url可以在网页迅速打开 但urllib2.urlopen(url，timeout=xx) 却超时了

[Ray_20]

#! /usr/bin/python
#coding=utf-8

import urllib2
import urllib
from sys import argv  # get data from command line
import HTMLParser # parse the data which spider get
import re
import redis
import string
import datetime


class SpiderRegular(object):

    def __init__(self, pattern , string):
        self.pattern = pattern
        self.string = string

    def getnexturl(self):

        sub = re.search(self.pattern, self.string)
        if not sub:
            return None
        return re.search(r'".+\.html"', sub.group()).group()

    def inredis(self):

        try:
            redis_conn = redis.Redis(host='127.0.0.1', port=6379)
            redis_conn.set('nexturl', self.getnexturl())
        except redis.RedisError, e:
            raise(e)

    def outredis(self):

        self.inredis()

        try:
            redis_conn = redis.Redis(host='127.0.0.1', port=6379)
            nexurl = redis_conn.get('nexturl')
        except redis.RedisError, e:
            raise(e)
        else:
            return nexurl




class Spider(object):

    def __init__(self, baseurl):

        self.nexturl = baseurl


    def getindexpage(self):
        self.html = ''
        try:
            htmlobj = urllib2.urlopen(self.nexturl, timeout=350)
            self.html = htmlobj.read()
        except Exception, e:
            raise e
        else:
            htmlobj.close()
            return self.html


    def geturls(self):

        self.indexpage = self.getindexpage()
        urls = {}

        if self.indexpage:
            nextpath = SpiderRegular(r'<LINK HREF=".+" REL=next>', self.indexpage).getnexturl()
            if nextpath:
                self.nexturl = self.nexturl[:self.nexturl.rfind('/')+1] + nextpath.strip('"')
                print 'get url: %s' % self.nexturl
                urls[nextpath.strip('"')] = self.nexturl
                print '[%s]: set url {%s} to dict' % (datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S'), self.nexturl)
                self.geturls()
            else:
                return urls
        return urls

    def action(self, path):

        urls = self.geturls()
        print '[%s]: get urls success . . .' % datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')
        for url in urls:
            urllib.urlretrieve(url, path + urls[url])

        print '[%s]: Download success' % datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')


def main():
    spider = Spider('http://www.tldp.org/HOWTO/Bash-Prog-Intro-HOWTO.html')
    spider.action('/home/yfsuse/pyproject/pyeah/pyspider/howtobash/')


if __name__ =='__main__':
    main()

[lsjfdjoijvtghu]

在交互界面urlopen试试快不快
还是不快的话，python的urlopen有时的确匪夷所思，比如同样内容python发出去就是没响应