Anon

print "Mi-Chan firing up..."import sys, os, re, timefrom urllib2 import HTTPErrorimport mechanizeassert mechanize.__version__ >= (0, 0, 6, "a")import syssite = "http://img.4chan.org/" #don't screw with thissettingsfile = os.path.dirname( (sys.argv[0]))+"\\settings.txt"if len(sys.argv)==2:    settingsfile = sys.argv[1]print "Running settings from "+settingsfiletry: execfile(settingsfile)except:    print "There's an error in the settings file!"    print "A detailed explanation of the error should follow"url = site+folder+"/"base_url = urlb = mechanize.Browser()b.set_handle_robots(False)if not os.path.exists(outpath):    os.mkdir(outpath)wastedBandwidth = 0images = 0imgNum = 0    #Defs go heredef print_info():    print "Crawling "+b.title()    print "Dumping to "+outpath    print "Specific target path: "+url    print "Rest time is "+str(restPeriod)+"s between images and "+str(threadRestPeriod)+"s between threads"    returndef writeLast(last):    try:        f = open("last.dat", "wb")        f.write(last)        f.close()    except:        returndef grab_images(target,outsubpath=""):    update = 0    resp = b.open(target)    haystack = resp.read()    test = re.compile("[0-9]*\.(?:jpg|bmp|gif)",re.IGNORECASE) #grab numbered images    ret = test.findall(haystack)    resp.close()    print "Fetching images from "+target    lastTime = time.time()        global imgNum    imgNum = 0    for i in ret:        if len(i)>4:            fetchPath = base_url+"src/"+i            filename = outpath+outsubpath+os.path.basename(fetchPath)            if not os.path.exists(filename):                                try:                    r = b.open(fetchPath)                except HTTPError, e:                    continue                f = open(filename, "wb")                print "["+str(imgNum+1)+"] %s -->" % filename,                                while 1:                    data = r.read(1024*500)                    if not data: break                    f.write(data)                f.close()                r.close()                writeLast(filename)                print os.stat(filename).st_size, "bytes"                global wastedBandwidth                wastedBandwidth = wastedBandwidth+(os.stat(filename).st_size)                global images                images = images+1                update = 1                global restPeriod                time.sleep(restPeriod) #sleep 1 second to avoid overflow?                                    imgNum = imgNum+1         return update #return whether any new images were grabbedtot_images = 0                lastTime = time.time()-updatePeriodtry:    r = b.open("http://www.heraldsofdeath.com/geargod/prefetch.php")    r.close()except: print ""while 1:    if time.time()-lastTime>updatePeriod:        time.sleep(1)                        images = 0        try: grab_images(url)        except: print "ERROR"        lastTime = time.time()        tot_images = tot_images + images        print "All done, "+str(images)+" new images were fetched"        print "Next update will be in "+str(updatePeriod)+" second(s)"        if wastedBandwidth>mbToWaste*1024*1024 and mbToWaste>0:            print "Exceeded bandwidth limit of "+str(mbToWaste)+"mb, shutting down"            break