python爬虫原理讲解

原理很简单，利用python下载我更新的txt题库，然后转化为字典，最后对应答案输出。

# -*- coding: utf-8 -*-
"""
Created on Tue Jan  9 12:05:34 2018

@author: admin
"""
info = []
from bs4 import BeautifulSoup
import requests
import os
print('========Welcome to use QduSafeExamHelper========')
print('|                                              |')
print('|             Made with python3.6              |')
print('|                                              |')
print('=========== Verison: 1.0.6 by ARCHer ===========\n')
print('请将考试页面保存（Ctrl+s）在当前程序同一目录下并按照下方面的说明操作！')
print('1.请确认保存的网页名为.html ')
print('2.html文件与本程序在同一目录')
print('3.确认前两项无误后按回车确认')
input()
result = {}
update_url = 'https://kaoshidaan.oss-cn-qingdao.aliyuncs.com/result.txt'
r = requests.get(update_url)
with open("result.txt",'wb') as f:
    f.write(r.content)
file = open( 'result.txt' , 'r' )
lines = file.readlines()
file.close()
for line in lines:
    result_data = line.split('----', 1 )
    result[result_data[0]] = result_data[1].strip()
#print(result)
with open( '.html',encoding = 'utf-8') as wb_data:
    soup = BeautifulSoup( wb_data , 'lxml' )
    numbers = soup.select('dd > a')
    questions = soup.select( 'dd > a' )
for question,number in zip( questions, numbers ):
    data = {
            'question':question.get('href'),
            'number':number.get_text(),
            'answer':result.get(question.get('href'))
            }
    info.append(data)
os.remove('result.txt')
for i in info:
    print('题目序号：',i['number'] ,'题目答案：',i['answer'] )
input('Finished')