= Python Wiki =

You said you wanted to mirror the Python wiki on the CD, here is a little script to suck the pages from the wiki to a folder:
{{{
#!python
import socket, os, sys, urllib2
socket.setdefaulttimeout(15)
from time import sleep

def suckwiki(pagelist, #url to plain text list of wiki pages
             rawpage, #url to raw wiki text of a page
             foldername="wikifiles", #name of folder to save files to
             sleeptime=1 #seconds to sleep between page accesses
             ):
    foldername = os.path.join(os.path.abspath(os.path.dirname(sys.argv[0])), foldername)
    if not os.path.exists(foldername): os.mkdir(foldername)
    opener = urllib2.build_opener()
    listrequest = urllib2.Request(pagelist)
    listresponse = opener.open(listrequest)
    sleep(sleeptime)
    for pagename in listresponse:
        pagename = pagename.strip()
        pagename = pagename.replace('_','_5f')
        pagename = pagename.replace(' ','_20')
        print pagename
        fullpagename = rawpage % {'pagename':pagename}
        pagerequest = urllib2.Request(fullpagename)
        page = opener.open(pagerequest)
        f = open(os.path.join(foldername,pagename),"wb")
        f.write(page.read())
        f.close()
        page.close()
        sleep(sleeptime)

if __name__ == '__main__':
    pagelist = "http://www.python.org/cgi-bin/moinmoin/TitleIndex?action=titleindex"
    rawpage = r"http://www.python.org/cgi-bin/moinmoin/%(pagename)s?action=raw"
    foldername = "pythonwiki" #name of folder to save pages to
    suckwiki(pagelist,rawpage,foldername)
}}}


Thanks! -- ThomasWaldmann <<DateTime(2004-06-22T05:23:14Z)>>