urls - reformat headers

[erebus.git] / modules / urls.py

diff --git a/modules/urls.py b/modules/urls.py
index c1e27055a8ead6cd53f3a4a64e3768ab2d152e4a..502920864c3fe619e533a28500cc087999f6c1dd 100644 (file)
--- a/modules/urls.py
+++ b/modules/urls.py
@@ -248,7 +248,21 @@ def _do_request(url, try_aia=False):
                - and a flag indicating whether AIA was used
        """
        try:
-               request = urllib2.Request(url, headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36', 'Sec-Ch-Ua': '"Chromium";v="116", "Not)A;Brand";v="24", "Google Chrome";v="116"', 'Sec-Ch-Ua-Mobile': '?0', 'Sec-Ch-Ua-Platform': '"Linux"', 'Sec-Fetch-Dest': 'document', 'Sec-Fetch-Mode': 'navigate', 'Sec-Fetch-Site': 'same-origin', 'Sec-Fetch-User': '?1', 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7', 'Accept-Language': 'en-US,en;q=0.9', 'Cache-Control': 'no-cache', 'Pragma': 'no-cache', 'Upgrade-Insecure-Requests': '1'})
+               request = urllib2.Request(url, headers={
+                       'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36',
+                       'Sec-Ch-Ua': '"Chromium";v="116", "Not)A;Brand";v="24", "Google Chrome";v="116"',
+                       'Sec-Ch-Ua-Mobile': '?0',
+                       'Sec-Ch-Ua-Platform': '"Linux"',
+                       'Sec-Fetch-Dest': 'document',
+                       'Sec-Fetch-Mode': 'navigate',
+                       'Sec-Fetch-Site': 'same-origin',
+                       'Sec-Fetch-User': '?1',
+                       'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
+                       'Accept-Language': 'en-US,en;q=0.9',
+                       'Cache-Control': 'no-cache',
+                       'Pragma': 'no-cache',
+                       'Upgrade-Insecure-Requests': '1'
+               })
        except ValueError:
                return '', False
        if try_aia:
@@ -336,7 +350,7 @@ def goturl(url):
        return ''.join(output)
 
 url_regex = (
-       re.compile(r'https?://(?:[^/\s.]+\.)+[^/\s.]+(?:/\S+)?'),
+       re.compile(r'https?://(?:[^/\s.]+\.)+[a-z0-9-]+(?:/[^\s\]>)}]+)?', re.I),
 )
 other_regexes = (
        (lambda x: '', (re.compile(r"""https?://(?:www\.)?(?:twitter|x)\.com/""", re.I),)), # skip twitter