#導(dǎo)入需要的模塊
import time
import requests
from lxml import etree

#進(jìn)行UA偽裝
headers={
    "User-agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36"
}
#創(chuàng)建文件，存儲(chǔ)爬到的數(shù)據(jù)，做持久化,以追加的方式打開(kāi)，可讀可寫(xiě)
fp=open('./counter.txt','a+',encoding = 'utf-8')
#記錄當(dāng)前查詢(xún)時(shí)間
select_time=time.strftime('%Y.%m.%d %H:%M:%S ',time.localtime(time.time()))
fp.write('查詢(xún)的時(shí)間為：'+select_time+'\n')
def spider():
    #總閱讀量
    counts=0
    #分頁(yè)爬取數(shù)據(jù)加和
    for page_num in range(1,20):
        #設(shè)置url
        url="https://www.cnblogs.com/andrew3/default.html?page=%d"
        new_url=format(url%page_num)
        #獲取頁(yè)面數(shù)據(jù)
        page_text=requests.get(url=new_url,headers=headers).text
        tree=etree.HTML(page_text)
        #解析數(shù)據(jù)，得到每頁(yè)每篇博文的閱讀量
        count_list=tree.xpath('//div[@class="forFlow"]/div/div[@class="postDesc"]/span[1]/text()')
        print(count_list)
        #每一頁(yè)的閱讀量
        sum=0
        #計(jì)算每頁(yè)的閱讀量
        for i in range(len(count_list)):
            sum+=int(count_list[i][3:len(count_list[i])-1])
        #計(jì)算總閱讀量
        counts+=sum
        #打印每頁(yè)每篇博文的閱讀量
        print(sum,counts)
    #總閱讀量持久化
    fp.write("總閱讀量為：%s" % counts + '\n')
#關(guān)閉文件，釋放資源
def close_file():
    fp.close()
def main():
    spider()
    close_file()
if __name__ == '__main__':
    main()