"""
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',
- 'Upgrade-Insecure-Requests': '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': 'max-age=0',
+ 'sec-ch-ua': '"Chromium";v="122", "Not(A:Brand";v="24", "Google Chrome";v="122"',
+ 'sec-ch-ua-mobile': '?0',
+ 'sec-ch-ua-platform': '"Linux"',
+ 'sec-fetch-dest': 'document',
+ 'sec-fetch-mode': 'navigate',
+ 'sec-fetch-site': 'none',
+ 'sec-fetch-user': '?1',
+ 'upgrade-insecure-requests': '1',
+ 'user-agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36'
})
except ValueError:
return '', False
return ''.join(output)
url_regex = (
- re.compile(r'https?://(?:[^/\s.]+\.)+[a-z0-9-]+(?:/[^\s\]>)}]+)?', re.I),
+ re.compile(r'https?://(?:[^/\s.]+\.)+[a-z0-9-]+(?::\d{1,5})?(?:/[^\s\]>)}]+)?', re.I),
)
other_regexes = (
(lambda x: '', (re.compile(r"""https?://(?:www\.)?(?:twitter|x)\.com/""", re.I),)), # skip twitter