gistfile1.py

#! /usr/bin/env python3

# USAGE:
# h -- prints out the http server headers for a given URL
# Command-Line: h [agent] URL
# Agent can be any of: ff, chrome, ie, googlebot, safari
# If nothing is given on the command line, clipboard data
# is tried (under OS X and Windows). If it contains a valid
# URL, then that is used.

import sys
import http.client
import urllib.parse
import textwrap
import subprocess

AGENTS = {
  'ff': 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.2b4) ' \
        'Gecko/20091124 Firefox/3.6b4',
  'chrome': 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/533.4 ' \
            '(KHTML, like Gecko) Chrome/5.0.375.125 Safari/533.4',
  'ie': 'Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; SLCC1; .NET ' \
        'CLR 3.0.4506.2152; .NET CLR 3.5.30729; .NET CLR 1.1.4322)',
  'googlebot': 'Googlebot/2.1 (+http://www.googlebot.com/bot.html)',
  'safari': 'Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_3; en-us) AppleWebKit/534.1+ ' \
            '(KHTML, like Gecko) Version/5.0 Safari/533.16'
}

def wrap(s, indent_by):
    prefix = ' ' * indent_by
    return '\n'.join(prefix + x for x in textwrap.wrap(s, 50)).lstrip()

def url_from_clipboard():
    data = ''
    if sys.platform == 'darwin':
        data = subprocess.getoutput('pbpaste')
    elif sys.platform == 'win32':
        try:
            import ctypes
        except ImportError:
            pass
        else:
            ctypes.windll.user32.OpenClipboard(None)
            pc = ctypes.windll.user32.GetClipboardData(1)
            data = ctypes.c_char_p(pc).value
    if data.startswith('http') or data.startswith('www.'):
        return data
    else:
        return None

def get_headers(url, user_agent):
    if not url.startswith('http'):
        url = 'http://' + url
    parts = urllib.parse.urlparse(url)
    cls = http.client.HTTPConnection
    if parts.scheme == 'https':
        cls = http.client.HTTPSConnection
    hconn = cls(parts.hostname, parts.port)
    client_headers = {}
    if user_agent:
        client_headers['User-Agent'] = user_agent
    hconn.request('GET', parts.path or '/', headers=client_headers)
    return hconn.getresponse().getheaders()

def main():
    url = None
    agent = None
    nargs = len(sys.argv) - 1

    if nargs == 0:
        url = url_from_clipboard()
    elif nargs == 1:
        url = sys.argv[1]
    else:
        agent = AGENTS.get(sys.argv[1])
        url = sys.argv[2]
    if not url:
        return

    try:
        headers = get_headers(url, agent)
        headers.sort()
        headers.insert(0, ('Url', url))
        for k, v in headers:
            print('{0:>20}: {1}'.format(k, wrap(v, 23)))
    except Exception as e:
        print("** error", e)

if __name__ == '__main__':
    main()