python定时爬取_python使用 Timer 间隔一定时间爬取(BeautifulSoup)csdn的访问量

#!/usr/bin/env python

# -*- coding: utf-8 -*-

# @Date : 2018-03-25 22:11:35

# @Author : awakeljw

# @Link : http://blog.csdn.net/awakeljw/

# @Version : $Id$

import os

import re

import time

import urllib.request

from bs4 import BeautifulSoup

from threading import Timer

# filename = r'F:\wargame\title.txt'

# if not os.path.exists(filename):

# os.system(r"touch %s" % filename)

def get_n_title():

url = 'https://blog.csdn.net/awakeljw'

user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36'

HEADERS = {"User-Agent":user_agent}

req = urllib.request.Request(url, headers=HEADERS) #伪装浏览器访问

page = urllib.request.urlopen(req).read()