【Python爬虫】查自己博客每月发帖量的小程序

【前提：安装beautifulsoup4和requests】

pip install beautifulsoup4

pip install requests

【代码】

#encoding=utf-8

from bs4 import BeautifulSoup
import requests
import re

user_agent='Mozilla/4.0 (compatible;MEIE 5.5;windows NT)'
headers={'User-Agent':user_agent}

dic={}; #定义个字典对象，存月份和个数
for i in range(1,139):
    html=requests.get('http://www.cnblogs.com/heyang78/p/?page='+str(i),headers=headers)
    soup= BeautifulSoup(html.text,'html.parser');

    for descDiv in soup.find_all(class_="postDesc2"):
         rawInfo=descDiv.text #得到class="postDesc2"的div的内容
         yearMonth=re.search(r'\d{4}-\d{2}',rawInfo).group() #用正则表达式去匹配年月并取其值

         # 将年月存入字典，如果存在就在原基础上加一         
         if yearMonth in dic:
               dic[yearMonth]=dic[yearMonth]+1
         else:
               dic[yearMonth]=1


list=sorted(dic.items(),key=lambda x:x[0]) #将排序后的字典转化为数组

#存入文件
with open(r'output.txt','w') as outfile:
    for item in list:
        print(item)
        outfile.write(str(item)+"\n")

【输出示例】

('2016-02', 8)
('2016-03', 14)
('2016-05', 1)
('2016-06', 1)
('2016-07', 17)
('2016-08', 12)
('2016-10', 1)
('2017-01', 19)
('2017-02', 3)
('2017-03', 2)
('2017-04', 1)
('2017-05', 1)
('2017-06', 20)
('2017-07', 10)
('2017-08', 16)
('2017-09', 78)
('2017-10', 5)
('2017-11', 32)
('2017-12', 21)
('2018-01', 7)
('2018-03', 19)
('2018-04', 45)
('2018-05', 43)
('2018-06', 2)
('2018-07', 2)
('2019-03', 37)
('2019-04', 1)
('2019-05', 2)
('2019-07', 1)
('2019-08', 17)
('2019-09', 41)
('2019-10', 63)
('2019-11', 73)
('2019-12', 64)
('2020-01', 80)
('2020-02', 42)
('2020-03', 61)
('2020-04', 43)
('2020-05', 68)
('2020-06', 26)
('2020-09', 1)
('2021-08', 39)
('2021-09', 73)
('2021-10', 61)
('2021-11', 42)
('2021-12', 46)
('2022-01', 30)
('2022-02', 63)
('2022-03', 26)

END