基于Python实现文章信息统计的小工具

from spider import spider
from store import write_data


# 设置博客名，例如我的博客地址为：https://www.cnblogs.com/KoiC，此处则填入KoiC
blog_name = 'KoiC'



if __name__ == '__main__':
    post_info = spider(blog_name)
    # print(post_info)
    write_data(post_info, blog_name)
    print('执行完毕！')

import time
import requests
import re
from lxml import etree


def spider(blog_name):
    """
        爬取相关数据
    """
    
    # 设置UA和目标博客url
    headers = {
        "User-agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36 Edg/110.0.1587.41"
    }
    url = "https://www.cnblogs.com/" + blog_name + "/default.html?page=%d"
    
    # 测试访问
    req = requests.get(url, headers)
    print('测试访问状态：%d'%req.status_code)
    
    
    print('开始爬取数据...')
    
    post_info = [] # 全部博文信息
    
    #分页爬取数据
    for page_num in range(1, 999):
        
        # 指向目标url
        new_url = format(url%page_num)
        
        # 获取页面
        req = requests.get(url=new_url, headers=headers)
        # print(req.status_code)
        
        tree = etree.HTML(req.text)
        
        # 获取目标数据（各博文名称和阅读量）
        count_list = tree.xpath('//div[@class="forFlow"]/div/div[@class="postDesc"]/span[1]/text()')        
        title_list = tree.xpath('//div[@class="postTitle"]/a/span/text()')
        
        # 获取该页博文数量
        post_count = len(count_list)
        # 如果该页没有博文，跳出循环
        if post_count == 0:
            break
        
        # 解析目标数据
        
        for i in range(post_count):
            # 对数据进行处理
            post_title = title_list[i].strip() # 处理前后多余的空格、换行等
            post_view_count = re.findall('\d+', count_list[i]) # 正则表达式获取阅读量数据
            
            single_post_info = [post_title, post_view_count[0]] # 单篇博文数据
            
            post_info.append(single_post_info)
        
        time.sleep(0.8)
        
    return post_info  

import os
import time


def write_data(post_info, blog_name):
    """
        对数据进行持久化
    """
    
    print('开始写入数据...')
    
    # 获取时间
    now_time = time.localtime(time.time())
    select_date = time.strftime('%Y-%m-%d', now_time)
    select_time = time.strftime('%Y-%m-%d %H:%M:%S ', now_time)
    
    # 按日期创建文件路径
    file_path = './{:s}/{:s}'.format(str(now_time.tm_year), str(now_time.tm_mon))
    
    try: 
        os.makedirs(file_path) # 该方法创建路径时，若路径存在会报异常，使用 try catch 跳过异常
    except OSError:
        pass
    
    # 写入数据  
    try:
        fp = open('{:s}/{:s}.txt'.format(file_path, select_date), 'a+', encoding = 'utf-8')

        fp.write('阅读量\t\t 博文题目\n')

        view_count = 0 # 总阅读量
        for single_post_info in post_info:
            view_count += int(single_post_info[1])
            fp.write('{:<12s}{:s}\n'.format(single_post_info[1], single_post_info[0]))
        
        fp.write('------博客名:{:s} 博文数量:{:d} 总阅读量:{:d} 统计时间:{:s}\n\n'.format(blog_name, len(post_info), view_count, select_time))
        
        # 关闭资源
        fp.close()
    except FileNotFoundError:
        print('无法打开指定的文件')
    except LookupError:
        print('指定编码错误')
    except UnicodeDecodeError:
        print('读取文件时解码错误')