# -*- coding:utf-8 -*-
from urllib import request as urllib2
from urllib import parse
import random
def loadPage(url, page):
  '''
  根據(jù)url獲取服務器響應文件
  url:需要爬取的url
  '''
  print('---------正在下載頁面%d-------' % page)
  ua_list = [
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv2.0.1) Gecko/20100101 Firefox/4.0.1",
    "Mozilla/5.0 (Windows NT 6.1; rv2.0.1) Gecko/20100101 Firefox/4.0.1",
    "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",
    "Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11"
  ]
  header = random.choice(ua_list)
  request = urllib2.Request(url)
  request.add_header('User-Agent', header)
  response = urllib2.urlopen(request)
  html = response.read()
  return html
def write(html, page):
  '''
  將html文件寫入本地
  :param html: 服務器響應文件內容
  :return:
  '''
  data = html
  file_name = 'tieba{}.txt'.format(page)
  print('---------正在保存文件%s-------'%file_name)
  # 運用with open as語句使代碼更加簡潔 避免寫異常處理和文件關閉語句
  with open(file_name,'w',encoding='utf-8') as file:
    file.write(data.decode())
  print('---------success!---------')
def tiebaSpider(url, kw, begin, end):
  '''
  爬取貼吧信息
  '''
  words = {
    'kw':kw
  }
  kw = parse.urlencode(words)
  url = url % (kw)
  for page in range(begin, end + 1):
    pn = ((page-1)*50)
    ful_url = url + str(pn)
    html = loadPage(url, page)
    write(html, page)
if __name__ == '__main__':
  kw = input('請輸入爬取貼吧名:')
  beginPage = int(input('請輸入起始頁:'))
  endPage = int(input('請輸入結束頁:'))
  url = r'http://tieba.baidu.com/f?%s&pn='
  tiebaSpider(url, kw, beginPage, endPage)