当当网（完善版）

国际标准书号：9787115428028

• 引入相关库

import requests
from lxml import html
import  pandas as pd

• 函数体

def spider(isbn):
    # 用国际标准书号的方式获取查询网站的链接
    url = "http://search.dangdang.com/?key={}&act=input".format(isbn)
    print(url)

    # 获取网页源代码
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.70 Safari/537.36'}

    html_data = requests.get(url, headers=headers).text

    # 使用xpath语法提取我们需要的内容
    selector = html.fromstring(html_data)
    ul_list = selector.xpath('//div[@id="search_nature_rg"]/ul/li')
    print('有{}家商家出售此书'.format(len(ul_list)))

    book_info_list = []
    for li in ul_list:

        title = li.xpath('a/@title')
        title = '没有这数据！' if len(title) == 0 else title[0]

        link = li.xpath('a/@href')
        link = '没有这数据！' if len(link) == 0 else link[0]

        price = li.xpath('p[@class="price"]/span[@class="search_now_price"]/text()')
        price = '没有这数据！' if len(price) == 0 else price[0]
        price = price.replace('¥', '')

        store = li.xpath('p[@class="search_shangjia"]/a/text()')
        store = '当当自营' if len(store) == 0 else store[0]

        # 往book_info_list列表中添加元素
        book_info_list.append(
            {"title": title, 
             "price": price, 
             "link": link, 
             "store": store}
        )
    print(book_info_list)

    for book in book_info_list:
        print('排序前：', book)

    print("#######################################")
    print("#######################################")
    print("#######################################")

    book_info_list.sort(key=lambda x: float(x['price']))
    print(book_info_list)

    for book in book_info_list:
        print('排序后：', book)

    df = pd.DataFrame(book_info_list)    # 转化成dataframe格式
    df.to_csv('当当图书信息.csv')    # 存储成csv，csv：逗号分隔符文件

• 引用函数

isbn = input("请输入你要查询的书号：")
spider(isbn)