Created
October 5, 2010 15:13
-
-
Save jpadilla/611708 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import mechanize | |
import cookielib | |
from BeautifulSoup import BeautifulSoup | |
# Browser | |
br = mechanize.Browser() | |
# Cookie Jar | |
cj = cookielib.LWPCookieJar() | |
br.set_cookiejar(cj) | |
# Browser options | |
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) | |
# Follows refresh 0 but not hangs on refresh > 0 | |
br.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 (iPhone; U; CPU like Mac OS X; en) AppleWebKit/420+ (KHTML, like Gecko) Version/3.0 Mobile/1A543a Safari/419.3')] | |
# Open some site, let's pick a random one, the first that pops in mind: | |
r = br.open('https://m.bancopopular.com/cibp-web/actions/login') | |
# Show the html title | |
print br.title() | |
# Show the available forms | |
for f in br.forms(): | |
print f |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment