Simple Python proxy server based on Flask and Requests. See: http:/python-proxy-server/gear11.com/2013/12/python-proxy-server/

main.py

"""
A simple proxy server. Usage:

http://hostname:port/p/(URL to be proxied, minus protocol)

For example:

http://localhost:8080/p/www.google.com

"""
from flask import Flask, render_template, request, abort, Response, redirect
import requests
import logging

app = Flask(__name__.split('.')[0])
logging.basicConfig(level=logging.INFO)
APPROVED_HOSTS = set(["google.com", "www.google.com", "yahoo.com"])
CHUNK_SIZE = 1024
LOG = logging.getLogger("main.py")


@app.route('/<path:url>')
def root(url):
    LOG.info("Root route, path: %s", url)
    # If referred from a proxy request, then redirect to a URL with the proxy prefix.
    # This allows server-relative and protocol-relative URLs to work.
    proxy_ref = proxy_ref_info(request)
    if proxy_ref:
        redirect_url = "/p/%s/%s%s" % (proxy_ref[0], url, ("?" + request.query_string if request.query_string else ""))
        LOG.info("Redirecting referred URL to: %s", redirect_url)
        return redirect(redirect_url)
    # Otherwise, default behavior
    return render_template('hello.html', name=url,request=request)


@app.route('/p/<path:url>')
def proxy(url):
    """Fetches the specified URL and streams it out to the client.

    If the request was referred by the proxy itself (e.g. this is an image fetch for
    a previously proxied HTML page), then the original Referer is passed."""
    r = get_source_rsp(url)
    LOG.info("Got %s response from %s",r.status_code, url)
    headers = dict(r.headers)
    def generate():
        for chunk in r.iter_content(CHUNK_SIZE):
            yield chunk
    return Response(generate(), headers = headers)


def get_source_rsp(url):
        url = 'http://%s' % url
        LOG.info("Fetching %s", url)
        # Ensure the URL is approved, else abort
        if not is_approved(url):
            LOG.warn("URL is not approved: %s", url)
            abort(403)
        # Pass original Referer for subsequent resource requests
        proxy_ref = proxy_ref_info(request)
        headers = { "Referer" : "http://%s/%s" % (proxy_ref[0], proxy_ref[1])} if proxy_ref else {}
        # Fetch the URL, and stream it back
        LOG.info("Fetching with headers: %s, %s", url, headers)
        return requests.get(url, stream=True , params = request.args, headers=headers)


def is_approved(url):
    """Indicates whether the given URL is allowed to be fetched.  This
    prevents the server from becoming an open proxy"""
    host = split_url(url)[1]
    return host in APPROVED_HOSTS


def split_url(url):
    """Splits the given URL into a tuple of (protocol, host, uri)"""
    proto, rest = url.split(':', 1)
    rest = rest[2:].split('/', 1)
    host, uri = (rest[0], rest[1]) if len(rest) == 2 else (rest[0], "")
    return (proto, host, uri)


def proxy_ref_info(request):
    """Parses out Referer info indicating the request is from a previously proxied page.

    For example, if:
        Referer: http://localhost:8080/p/google.com/search?q=foo
    then the result is:
        ("google.com", "search?q=foo")
    """
    ref = request.headers.get('referer')
    if ref:
        _, _, uri = split_url(ref)
        if uri.find("/") < 0:
            return None
        first, rest = uri.split("/", 1)
        if first in "pd":
            parts = rest.split("/", 1)
            r = (parts[0], parts[1]) if len(parts) == 2 else (parts[0], "")
            LOG.info("Referred by proxy host, uri: %s, %s", r[0], r[1])
            return r
    return None

I'm working on a flask-based, bitcoin micro-payments proxy for a small server. This code helped.

Content-Encoding gzip is not considered.

This was neat and helpful! Thanks

Doesn't work for video files - (specifically, the seeking). Does someone know why?

Example: /p/cdn.selz.com/plyr/1.5/View_From_A_Blue_Moon_Trailer-HD.mp4

Don't use generate() in line 48 else you get truncated data if content is gzipped encoded.
Either use r.raw.data (and delete generate function) or iterate over r.raw.stream(decode_content=False) instead of r.iter_content()

I'm still getting "Illegal or missing hexadecimal sequence in chunked-encoding" :(
I tied both with r.raw.data and r.raw.stream(...).
I can get response content via r.text and even construct the response Response but somehow client fails with
The response headers were:

Content-Type: application/vnd.orcid+xml; qs=5; charset=UTF-8'
Transfer-Encoding: chunked
Connection: keep-alive
Content-Encoding: gzip

Any ideas what might have gone wrong?

@gear11 do you have a preferred license for this? My preference is for MIT, but since I'm forking this wanted to pass that by you.