gistfile1.py

import mechanize
import cookielib
from BeautifulSoup import BeautifulSoup

URL = 'http://leginfo.legislature.ca.gov/faces/codes.xhtml'

class Browser(object):
    def __init__(self, section, code):
        br = mechanize.Browser()
        cj = cookielib.LWPCookieJar()
        br.set_cookiejar(cj)
        br.set_handle_equiv(True)
        br.set_handle_gzip(True)
        br.set_handle_redirect(True)
        br.set_handle_referer(True)
        br.set_handle_robots(False)
        br.set_handle_refresh(mechanize._http.HTTPRefreshProcessor(), max_time=1)
        br.addheaders = [('User-agent','Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.1) Gecko/2008071615 Fedora/3.0.1-1.fc9 Firefox/3.0.1') ]
        self.browser = br
        self.browser.open(URL)
        self.browser.select_form(name='expertsearchformid')
        self.browser['expertsearchformid:toctextcodeid'] = [section]
        self.browser['expertsearchformid:toctextsectionid'] = str(code)
        self.browser.submit()
        self.response = self.browser.response().read()
        self.soup = BeautifulSoup(self.response)
        self.text = self.soup.find('div', {'id': 'codeLawSectionNoHead'}).prettify()