Unlimited Residential Proxies for AI, RAG & LLM Data Training Proxies

import os
import requests
from bs4 import BeautifulSoup

PROXY_URL = "http://your_username:your_password@gate.proxytee.com:8080"
proxies = {"http": PROXY_URL, "https": PROXY_URL}

def fetch_clean_markdown_text(url: str) -> str:
    resp = requests.get(url, proxies=proxies, headers={"User-Agent": "Mozilla/5.0"}, timeout=20)
    soup = BeautifulSoup(resp.text, "html.parser")
    return " ".join(p.get_text(" ", strip=True) for p in soup.find_all("p"))

print("Extracted RAG Context Characters:", len(fetch_clean_markdown_text("https://example.com")))