爬虫--豆瓣读书TOP250书籍

• 练手系列，直接上代码

import requests
import time
from lxml import etree

with open('C:\\Users\\HY\\Desktop\\book_douban.csv','w',encoding = 'utf-8') as f:
    for a in range(10):
        url = 'https://book.douban.com/top250?start={}'.format(a*25)
        data = requests.get(url).text
        s = etree.HTML(data)
        
        book = s.xpath('//*[@id="content"]/div/div[1]/div/table')
        time.sleep(3)
        for div in book:
            title = div.xpath('./tr/td[2]/div[1]/a/@title')[0]
            href = div.xpath('./tr/td[2]/div[1]/a/@href')[0]
            score = div.xpath('./tr/td[2]/div[2]/span[2]/text()')[0]
            num = div.xpath('./tr/td[2]/div[2]/span[3]/text()')[0].strip("(").strip().strip(")")
            scribe = div.xpath('./tr/td[2]/p[2]/span/text()')
                    
            if len(scribe) > 0:
                f.write('{},{},{},{},{}\n'.format(title,href,score,num,scribe[0]))
                
            else:
                f.write('{},{},{},{}\n'.format(title,href,score,num))

• 输出情况如图（数据过多，截取部分）

  
  
  TOP250图书信息.png