把cc98的中包含的网址抓取下来，保存在tempurl2.txt中

grep98list.py

import urllib2
from BeautifulSoup import BeautifulSoup

#判断是不是table，即是不是帖子目录了
def isTable(url):
    page = urllib2.urlopen(url)
    soup = BeautifulSoup(page)
    tdTags = soup('td', align='left', width='*')
    if len(tdTags) <= 1:
        return True
    else:
        return False 

#path 保存的是当前走过的路径。为深度遍历
def helper(url, path, fileHandle):
    if not isTable(url):
        finalPage = urllib2.urlopen(url)
        finalSoup = BeautifulSoup(finalPage)
        tdTags = finalSoup('td', align='left', width='*')
        tdTags = tdTags[1:]
        for tdTag in tdTags:
            print path +" " + tdTag.contents[1].string
            fileHandle.write(path.encode('utf-8')+' http://www.cc98.org/'+tdTag.contents[1]['href'].encode('utf-8') + '\n')
            #fileHandle.write(path.encode('utf-8'))
        return
    else:
        page = urllib2.urlopen(url)
        soup = BeautifulSoup(page)
        trTags = soup('tr', valign='middle')
        trTags = trTags[1:]
        for trTag in trTags:
            url2 = url[:url.find('?')]
            url2 += trTag.contents[2].contents[0]['href']
            name = trTag.contents[2].contents[0].string
            helper(url2, path + ' '+ name, fileHandle)

if __name__ =='__main__':
    url = 'http://www.cc98.org/list_best.asp?boardid=147'
    fileHandle = open('tempurl2.txt', 'w')
    helper(url, '', fileHandle)
    fileHandle.close()