Python Mechanize Cheat Sheet

Python Mechanize Overview

• Python mechanize site http://wwwsearch.sourceforge.net/mechanize/
• mechanize docs http://wwwsearch.sourceforge.net/mechanize/doc.html
• ClientForm docs http://wwwsearch.sourceforge.net/old/ClientForm/
• BeautifulSoup http://www.crummy.com/software/BeautifulSoup/

Mechanize cheat sheet1

Create a browser object

import mechanizebr = mechanize.Browser()br.set_all_readonly(False)    # allow everything to be written tobr.set_handle_robots(False)   # no robotsbr.set_handle_refresh(False)  # can sometimes hang without thisbr.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')]# [('User-agent', 'Firefox')]

Open a webpage and inspect its contents

response = br.open(url)print response.read()      # the text of the pageresponse1 = br.response()  # get the response againprint response1.read()     # can apply lxml.html.fromstring()

Using forms

#List the formsfor form in br.forms():    print "Form name:", form.name    print form#select formbr.select_form("form1")         # works when form has a namebr.form = list(br.forms())[0]  # use when form is unnamed#login form examplebr.select_form("login")         br['login:loginUsernameField'] = userbr['login:password'] = passwordbr.method = "POST"response = br.submit()

Using Controls

# Iterate through the controls in the form.for control in br.form.controls:    print control    print "type=%s, name=%s value=%s" % (control.type, control.name, br[control.name])# Controls can be found by namecontrol = br.form.find_control("controlname")# Having a select control tells you what values can be selectedif control.type == "select":  # means it's class ClientForm.SelectControl    for item in control.items:    print " name=%s values=%s" % (item.name, str([label.text  for label in item.get_labels()]))# Because Select type controls can have multiple selections, they must be set with a list, even if it is one element.print control.valueprint control  # selected value is starredcontrol.value = ["ItemName"]print controlbr[control.name] = ["ItemName"]  # equivalent and more normal# Text controls can be set as a stringif control.type == "text":  # means it's class ClientForm.TextControl    control.value = "stuff here"br["controlname"] = "stuff here"  # equivalent# Controls can be set to readonly and disabled (sometimes necessary for superfluous submit buttons).control.readonly = Falsecontrol.disabled = True# OR disable all of them like sofor control in br.form.controls:   if control.type == "submit":       control.disabled = True

Using Links

#Iterate the linksfor link in br.links():    print link.text, link.url# Follow link and click links is the same as submit and clickrequest = br.click_link(link)response = br.follow_link(link)print response.geturl()

Using Cookie jars

request = br.click()  # creates the request objectcj = mechanize.CookieJar()br2 = mechanize.Browser()br2.set_cookiejar(cj)br2.open(request)

More example

emulate a browser

import mechanizeimport cookielib# Browserbr = mechanize.Browser()# Cookie Jarcj = cookielib.LWPCookieJar()br.set_cookiejar(cj)# Browser optionsbr.set_handle_equiv(True)br.set_handle_gzip(True)br.set_handle_redirect(True)br.set_handle_referer(True)br.set_handle_robots(False)# Follows refresh 0 but not hangs on refresh > 0br.set_handle_refresh(mechanize._http.HTTPRefreshProcessor(), max_time=1)# Want debugging messages?#br.set_debug_http(True)#br.set_debug_redirects(True)#br.set_debug_responses(True)# User-Agent (this is cheating, ok?)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')]

access a password protected site

# If the protected site didn't receive the authentication data you would# end up with a 410 error in your facebr.add_password('http://safe-site.domain', 'username', 'password')br.open('http://safe-site.domain')

Downloading a file

# Downloadf = br.retrieve('http://www.google.com.br/intl/pt-BR_br/images/logo.gif')[0]print ffh = open(f)

Setting a proxy

# Proxy and user/passwordbr.set_proxies({"http": "joe:[e-mail]:3128"})# Proxybr.set_proxies({"http": "myproxy.example.com:3128"})# Proxy passwordbr.add_proxy_password("joe", "password")

quickly open an webpage

import urllib2print urllib2.urlopen('http://stockrt.github.com').read()# With password?import urllibopener = urllib.FancyURLopener()print opener.open('http://user:[e-mail]').read()