#-*-coding:utf-8-*-
#参考文档
#https://www.crummy.com/software/BeautifulSoup/bs4/doc/index.zh.html#find-all
import requests
import re
from bs4 import BeautifulSoup
html = requests.get('https://m.cnitpm.com/exam/ExamST1_1031655.htm/')
soup = BeautifulSoup(html.text,'lxml')
ulTag=soup.find_all('ul','tit')
#计数器每次调用加1
def create_counter():
 def increase(): #定义一个还有自然数算法的生成器,企图使用next来完成不断调用的递增
 n = 0
 while True:
 n = n+1
 yield n
 it = increase() #一定要将生成器转给一个(生成器)对象,才可以完成,笔者第一次做,这里一直出问题,
 def counter(): #再定义一内函数
 return next(it) #调用生成器的值,每次调用均自增
 return counter
counter_ = create_counter() #用变量来指向(闭包函数返回的函数)
#保存文件
def save(filename, contents):
 #print(counter_())
 fh = open(filename, 'a+', encoding='utf-8')
 #print(str(counter_())+contents.strip()+'\n')
 fh.write(str(counter_())+'、'+contents.strip()+'\n')
 fh.close()


###################################网络爬取页面分析
for item in ulTag:
 a_temp=item.find_all('a')
 #print(a_temp)
 for aitem in a_temp:
 #print (aitem.get('href'))
 html2 = requests.get(aitem.get('href'))
 #解决乱码问题
 html2.encoding = 'utf-8'
 soup2 = BeautifulSoup(html2.text, 'lxml')
 divTag = soup2.find_all('div', 'tm-box')
 for divitem in divTag:
 #print(divitem.get_text())
 #保存到文档
 save('G:/aa/qa.txt',divitem.get_text())
 #print(divTag.replace('[<div class="tm-box">', ''))