【python】当当网某分类页面爬虫练习

君哥 阅读:2321 2023-12-22 17:17:12 评论:0

import requests
from lxml import etree
import csv
import time
import random
import os
os.makedirs('dangdang', exist_ok=True)
writer =csv.writer(open('dangdang/dangdang.csv', 'w', newline='', encoding='utf-8-sig'))
writer.writerow(['图书名称', '上架时间', '出版社', '价格'])

allUrl = ['https://category.dangdang.com/pg{}-cp01.54.92.02.00.00.html'.format(str(i)) for i in range(1, 10)]

count=0

for url in allUrl:
    count = count + 1
    print(url)
    response = requests.get(url)
    response.encoding = 'GB2312'
    html = etree.html(response.text)
    print(html)
    allli = html.xpath('//*[@id="component_59"]/li')
    print(allli)
    print('第{}页开始采集'.format(count))
    for li in allli:
        print(li)
        book_name = li.xpath('./a/@title')[0]
        book_time = li.xpath('./p[5]/span[2]/text()')
        book_pub = li.xpath('./p[5]/span[3]/a/text()')  
        book_price = li.xpath('./p[3]/span[1]/text()')

        if book_time:
            book_time = book_time[0].replace('/','')
        else:
            book_time = '无'

        if book_pub:
            book_pub = book_pub[0] 
        else:
            book_pub = '暂无'

        if book_price:
            book_price = book_price[0].strip('¥')
        else:
            book_price = 0


        rowInfo = (
                   book_name,   
                   book_time,  
                   book_pub,  
                   book_price
                    )
        print(rowInfo)
        writer.writerow(rowInfo)
    print('第{}页采集完成!'.format(count)) 
    time.sleep(random.randint(3, 10))

本文链接:http://www.yanjun202.com/post/89.html 

分享到:
可以去百度分享获取分享代码输入这里。
发表评论
搜索
排行榜
关注我们

扫一扫关注我们,了解最新精彩内容