Python实时爬取CSDN博客阅读量增长图

基于requests 库与numpy 库 实现的实时博客增长监测系统。

原理

效果预览

异常的断崖式增长、平直的增长线。

实现代码

import requests
import re
import matplotlib.pyplot as plt
import numpy as np
import smtplib
from email.mime.text import MIMEText
import time

def getHTMLText(url):
    '''爬取目标网页'''
    headers = {}
    r = requests.get(url,headers=headers)
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    #print(r.text)
    return r.text


def paserPage(lst,html,count):
    '''提取阅读量数字'''
    catch = re.findall(r'访问量 \d*',html)
    #print('catch =',catch)
    num = eval(catch[0].split(' ')[1])
    if count==1:
        count = num
        num -= count
    else:
        num -= count
    lst.append(num)
    return count


def Plot(y):
    '''绘图'''
    x = np.arange(len(y))
    plt.plot(x,y)
    plt.xlabel('Time/s'),plt.ylabel('Amount')
    plt.pause(30)
    plt.close()


def Email(num):

    sender = '1650887506@qq.com'
    receiver = '1650887506@qq.com'
    subject = '博客订阅量'
    smtpserver = 'smtp.qq.com'
    username = '1650887506@qq.com'
    password = 'htveoihjdjzighda'
    msg = MIMEText('</pre><h1>博客阅读量突破%d</h1><pre>'%num,'html','utf-8')
    msg['Subject'] = subject

    smtp = smtplib.SMTP()
    smtp.connect('smtp.qq.com')
    smtp.login(username, password)
    smtp.sendmail(sender, receiver, msg.as_string())
    smtp.quit()


def main():
    
    lst = []
    url = 'https://blog.csdn.net/qq_43161186/article/details/104219604'
    count = 1   #用于存储初始博客访问量

    while True:

        html = getHTMLText(url)
        count = paserPage(lst,html,count)
        print(lst)
        Plot(lst)

        if (lst[-1]+count)%1000==0:
            Email(lst[-1]+count)

        time.sleep(30)


if __name__ == "__main__":

    main()