当当网爬虫保存到本地

以下是一个将当当网的书名、链接、价格和评论数爬取并保存到本地的爬虫示例：

import requests
from lxml import etree
import csv

# 定义爬取函数
def crawl_dangdang():
    url = "http://search.dangdang.com/?key=python&act=input&page_index=1"
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
    }
    response = requests.get(url, headers=headers)
    html = response.text
    
    # 使用lxml解析网页源码
    tree = etree.HTML(html)
    
    # 获取书名、链接、价格和评论数
    book_names = tree.xpath('//ul[@class="bigimg"]/li//a[@class="pic"]/@title')
    book_links = tree.xpath('//ul[@class="bigimg"]/li//a[@class="pic"]/@href')
    book_prices = tree.xpath('//ul[@class="bigimg"]/li//p[@class="price"]/span[@class="search_now_price"]/text()')
    book_comments = tree.xpath('//ul[@class="bigimg"]/li//p[@class="search_star_line"]/a/text()')
    
    # 将数据写入CSV文件
    with open('books.csv', 'w', encoding='utf-8', newline='') as csvfile:
        writer = csv.writer(csvfile)
        writer.writerow(['书名', '链接', '价格', '评论数'])
        for i in range(len(book_names)):
            writer.writerow([book_names[i], book_links[i], book_prices[i], book_comments[i]])

# 调用爬取函数
crawl_dangdang()

这个爬虫会将爬取到的书名、链接、价格和评论数保存到名为`books.csv`的CSV文件中。