Spider

An attempt to write a spider which 1) prints all URL's for a desired web-page. 2) excludes/includes certain urls in a filter-script and 3) Picks one of the filterd urls and 4) eventually sends it back to 1) in a continous loop

1)

import sys, httplib2, os, time, urllib, lxml.html, re
from urlparse import urlparse, urljoin, urldefrag
def visit (url, depth=1):
    global visited
    #print url
    print url
    # remember we visited
    visited[url] = True
    if depth >= MAX_DEPTH: return
    connection = urllib.urlopen(url)
   
    dom =  lxml.html.fromstring(connection.read())
   
    for xpath in ['//a/@href', '//img/@src']:
        # select the url in href for all a tags(links)
        for link in dom.xpath(xpath): 
            #print link
            link = link.strip()
            if link.lower().startswith("javascript"):
                continue
            # normalize url
            link = urljoin(url,link)
            link = urldefrag(link)[0]
            # strip for /
            link = link.rstrip('/')
            # if (link not in visited) and link.startswith(PREFIX) and depth<MAX_DEPTH:
            if (link not in visited) and depth<MAX_DEPTH:
               visit(link, depth+1)

MAX_DEPTH = 2

visited = {}

starturl = sys.argv[1]

try:
   PREFIX = sys.argv[2]
except IndexError:
   PREFIX = starturl 
visit(starturl)

2)

3)

4)