日常代码分享

from bs4 import BeautifulSoup
import requests
book_list = []
#用于存储所有的信息，书籍以字典的形式保存
def getInfo(url):
    #获取页面信息
    headers={"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/106.0.0.0 Safari/537.36"}
    res=requests.get(url,headers=headers)
    #提取待定信息，并封装成字典
    soup=BeautifulSoup(res.text,'html.parser')
    lis=soup.select('#csproduct > li')
    for li in lis:
        title=li.select('a > span')[0].text
        p=li.select('a > p')
        author=p[0].text
        isbn=p[1].text
        price=p[2].text
        print(title,author,isbn,price)
        dic={'title':title,'author':author,"isbn":isbn,'price':price}
        book_list.append(dic)
    #将字典存入book_list
#获取多页数据
def getBooks(page_num):
    #通过循环调用getInfo（） 获取多页数据
    #(1)拼接网址
    #（2）调用getInfo（）

    url1='http://www.tup.tsinghua.edu.cn/bookscenter/booklist.html?keyword=%e5%a4%a7%e6%95%b0%e6%8d%ae&keytm=8d333327918b976e8c&page='
    for i in range(1,page_num+1):
        url= url1+str(i)
        getInfo(url)
#将列表book_list中的数据存入文件
def saveData():
    res=''
    i = 1
    for book in book_list:
        res+=str(i)+"."+book['title']+"\n"+book['author']+'\n'+book['isbn']+'\n'+book['price']+'\n\n'
        i=i+1
    with open('book.txt','w',encoding='utf-8') as fp:
        fp.write(res)

url = "http://www.tup.tsinghua.edu.cn/booksCenter/booklist.html?keyword=%E5%A4%A7%E6%95%B0%E6%8D%AE&keytm=8D333327918B976E8C"
getInfo(url)
saveData()