# coding:utf-8import urllibdomain = 'http://www.liaoxuefeng.com'           #廖雪峰的域名path = r'C:/Users/cyhhao2013/Desktop/temp//'    #html要保存的路徑# 一個(gè)html的頭文件input = open(r'C:/Users/cyhhao2013/Desktop/0.html', 'r')head = input.read()# 打開python教程主界面f = urllib.urlopen("http://www.liaoxuefeng.com/wiki/001374738125095c955c1e6d8bb493182103fac9270762a000")home = f.read()f.close()# 替換所有空格回車（這樣容易好獲取url）geturl = home.replace("/n", "")geturl = geturl.replace(" ", "")# 得到包含url的字符串list = geturl.split(r'em;"><ahref="')[1:]# 強(qiáng)迫癥犯了，一定要把第一個(gè)頁面也加進(jìn)去才完美list.insert(0, '/wiki/001374738125095c955c1e6d8bb493182103fac9270762a000">')# 開始遍歷url Listfor li in list:    url = li.split(r'">')[0]    url = domain + url              #拼湊url    PRint url    f = urllib.urlopen(url)    html = f.read()    # 獲得title為了寫文件名    title = html.split("<title>")[1]    title = title.split(" - 廖雪峰的官方網(wǎng)站</title>")[0]    # 要轉(zhuǎn)一下碼，不然加到路徑里就悲劇了    title = title.decode('utf-8').replace("/", " ")    # 截取正文    html = html.split(r'<!-- block main -->')[1]    html = html.split(r'<h4>您的支持是作者寫作最大的動(dòng)力！</h4>')[0]    html = html.replace(r'src="', 'src="' + domain)    # 加上頭和尾組成完整的html    html = head + html+"</body></html>"    # 輸出文件    output = open(path + "%d" % list.index(li) + title + '.html', 'w')    output.write(html)    output.close()