def getHtml(url): #從URL中讀取html內(nèi)容
    page = urllib.urlopen(url)
    html = page.read()
    page.close()
    return html

def getDictionary(html): #匹配成語
    reg = "<a href=\"/cy(\d+)/(\d+).html\">(.*?)</a>"  
    dicList = re.compile(reg).findall(html)
    return dicList

def getItemSite():#手工把每個(gè)字母開頭的頁面數(shù)統(tǒng)計(jì)下來
    itemSite = {}#申明為空字典
    itemSite["A"] = 3
    itemSite["B"] = 21
    itemSite["C"] = 19
    itemSite["D"] = 18
    itemSite["E"] = 2
    itemSite["F"] = 14
    itemSite["G"] = 13
    itemSite["H"] = 15
    itemSite["J"] = 23
    itemSite["K"] = 6
    itemSite["L"] = 15
    itemSite["M"] = 12
    itemSite["N"] = 5
    itemSite["O"] = 1
    itemSite["P"] = 6
    itemSite["Q"] = 16
    itemSite["R"] = 8
    itemSite["S"] = 26
    itemSite["T"] = 12
    itemSite["W"] = 13
    itemSite["X"] = 16
    itemSite["Y"] = 35
    itemSite["A"] = 21
    return itemSite
   

if __name__== "__main__":
    dicFile = open("dic.txt","w+")#保存成語的文件
    domainsite = "http://chengyu.itlearner.com/list/"
    itemSite = getItemSite()
    for key,values in itemSite.items():
        for index in range(1,values+1):
            site = key +"_"+str(index)+".html"             
            dictionary = getDictionary(getHtml(domainsite+site))
            for dic in dictionary:
                dicFile.write(dic[2]+"@@CY\n")#標(biāo)記為成語，分詞時(shí)使用
        print key+'字母成語抓取完畢'       
    dicFile.close()   
    print '全部成語抓取完畢'

                <a href="/u/kkun/" title="kkun">kkun</a>

            </div>