Created
April 23, 2019 13:29
-
-
Save shellkore/8e43f1edb5316c5fa7da777ad8deeb6d to your computer and use it in GitHub Desktop.
a code snippet to get list of HTTPS proxies from "free-proxy-list.net".
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import requests | |
import re | |
proxy_url = "https://free-proxy-list.net/" | |
def getProxyBuffer(): | |
headers = {'User-Agent': "Mozilla/5.0"} | |
source = str(requests.get(proxy_url, headers=headers, timeout=10).text) | |
data = [list(filter(None, i))[0] for i in re.findall("<td>(.*?)</td>|<td class='hx'>(.*?)</td>", source)] | |
groupings = [dict(zip(['ip', 'port', 'code', 'using_anonymous', 'https'], data[i:i + 5])) for i in | |
range(0, len(data), 5)] | |
for item in groupings: | |
try: | |
if item['https'] == 'no': | |
groupings.remove(item) | |
except: | |
pass | |
final_groupings = ["{ip}:{port}".format(**i) for i in groupings] | |
return final_groupings | |
getProxyBuffer() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment