phenny/modules/head.py

#!/usr/bin/env python
"""
head.py - Phenny HTTP Metadata Utilities
Copyright 2008, Sean B. Palmer, inamidst.com
Licensed under the Eiffel Forum License 2.

http://inamidst.com/phenny/
"""

import re
import urllib.request
import urllib.parse
import urllib.error
import http.client
import http.cookiejar
import time
import web
from tools import deprecated
from modules.linx import get_title

cj = http.cookiejar.LWPCookieJar()
opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cj))
urllib.request.install_opener(opener)


def head(phenny, input): 
    """Provide HTTP HEAD information."""
    uri = input.group(2)
    uri = (uri or '')
    if ' ' in uri: 
        uri, header = uri.rsplit(' ', 1)
    else: uri, header = uri, None

    if not uri and hasattr(phenny, 'last_seen_uri'): 
        try: uri = phenny.last_seen_uri[input.sender]
        except KeyError: return phenny.say('?')

    if not uri.startswith('htt'): 
        uri = 'http://' + uri
    # uri = uri.replace('#!', '?_escaped_fragment_=')
    
    start = time.time()

    try:
        info = web.head(uri)
        info['status'] = '200'
    except urllib.error.HTTPError as e:
        return phenny.say(str(e.code))
    except http.client.InvalidURL:
        return phenny.say("Not a valid URI, sorry.")
    except IOError:
        return phenny.say("Can't connect to %s" % uri)

    resptime = time.time() - start

    if header is None: 
        data = []
        if 'Status' in info: 
            data.append(info['Status'])
        if 'content-type' in info: 
            data.append(info['content-type'].replace('; charset=', ', '))
        if 'last-modified' in info: 
            modified = info['last-modified']
            modified = time.strptime(modified, '%a, %d %b %Y %H:%M:%S %Z')
            data.append(time.strftime('%Y-%m-%d %H:%M:%S UTC', modified))
        if 'content-length' in info: 
            data.append(info['content-length'] + ' bytes')
        data.append('{0:1.2f} s'.format(resptime))
        phenny.reply(', '.join(data))
    else: 
        headerlower = header.lower()
        if headerlower in info: 
            phenny.say(header + ': ' + info.get(headerlower))
        else: 
            msg = 'There was no %s header in the response.' % header
            phenny.say(msg)
head.commands = ['head']
head.example = '.head http://www.w3.org/'

@deprecated
def f_title(self, origin, match, args): 
    """.title <URI> - Return the title of URI."""
    uri = match.group(2)
    uri = (uri or '')

    if not uri and hasattr(self, 'last_seen_uri'): 
        uri = self.last_seen_uri.get(origin.sender)
    if not uri: 
        return self.msg(origin.sender, 'I need a URI to give the title of...')
    title = get_title(uri)
    if title:
        self.msg(origin.sender, origin.nick + ': ' + title)
    else: self.msg(origin.sender, origin.nick + ': No title found')
f_title.commands = ['title']

r_title = re.compile(r'(?ims)<title[^>]*>(.*?)</title\s*>')
r_entity = re.compile(r'&[A-Za-z0-9#]+;')

def noteuri(phenny, input): 
    uri = input.group(1)
    if not hasattr(phenny.bot, 'last_seen_uri'): 
        phenny.bot.last_seen_uri = {}
    phenny.bot.last_seen_uri[input.sender] = uri
noteuri.rule = r'.*(http[s]?://[^<> "\x01]+)[,.]?'
noteuri.priority = 'low'

titlecommands = r'(?:' + r'|'.join(f_title.commands) + r')'
def snarfuri(phenny, input):
    if re.match(r'(?i)' + phenny.config.prefix + titlecommands, input.group()):
        return
    uri = input.group(1)
    title = get_title(uri, input.sender)
    if title:
        phenny.msg(input.sender, title)
snarfuri.rule = r'.*(http[s]?://[^<> "\x01]+)[,.]?'
snarfuri.priority = 'low'
snarfuri.thread = True


if __name__ == '__main__': 
    print(__doc__.strip())