs['data'] = data
method = 'POST'
if proxy:
kwargs['proxy'] = dict(http=proxy)
from .configuration import get_share_file
try:
kwargs["verify"] = get_share_file('cacert.pem')
except ValueError:
pass
try:
response = requests.request(method, url, **kwargs)
return response.text, response.headers
except (
requests.exceptions.RequestException,
requests.exceptions.BaseHTTPError,
) as msg:
log.warn(
LOG_CHECK,
("Could not get content of URL %(url)s: %(msg)s.")
% {"url": url, "msg": str(msg)},
)
return None, str(msg)
def shorten_duplicate_content_url(url):
"""Remove anchor part and trailing index.html from URL."""
if '#' in url:

View file

@ -17,7 +17,7 @@
"""
Test url routines.
"""
from . import need_network, need_posix, need_windows
from . import need_posix, need_windows
import unittest
import os
import re
@ -547,10 +547,6 @@ class TestUrl(unittest.TestCase):
self.assertTrue(is_safe_domain("a-b.example.com"))
self.assertTrue(is_safe_domain("x1.example.com"))
@need_network
def test_get_content(self):
linkcheck.url.get_content("http://www.debian.org/")
def test_duplicate_urls(self):
is_dup = linkcheck.url.is_duplicate_content_url
self.assertTrue(is_dup("http://example.org", "http://example.org"))