python爬取学校题库_Python爬虫实战-获取某网站题库

爬取*网站题库

import requests

import re

import time

import html

headers = {

'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36'

'(KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36' #加入请求头

}

f = open('/Volumes/SHARE/Python/GetAcmText/Text.txt', 'a+') #在路径下创建文件名为Text.txt的文件

def get_info(url):

global i

i = i + 1

print(i) #用于观察

res = requests.get(url, headers=headers)

if res.status_code == 200: #判断网站是否为可访问

title = re.findall('

(.*?)

', res.content.decode('utf-8'), re.S)[1].strip() #正则获取题目名

describes = re.findall('

(.*?)', res.content.decode('utf-8'), re.S)

describe = describes[0].strip()

tinput = describes[1].strip()

toutput = describes[2].strip()

einput = re.fi