Das deutsche Python-Forum

Code: Alles auswählen

#!/usr/bin/env python
# -*- coding: UTF-8 -*-

import cookielib
import urllib
import urllib2

cj = cookielib.CookieJar()
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))
resp = opener.open('http://stooq.pl') # save a cookie

theurl = 'http://stooq.pl/logred.htm' # an example url that sets a cookie, try different urls here and see the cookie collection you can make !
body={'in':'1','url':'/','login':'########','haslo':'########'}
txdata = urllib.urlencode(body) # if we were making a POST type request, we could encode a dictionary of values here - using urllib.urlencode
txheaders =  {'User-agent' : 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'} # fake a user agent, some websites (like google) don't like automated exploration


try:
    req = urllib2.Request(theurl, txdata, txheaders) # create a request object
    handle = opener.open(req) # and open it to return a handle on the url
    HTMLSource = handle.read()
    f = file('home.html', 'w')
    f.write(HTMLSource)
    f.close()
# http://stooq.pl/bazy/waluty.html
    theurl = 'http://stooq.pl/bazy/waluty.prn'
    body   = {'data':'20080922','granica':'0','waluty_4':'1','beztrans':'1','prn':'1'}
    txdata = urllib.urlencode(body)
    req    = urllib2.Request(theurl,txdata, txheaders) # create a request object
    handle = opener.open(req) # and open it to return a handle on the url
    HTMLSource = handle.read()
    f = file('pobur.html', 'w')
    f.write(HTMLSource)
    f.close()
    
except IOError, e:
    print 'We failed to open "%s".' % theurl
    if hasattr(e, 'code'):
        print 'We failed with error code - %s.' % e.code
    elif hasattr(e, 'reason'):
        print "The error object has the following 'reason' attribute :", e.reason
        print "This usually means the server doesn't exist, is down, or we don't have an internet connection."
        sys.exit()

else:
    print 'Here are the headers of the page :'
    print handle.info() # handle.read() returns the page, handle.geturl() returns the true url of the page fetched (in case urlopen has followed any redirects, which it sometimes does)
    print handle.read()
    print handle.geturl()

Code: Alles auswählen

#!/usr/bin/env python
# -*- coding: UTF-8 -*-

import mechanize
import ClientForm
from ClientForm import ParseResponse
# Call html document and store cookie
request  = mechanize.Request("http://www.stooq.pl/")
response = mechanize.urlopen(request)
# Read the form here form[2]
forms = ParseResponse(response, backwards_compat=False)
form  = forms[2]
# Set login and password
form.set_value("######", name="login")
form.set_value("######", name="haslo")
# Send form
request  = form.click()
response = mechanize.urlopen(request)

request  = mechanize.Request("http://stooq.pl/bazy/waluty.html")
response = mechanize.urlopen(request)
forms    = ParseResponse(response, backwards_compat=False)
form     = forms[3]

# Set values for file
...
# Hier wird die Datei erzeugt die ich speichern möchte
request  = form.click()
#response = mechanize.urlopen(request)
print request

response.close()

Code: Alles auswählen

<form method=post action=bazy/waluty.prn name=prn>

Code: Alles auswählen

request  = mechanize.Request("http://www.stooq.pl/bazy/waluty.prn")

Code: Alles auswählen

<closeable_response at 0xbc93f8 whose fp = <socket._fileobject object at 0  x7f6669a2f848>>

Code: Alles auswählen

import mechanize

br = mechanize.Browser()
br.open('http://www.stooq.pl/')
br.select_form(nr=2)
br.set_value("######", name="login")
br.set_value("######", name="haslo")
br.submit()
br.open('http://stooq.pl/bazy/waluty.html')
# Kram den du hier machen willst, siehe oben
result = br.submit().read()

Code: Alles auswählen

br.submit().read()

Code: Alles auswählen

<form method=post action=bazy/waluty.prn name=prn>

Code: Alles auswählen

<prn POST http://stooq.pl/bazy/waluty.prn application/x-www-form-urlencoded

Code: Alles auswählen

from __future__ import with_statement

from contextlib import closing
from itertools import izip
from urllib import urlopen

from lxml.html import soupparser


def main():
    url = 'http://www.ecb.europa.eu/stats/eurofxref/eurofxref-daily.xml'
    with closing(urlopen(url)) as f: 
        site = soupparser.parse(f)
    nodes = site.findall('.//cube[@rate]')
    curs = (elem.get('currency') for elem in nodes)
    rates = (elem.get('rate') for elem in nodes)
    for cur, rate in izip(curs, rates):
        print '%s : %s' % (cur, rate)


if __name__ == '__main__':
    main()

Code: Alles auswählen

[...]
result = br.submit().read()
try:
    f = open('waluty.prn', 'w')
    f.write(result)
finally:
    f.close()

Code: Alles auswählen

from time import strftime, localtime
filename = strftime('%Y-%m-%d', localtime()) + '.prn'

Code: Alles auswählen

'2008-09-26.prn'

Code: Alles auswählen

#!/usr/bin/env python
# -*- coding: UTF-8 -*-

import mechanize

br = mechanize.Browser()
br.open("http://www.stooq.pl/bazy/waluty.html")

br.select_form(nr=2)
br.set_value("#####", name="login")
br.set_value("#####", name="haslo")
result = br.submit().read()
print result
br.select_form(nr=3)
print br
result = br.submit().read()

try:
    f = open('waluty.prn', 'w')
    f.write(result)
finally:
    f.close()

Code: Alles auswählen

br['login'] = 'hier dein username'
br['haslo'] = 'hier das passwort'

Code: Alles auswählen

import mechanize

br = mechanize.Browser()
br.open("http://www.stooq.pl/bazy/waluty.html")

br.select_form(nr=2)
br['login'] = 'dein username'
br['haslo'] = 'dein passwort'
br.submit()

br.select_form(nr=3) # hier vielleicht auf 2 ändern?
# Felder ausfüllen, wenn nötig
result = br.submit().read()

try:
    f = open('waluty.prn', 'w')
    f.write(result)
finally:
    f.close()

Code: Alles auswählen

lxml.etree.fromstring()