A script to scrape information from your facebook friends

infb.css

/*
	Ruel Pagayon (c) 2010 - [email protected]
	
	Cascading Style Sheet for InFB Log Output.
*/
body {
	background-color: #3C3C3C;
	color: #FFF;
	margin-top: 50px;
	margin-left: 25px;
	font-size: xx-small;
	font-family: Calibri, Arial, sans;
}
.rby {
	text-align: center;
	font-size: xx-small;
}

table  {
	text-align: center;
}

td {
	padding-top: 0.5em;
	padding-bottom: 0.5em;
	padding-left: 1em;
	padding-right: 1em;
	text-align: left;
	font-size: small;
}

td.num {
	color: #CCC;
}

td.cnum {
	color: #AFAFAF;
}

a:active, a:visited, a:link  {
	color: #FFF;
	font-weight: bold;
	text-decoration: none;
}

a:hover {
	color: #FFF;
	font-weight: bold;
	text-decoration: underline;
}

infb.py

#!/usr/bin/python
#
#	InFB - Information Facebook
#	Usage: infb.py [email protected] password
#	http://ruel.me
#
#	Copyright (c) 2010, Ruel Pagayon - [email protected]
#	All rights reserved.
#
#	Redistribution and use in source and binary forms, with or without
#		* Redistributions of source code must retain the above copyright
#		  notice, this list of conditions and the following disclaimer.
#		* Redistributions in binary form must reproduce the above copyright
#		  notice, this list of conditions and the following disclaimer in the
#		  documentation and/or other materials provided with the distribution.
#		* Neither the name of ruel.me nor the names of its contributors
#		  may be used to endorse or promote products derived from this
#		  script without specific prior written permission.
#
#	THIS SCRIPT IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
#	ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
#	WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
#	DISCLAIMED. IN NO EVENT SHALL RUEL PAGAYON BE LIABLE FOR ANY
#	DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
#	(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
#	LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
#	ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
#	(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
#	SCRIPT, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.


import sys, re, urllib, urllib2, cookielib, HTMLParser, getpass

class FormScraper(HTMLParser.HTMLParser):
    """
    Scrapes the Facebook login page for form values that need to be submitted on login.
    Necessary because the form values change each time the login page is loaded.

    Usage:
    form_scraper = FormScraper()
    form_scraper.feed(html_from_facebook)
    form_values = form_scraper.values
    """

    def __init__(self, *args, **kwargs):
        HTMLParser.HTMLParser.__init__(self, *args, **kwargs)
        self.in_form = False
        self.values = []

    def handle_starttag(self, tag, attrs):
        tag = tag.lower()
        attrs = dict(attrs)

        if tag == 'form' and attrs['id'] == 'login_form':
            self.in_form = True
        elif self.in_form and tag == 'input' and attrs['type'] == 'hidden':
            self.values.append( (attrs['name'], attrs['value']) )

    def handle_endtag(self, tag):
        if tag.lower() == 'form' and self.in_form:
            self.in_form = False

def main():
    if len(sys.argv) < 2:
        usage()
    
    user = sys.argv[1]

    if len(sys.argv) < 3:
        passw = getpass.getpass("Enter password: ")
    else:
        passw = sys.argv[2]

    # Set needed modules
    CHandler = urllib2.HTTPCookieProcessor(cookielib.CookieJar())
    browser = urllib2.build_opener(CHandler)
    browser.addheaders = [('User-agent', 'InFB - [email protected] - http://ruel.me')]
    urllib2.install_opener(browser)

    #Retrieve login form data and initialize the cookies
    print 'Initializing..'
    res = browser.open('https://www.facebook.com/login.php')

    #Determine string encoding
    content_type = res.info()['Content-Type'].split('; ')
    encoding = 'utf-8'
    if len(content_type) > 1 and content_type[1].startswith('charset'):
        encoding = content_type[1].split('=')[1]
    html = unicode( res.read(), encoding=encoding )
    res.close()

    #scrape form for hidden inputs, add email and password to values
    form_scraper = FormScraper()
    form_scraper.feed(html)
    form_data = form_scraper.values
    form_data.extend( [('email', user), ('pass', passw)] )
    #HACK: urlencode doesn't like strings that aren't encoded with the 'encode' function.
    #Using html.encode(encoding) doesn't help either. why ??
    form_data = [ ( x.encode(encoding), y.encode(encoding) ) for x,y in form_data ]
    data = urllib.urlencode(form_data)

    # Login
    print 'Logging in to account ' + user
    res = browser.open('https://login.facebook.com/login.php?login_attempt=1', data)
    rcode = res.code
    print rcode
    print res.url
    if not re.search('home\.php$', res.url):
        print 'Login Failed'
        exit(2)
    res.close()

    # Get Emails and Phone Numbers
    print "Getting Info..\n"
    flog = open(user + '.html', 'a')
    flog.write("<html>\n\t<head>\n\t\t<title>InFB - " + user + "</title>\n\t\t<link href=\"infb.css\" rel=\"stylesheet\" type=\"text/css\" />\n\t</head>\n\t<body>\n\t\t<div class=\"rby\">\n\t\t\t<table class=\"flist\">\n\t\t\t\t")
    page = 0
    while True:
        res = browser.open('http://m.facebook.com/friends.php?a&f=' + str(page))
        parp = res.read()
        m = re.findall('"\/friends\.php\?id=([0-9]+)&', parp)
        res.close()
        for i in m:
            prof = 'http://m.facebook.com/profile.php?id=' + i + '&v=info'
            res = browser.open(prof)
            cont = res.read()
            res.close()
            prof = prof.replace('m.', 'www.')
            ms = re.search('<div id="body"><div><div>(.*?)<\/div>', cont)
            if ms:
                name = ms.group(1)
            else:
                continue
            ms = re.search('href="tel:(.*?)"', cont)
            if ms:
                tel = ms.group(1)
            else:
                tel = ''
            ms = re.search('Emails?:<\/div><\/td><td valign="top"><div>(.*?)<\/div>', cont)
            if ms:
                email = re.sub('<br \/>', ', ', ms.group(1)).replace('&#64;', '@')
            else:
                continue
            print name + ' : ' + email + ' ' + tel
            flog.write("<tr class=\"lbreak\">\n\t\t\t\t\t<td class=\"num\">" + i + "</td><td class=\"fname\"><a href=\"" + prof + "\" title=\"" + name + "\">" + name + "</a></td><td class=\"fmail\">" + email + "</td></td><td class=\"cnum\">" + tel + "</td>\n\t\t\t\t\t</tr>\n\t\t\t\t")
        if re.search('Next', parp):
            page += 10
        else:
            break
    flog.write("\n\t\t\t</table>\n\t\t</div>\n\t</body>\n</html>")
    flog.close()

def usage():
    print 'Usage: ' + sys.argv[0] + ' [email protected] [password]'
    sys.exit(1)

if __name__ == '__main__':
    main()