# -*- coding: utf-8 -*-
"""
Created on Sun Nov  4 10:22:07 2018

@author: wangf
"""

from urllib.request import urlopen
import codecs
from bs4 import BeautifulSoup
i = 0
f = codecs.open("douban.txt", "w","utf-8")
while i< 50:
    a = "http://tieba.baidu.com/f?ie=utf-8&kw=%E4%B8%AD%E5%8C%97%E5%A4%A7%E5%AD%A6%E5%90%A7&fr=search"
    i+=50
    z = (i/50)
    print("第"+ str(z) + "頁")
    html = urlopen(a)
    bsObj = BeautifulSoup(html, "html.parser")
    for links in bsObj.findAll("a", {"class": "j_th_tit"}):
        print(links.attrs["href"] + "  " + links.text)
        f.write(links.text+"+++"+"\n")
f.close()