作业1.1.2

基于JSON的web信息提取

import requests

from bs4 import BeautifulSoup

url="http://bang.dangdang.com/books/fivestars/1-1"

header={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36'}

res=requests.get(url,headers=header)

res.encoding=res.apparent_encoding

#print(res.text)

soup=BeautifulSoup(res.text,"lxml")

book_list=soup.select("div.bang_list_box > ul > li")

print(len(book_list))

for book in book_list:

name=book.select("div.name > a")[0].text

cishu=book.select("div.biaosheng > span")[0].text

zuozhe=book.select("div.publisher_info > a")[0].text

chubanriqi= book.select("div.publisher_info > span")[0].text

chubanshe = book.select("div.publisher_info > a")[0].text

jiage=book.select("div.price > p > span ")[0].text

print("书名：",name,"评分次数：",cishu,"作者名：",zuozhe,"出版日期：",chubanriqi,"出版社：",chubanshe,"价格：",jiage)