source: py-scraping/foo.py@ 177

import json
import re
import mechanize
import sys
import pprint

cj = mechanize.LWPCookieJar()
cj.load("mycookies.txt",ignore_discard=True, ignore_expires=True)
#pprint.pprint(cj._cookies)

br = mechanize.Browser()
br.set_cookiejar(cj)

#br.open('https://login.facebook.com/login.php')
#br.select_form(nr=0)
#br["email"] = "rickvanderzwet@gmail.com"
#br["pass"] = "PASSWORD"
#response1 = br.submit()
#cj.save("mycookies.txt",ignore_discard=True, ignore_expires=True)
#pprint.pprint(cj._cookies)

#response2 = br.open('http://www.facebook.com/ajax/intent.php?filter=lf&__a=1')

#f = open('json.foo', 'w')
#f.write(response2.read())
#f.close()
#json.loads(response2.read())

f = open('json.foo', 'r')
foo = f.read()
foo = foo[9:]
#pprint.pprint(foo)
obj = json.loads(foo)

from xml.dom.minidom import parse, parseString
s = obj["payload"]["html"]
s = s.encode("utf-8")
pprint.pprint(s)
import tidy
s = tidy.parseString(s, indent=1, tidy_mark=0,doctype="omit").__str__()
print s.split()[14:20]
doc = parseString(s)
print doc.getElementsByTagName("a")
# br.select_form(name='login_form')
#url = 'https://login.facebook.com/login.php?login_attempt=1'
#values = {'email' : 'rickvanderzwet@gmail.com',
#'pass' : 'M3nF00b2r!F'}