当当网上筛选“python爬虫”系列书籍爬取9页数据

本文主要是介绍当当网上筛选“python爬虫”系列书籍爬取9页数据，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！

这周，我们老师让我们写个爬取电商数据的作业，题目如下
在这里插入图片描述
对此，我选择了在当当网上爬取“python爬虫”的数据，接下来我将附上我写的代码：

# -*- coding: utf-8 -*-
import requests
import csv
from bs4 import BeautifulSoup as bs
#获取网页信息
def request_dandan(url): try:#用户代理headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.163 Safari/537.36'}r = requests.get(url,headers=headers)if r.status_code == 200:return r.textexcept requests.RequestException:return None#存放列名
def write_item_to_file():csv_file = open('dangdang.csv', 'w', newline='', encoding="utf-8")writer = csv.writer(csv_file)writer.writerow(['书名','购买链接','纸质书价格','电子书价格','电子书链接','作者','出版时间','出版社'])print('列名已成功放入CSV中')
#解析网页并写入csv文件中
def parse_dangdang_write(html):  csv_file = open('dangdang.csv', 'a', newline='', encoding="utf-8")writer = csv.writer(csv_file)#解析网页soup = bs(html, 'html.parser')class_tag = ['line'+str(x) for x in range(1,61)]for class_tag in class_tag:li = soup.find('li',class_=class_tag)book_name = li.find('a',class_='pic').get('title') # 书名paperbook_price = li.find('span',class_='search_now_price').text  #纸质书价格try:ebook_price = li.find('a',class_='search_e_price').find('i').text  #电子书价格ebook_link = li.find('a',class_='search_e_price').get('href') #电子书链接except:ebook_price = ''ebook_link = ''#detail = li.find('p',class_='detail').text #书的详细介绍book_purchase_link = li.find('a',class_='pic').get('href') #每本书的详细购买链接#book_cover_link = li.find('a',class_='pic').find('img').get('src')#书的封面地址#comment_link = li.find('a',class_='search_comment_num').get('href') #评论地址author = li.find('p',class_='search_book_author').find('span').text # 书的作者public_time = li.find('p',class_='search_book_author').find('span').next_sibling.text[2:]#出版时间public = li.find('p',class_='search_book_author').find('span').next_sibling.next_sibling.text[3:]#出版社writer.writerow([book_name,book_purchase_link,paperbook_price,ebook_price,ebook_link,author,public_time,public])csv_file.close()if __name__=='__main__':write_item_to_file()for page in range (1,10):#爬取9页数据存入csv文件url = 'http://search.dangdang.com/?key=python%C5%C0%B3%E6&act=input&page_index=' + str(page)html = request_dandan(url) #获取网页信息parse_dangdang_write(html)#解析网页并写入csv文件中print('第{}页数据成功放入CSV中'.format(page))