Darkly

import requests
from urllib.parse import urljoin
import re
import time

BASE_URL = "http://192.168.56.101/.hidden/"
visited = set()

HREF_RE = re.compile(r'href="([^"]+)"')

DICTIONARY = [
    "gauche", "voisin", "aide", "Demande", "droite", "toujours"
]
session = requests.Session()

def crawl(url):
    print(f"{url}")

    if url in visited:
        return False
    visited.add(url)

    try:
        r = session.get(url, timeout=5)
        if r.status_code != 200:
            return False
    except Exception as e:
        print(f"{e}")
        return False

    for line in r.text.splitlines():
        match = HREF_RE.search(line)
        if not match:
            continue

        name = match.group(1)
        if name == "../":
            continue

        full_url = urljoin(url, name)

        if name == "README":
            try:
                content = session.get(full_url, timeout=5).text
                content_lower = content.lower()
                if not any(word in content_lower for word in DICTIONARY):
                    print("\nREADME ISOLÉ DÉTECTÉ")
                    print("PATH :", full_url)
                    print("CONTENT :\n", content)
                    return True
                    

            except Exception as e:
                print(f"{e}")

        elif name.endswith("/"):
            if crawl(full_url):
                return True

    return False

if __name__ == "__main__":
    crawl(BASE_URL)
Créé il y a 1 semaine.