urlquery.net parser

urlquery_parser.py

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

from lxml.etree import tostring
from lxml.html import fromstring
import urllib2


def req(url, http_proxy=None, timeout=30, retry=2):
    result = None
    if not timeout or timeout is None:
        timeout = 30
    if retry is None or retry < 0:
        retry = 2
    if http_proxy:
        # http://username:password@someproxyserver.com:1337
        http_proxy_full_auth_string = "http://%s:%s@%s:%s" % (http_proxy["user"],
                                                              http_proxy["passwd"],
                                                              http_proxy["server"],
                                                              http_proxy["port"])
        proxy_handler = urllib2.ProxyHandler({"http": http_proxy_full_auth_string,
                                              "https": http_proxy_full_auth_string})
        opener = urllib2.build_opener(proxy_handler)
        #urllib2.install_opener(opener)
    else:
        proxy_handler = urllib2.ProxyHandler({})
        opener = urllib2.build_opener(proxy_handler)

    postDatas = {"User-Agent": "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)",
                 "Cache-Control": "no-cache",
                 "Pragma": "no-cache"}

    request = urllib2.Request(url, None, postDatas)
    loop = 0
    while not result and loop <= retry:
        try:
            # Permet de passer par le proxy sans installer d'opener
            connection = opener.open(request, timeout=timeout)
        except Exception as err:
            # Si il y a une erreur de connexion (timeout etc.)
            print "Error with %s: %s" % (url, err)
        else:
            retcode = connection.getcode()
            # if retcode != 200:
            #     result.log("Mauvais code retourne par %s: %d" % (url, retcode), logging.ERROR)
            # else:
            # try:
            source = connection.read()
            # except Exception as err:
            #     # Si il y a une erreur de connexion (timeout etc.)
            #     result.add_error(err, "%s ne repond pas" % url)
            # else:
            connection.close()
            # if not source:
            #     result.log("La page retournee par %s est vide" % url, logging.ERROR)
            # else:
            if source:
                # result.add_data(source, display=False)
                result = source
                break
        loop += 1
    return result


if __name__ == '__main__':
    url = "http://urlquery.net/"
    sourceUrlQuery = req(url)
    rootUrlQuery = fromstring(sourceUrlQuery)
    resUrlQuery = []

    for td in rootUrlQuery.xpath('//tr[contains(@class, "odd_highlight") or contains(@class, "even_highlight")]'):
        date = td.xpath('td/nobr/center/text()')[0]
        #print date
        
        level = td.xpath('td[contains(@align, "center")]/b/text()')[0]
        #print level
        
        targeturl = td.xpath('td/a/@title')[0]
        #print targeturl
        
        country = td.xpath('td/img/@title')[0]
        #print country
            
        ipaddr = tostring(td.xpath('td/img')[0]).split('>')[1]
        #print ipaddr

        resUrlQuery.append([date, level, targeturl, country, ipaddr])
        #print "#"*50

    print '\n\n'.join("date: %s\nlevel: %s\ntargeturl: %s\ncountry: %s\nipaddr: %s" % (date, level, targeturl, country, ipaddr) for date, level, targeturl, country, ipaddr in resUrlQuery)
    print "\n", "#"*50, "\n%d result%s" % (len(resUrlQuery), 's' if len(resUrlQuery) > 1 else '')