Last active
October 25, 2015 12:23
-
-
Save koutoftimer/8053332bae362a3430f0 to your computer and use it in GitHub Desktop.
habraproxy
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# ~*~ encoding: utf-8 ~*~ | |
import argparse | |
import re | |
import requests | |
from urllib import urlencode | |
from urlparse import urljoin, urlparse | |
from bs4 import BeautifulSoup | |
from flask import Flask, Response, stream_with_context, request | |
app = Flask(__name__) | |
app.HOST = 'http://habrahabr.ru' | |
app.DOMAIN = None | |
ALLOWED_CONTENT_TYPES = ('text/html', 'text/xml', 'text/xhtml', 'text/plain') | |
WORD_RE = re.compile(r'(?P<prefix>^|\W)(?P<word>\w{6})(?P<suffix>$|\W)', | |
re.UNICODE) | |
WORD_REPLACEMENT = u'\g<prefix>\g<word>™\g<suffix>' | |
def html_content_type(content_type): | |
""" | |
Determine whether `content_type` is subset of xml or plain text. | |
:type content_type: str | |
:rtype: bool | |
""" | |
return any(map(content_type.count, ALLOWED_CONTENT_TYPES)) | |
def replace(text): | |
html = BeautifulSoup(text, 'html.parser') | |
for line in html.find_all(text=True): | |
line.replace_with(WORD_RE.sub(WORD_REPLACEMENT, line)) | |
return str(html) | |
@app.route('/<path:url>') | |
def home(url): | |
headers = {k: v for k, v in request.headers if v} | |
headers.update({'Host': app.DOMAIN}) | |
url = ''.join([urljoin(app.HOST, url), urlencode(request.args)]) | |
response = requests.get( | |
url, stream=True, headers=headers, cookies=request.cookies) | |
if not html_content_type(response.headers['content-type']) or \ | |
response.status_code >= 300: | |
return Response(stream_with_context(response.iter_content()), | |
content_type=response.headers['content-type']) | |
return replace(response.text) | |
@app.route('/') | |
def index(): | |
return home('') | |
if __name__ == '__main__': | |
parser = argparse.ArgumentParser() | |
parser.add_argument('--host', help='Site host name, including protocol: ' | |
'http://host, https://host') | |
args = parser.parse_args() | |
#: Configure flask app. | |
if args.host: | |
app.HOST = args.host | |
app.DOMAIN = urlparse(app.HOST).netloc | |
app.run() | |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
beautifulsoup4 | |
flask | |
requests |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
$ python habraproxy.py --help | |
usage: habraproxy.py [-h] [--host HOST] | |
optional arguments: | |
-h, --help show this help message and exit | |
--host HOST Site host name, including protocol: http://host, https://host | |
$ python habraproxy.py --host https://docs.python.org | |
* Running on http://127.0.0.1:5000/ (Press CTRL+C to quit) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment