Das deutsche Python-Forum

Code: Alles auswählen

#!/usr/bin/env python
# -*- coding: iso-8859-15 -*-

import urllib2
import threading
import time


lock = threading.Lock()


def download(url, retvals):
    
    try:
        html = urllib2.urlopen(url).read()
    except urllib2.URLError, exception:
        html = "ERROR: %s" % str(exception)
    lock.acquire()
    retvals.append((url, html))
    lock.release()


def main():
    urls = (
        "http://gerold.bcom.at/",
        "http://halvar.at/",
        "http://lugt.at/",
        "http://microsoft.de/",
        "http://www.python-forum.de/",
        "http://python.org/",
        "http://wallerforum.com/",
        #"http://log-in.fachdid.fu-berlin.de/Archiv/2001/2/Thema/", # braucht zu lange
    )
    retvals = []
    threads = []
    for url in urls:
        threads.append(
            threading.Thread(
                target = download, kwargs = dict(url = url, retvals = retvals)
            )
        )
        threads[-1].start()
        time.sleep(0.2)
    
    # Warten bis alle fertig sind
    for thread in threads:
        thread.join()
        
    for url, html in retvals:
        print url
        if html.startswith("ERROR"):
            print "Achtung Fehler!"
        print html[:100]
        print


if __name__ == "__main__":
    main()

Code: Alles auswählen

#!/usr/bin/env python 
# -*- coding: iso-8859-15 -*- 

import os
import urllib
import urllib2
import threading
import time
print 'Content-Type: text/html\n\n'

lock = threading.Lock() 


def download(url, retvals): 
    
    try: 
        html = urllib2.urlopen(url).read() 
    except urllib2.URLError, exception: 
        html = "ERROR: %s" % str(exception) 
    lock.acquire() 
    retvals.append((url, html)) 
    lock.release() 


def main(): 
    urls = ( 
        "http://www.google.com/", 
        "http://www.gmail.com/", 
        #"http://log-in.fachdid.fu-berlin.de/Archiv/2001/2/Thema/", # braucht zu lange 
    ) 
    retvals = [] 
    threads = [] 
    for url in urls: 
        threads.append( 
            threading.Thread( 
                target = download, kwargs = dict(url = url, retvals = retvals) 
            ) 
        ) 
        threads[-1].start() 
        time.sleep(0.2) 
    
    # Warten bis alle fertig sind 
    for thread in threads: 
        thread.join() 
        
    for url, html in retvals: 
        print url 
        if html.startswith("ERROR"): 
            print "Achtung Fehler!" 
        print html[:100] 
        print 

main()

Code: Alles auswählen

import cgi
import cgitb; cgitb.enable()

Code: Alles auswählen

#!/usr/bin/python
#print 'Content-Type: text/html\n\n'
import os
import urllib
import urllib2
import threading
import time

print 'Content-Type: text/html\n\n'

#EAN ist sowas wie die ISBN nummer von einem buch
def geturltest(ean):
	url = 'http://www.foobar.ch/search.aspx?some=params'
	page = urllib.urlopen(url)
	pagedata = page.read()
	return pagedata

def strpos(string,search):
	pos = string.find(search)
	return pos

def test(string,pos):
	return string[pos+5:pos+12]


page = geturltest('9783280071465')
position = strpos(page,"Lieferzeit")
print test(page,position)