Last active
September 5, 2016 11:23
-
-
Save MyGodIsHe/22a34069cf25f645578ebb96886b7c5c to your computer and use it in GitHub Desktop.
pip install BeautifulSoup
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
#!/usr/bin/python | |
import SocketServer | |
import SimpleHTTPServer | |
import urllib | |
import re | |
from BeautifulSoup import BeautifulSoup, NavigableString, Tag, PageElement | |
TARGET = 'habrahabr.ru' | |
HOST = '127.0.0.1' | |
PORT = 8232 | |
PROXY_URL = 'http://%s:%s' % (HOST, PORT) | |
URL_REGEX = re.compile('^https?://%s' % TARGET) | |
# fix ampersand bug | |
PageElement._sub_entity = lambda self, x: x.group(0)[0] | |
def find_text(tag): | |
t_tag = type(tag) | |
if t_tag == Tag: | |
if tag.name in ['script', 'style']: | |
return [] | |
# replace target url | |
if tag.name == 'a' and tag.get('href'): | |
tag['href'] = URL_REGEX.sub(PROXY_URL, tag['href']) | |
# text | |
if t_tag == NavigableString: | |
return [tag] | |
# deep | |
data = [] | |
if hasattr(tag, 'contents'): | |
for i in tag.contents: | |
data.extend(find_text(i)) | |
return data | |
def tm_injection(data): | |
ln = 0 | |
for c in data: | |
if c.isalpha(): | |
ln += 1 | |
else: | |
if ln == 6: | |
c = '™' + c | |
ln = 0 | |
yield c | |
if ln == 6: | |
yield '™' | |
class HabrWrapper(object): | |
def __init__(self, f): | |
self.file = f | |
def read(self, size=None): | |
# read all | |
page = '' | |
while 1: | |
buf = self.file.read(16*1024) | |
if not buf: | |
break | |
page += buf | |
if not page: | |
return | |
soup = BeautifulSoup(page) | |
soup.convertHTMLEntities = False | |
text_tags = find_text(soup) | |
for tag in text_tags: | |
m_str = ''.join(tm_injection(tag.string)) | |
tag.replaceWith(m_str) | |
return soup | |
def __getattr__(self, attr): | |
return getattr(self.file, attr) | |
class Proxy(SimpleHTTPServer.SimpleHTTPRequestHandler): | |
def do_GET(self): | |
print self.requestline | |
f = urllib.urlopen('http://%s%s' % (TARGET, self.path)) | |
if f.headers['Content-Type'].startswith('text/html;'): | |
f = HabrWrapper(f) | |
self.copyfile(f, self.wfile) | |
if __name__ == '__main__': | |
httpd = SocketServer.TCPServer((HOST, PORT), Proxy) | |
print 'Starting proxy server at %s' % PROXY_URL | |
httpd.serve_forever() | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment