From 00ed3527b4f7c7cb3c2899785996573dcc96d854 Mon Sep 17 00:00:00 2001 From: Kuchen Date: Mon, 16 Oct 2023 16:01:42 +0200 Subject: [PATCH] will get proxies from tables now --- KC-Scraper.py | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/KC-Scraper.py b/KC-Scraper.py index d7cee06..354a424 100644 --- a/KC-Scraper.py +++ b/KC-Scraper.py @@ -21,6 +21,7 @@ class KCScraper: self.clearingProxy = "" self.proxyDelimiter = "" self.randomUseragent = "" + self.dictReplacements = {"&colon": ":", "": ":"} self.start = 0 @@ -112,7 +113,7 @@ class KCScraper: self.goodSites.add(site) locProxies = re.findall(r"\b\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}" + self.proxyDelimiter + - r"\d{1,5}\b", r.replace("&colon", ":")) + r"\d{1,5}\b", KCScraper.replaceAll(self, r)) length = len(locProxies) print(f"{self.prefix_plus} Scraped {self.color}{length}{self.white} from {self.color}{site}") self.proxyCount += length @@ -120,6 +121,12 @@ class KCScraper: if self.clearingProxy and length == 0: self.goodSites.remove(site) + def replaceAll(self, string: str) -> str: + for key, value in self.dictReplacements.items(): + string = string.replace(key, value) + + return string + def getSettings(self) -> tuple: with open("settings.yaml") as setting: settings = yaml.safe_load(setting.read())