generated from nathanwoodburn/python-webserver-template
parent
ec59656cad
commit
50275ba482
GPG Key ID:
203B000478AD0EF1
@ -4,4 +4,6 @@ requests
|
||||
python-dotenv
|
||||
dnspython
|
||||
cryptography
|
||||
datetime
|
||||
datetime
|
||||
beautifulsoup4
|
||||
requests-doh
|
||||
26
server.py
26
server.py
@ -24,6 +24,8 @@ dotenv.load_dotenv()
|
||||
app = Flask(__name__)
|
||||
|
||||
|
||||
BLOCKED_PATHS = ["https.js"]
|
||||
|
||||
def find(name, path):
|
||||
for root, dirs, files in os.walk(path):
|
||||
if name in files:
|
||||
@ -79,6 +81,30 @@ def wellknown(path):
|
||||
def index():
|
||||
return render_template("index.html")
|
||||
|
||||
@app.route("/proxy/<path:url>")
|
||||
def proxy(url: str):
|
||||
# Decode the URL
|
||||
url = urllib.parse.unquote(url)
|
||||
# Get last path segment
|
||||
path = url.split("/")[-1]
|
||||
if path in BLOCKED_PATHS:
|
||||
return render_template("404.html"), 403
|
||||
|
||||
|
||||
|
||||
content: requests.Response = tools.proxy(url)
|
||||
if not content.ok:
|
||||
return render_template("500.html"), 500
|
||||
|
||||
# Get the content type
|
||||
contentType = content.headers.get("Content-Type")
|
||||
if "text/html" in contentType:
|
||||
return tools.cleanProxyContent(content.text,url,request.host_url)
|
||||
|
||||
response = make_response(content.content)
|
||||
response.headers["Content-Type"] = contentType
|
||||
return response
|
||||
|
||||
|
||||
@app.route("/<path:path>")
|
||||
def catch_all(path: str):
|
||||
|
||||
21
templates/500.html
Normal file
21
templates/500.html
Normal file
@ -0,0 +1,21 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="en">
|
||||
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
<title>Nathan.Woodburn/</title>
|
||||
<link rel="icon" href="/assets/img/favicon.png" type="image/png">
|
||||
<link rel="stylesheet" href="/assets/css/404.css">
|
||||
</head>
|
||||
|
||||
<body>
|
||||
<div class="spacer"></div>
|
||||
<div class="centre">
|
||||
<h1>500 | Internal Server Error</h1>
|
||||
<p>Sorry, we can't seem to display this page. Maybe try again or your request might not be valid</p>
|
||||
<p><a href="/">Go back to the homepage</a></p>
|
||||
</div>
|
||||
</body>
|
||||
|
||||
</html>
|
||||
60
tools.py
60
tools.py
@ -1,4 +1,5 @@
|
||||
import random
|
||||
from urllib.parse import urlparse
|
||||
import dns.resolver
|
||||
import subprocess
|
||||
import tempfile
|
||||
@ -8,10 +9,19 @@ from cryptography.hazmat.backends import default_backend
|
||||
import datetime
|
||||
from dns import resolver
|
||||
import requests
|
||||
import re
|
||||
from bs4 import BeautifulSoup
|
||||
from requests_doh import DNSOverHTTPSSession, add_dns_provider
|
||||
import urllib3
|
||||
|
||||
|
||||
resolver = dns.resolver.Resolver()
|
||||
resolver.nameservers = ["194.50.5.28","194.50.5.27","194.50.5.26"]
|
||||
resolver.port = 53
|
||||
add_dns_provider("HNSDoH", "https://hnsdoh.com/dns-query")
|
||||
|
||||
# Disable warnings
|
||||
urllib3.disable_warnings()
|
||||
|
||||
|
||||
def check_ssl(domain: str):
|
||||
@ -179,14 +189,56 @@ def curl(url: str):
|
||||
url = "http://" + url
|
||||
try:
|
||||
# curl --doh-url https://hnsdoh.com/dns-query {url} --insecure
|
||||
commmand = f"curl --doh-url https://hnsdoh.com/dns-query {url} --insecure --silent"
|
||||
response = subprocess.run(commmand, shell=True, capture_output=True, text=True)
|
||||
command = f"curl --doh-url https://hnsdoh.com/dns-query {url} --insecure --silent"
|
||||
response = subprocess.run(command, shell=True, capture_output=True, text=True)
|
||||
if response.returncode != 0:
|
||||
return {"success": False, "error": response.stderr}
|
||||
else:
|
||||
return {"success": True, "result": response.stdout}
|
||||
except:
|
||||
return {"success": False, "error": "An error occurred"}
|
||||
|
||||
except Exception as e:
|
||||
return {"success": False, "error": "An error occurred", "message": str(e)}
|
||||
|
||||
def proxy(url: str) -> requests.Response:
|
||||
session = DNSOverHTTPSSession("HNSDoH")
|
||||
r = session.get(url,verify=False)
|
||||
return r
|
||||
|
||||
|
||||
|
||||
|
||||
def cleanProxyContent(htmlContent: str,url:str, proxyHost: str):
|
||||
# Find all instances of the url in the html
|
||||
hostUrl = f"{urlparse(url).scheme}://{urlparse(url).netloc}"
|
||||
proxyUrl = f"{proxyHost}proxy/{hostUrl}"
|
||||
# htmlContent = htmlContent.replace(hostUrl,proxyUrl)
|
||||
|
||||
# parse html
|
||||
soup = BeautifulSoup(htmlContent, 'html.parser')
|
||||
# find all resources
|
||||
|
||||
|
||||
for linkType in ['link','img','script', 'a']:
|
||||
links = soup.find_all(linkType)
|
||||
for link in links:
|
||||
for attrib in ['src','href']:
|
||||
if link.has_attr(attrib):
|
||||
if str(link[attrib]).startswith('/'):
|
||||
link.attrs[attrib] = proxyUrl + link[attrib]
|
||||
continue
|
||||
if str(link[attrib]).startswith('http'):
|
||||
link.attrs[attrib] = str(link[attrib]).replace(hostUrl,proxyUrl)
|
||||
continue
|
||||
ignored = False
|
||||
for ignore in ["data:", "mailto:", "tel:", "javascript:", "blob:"]:
|
||||
if str(link[attrib]).startswith(ignore):
|
||||
ignored = True
|
||||
break
|
||||
if not ignored:
|
||||
link.attrs[attrib] = f"{proxyUrl}/{link[attrib]}"
|
||||
|
||||
|
||||
return soup.prettify()
|
||||
|
||||
# if __name__ == "__main__":
|
||||
# print(curl("https://dso.dprofile"))
|
||||
Loading…
Reference in New Issue
Block a user