python爬虫豆瓣250排行书籍

爬虫代码

# 豆瓣图书Top250

import requests
from bs4 import BeautifulSoup

for page in range(10):
    url = 'https://book.douban.com/top250?start={}'.format(page*25)
    r = requests.get(url).text
    bsObj = BeautifulSoup(r,'html.parser')
    td_tags = bsObj.find_all('td',{'valign':'top','width':None})
    #print(td_tags)
    for td_tag in td_tags:
        try:
            name = td_tag.find('a').get_text().strip('\n').replace('\n','').replace(' ','')
            info = td_tag.find('p',{'class':'pl'}).get_text()
            rating_nums = td_tag('div',{'class':'star clearfix'})[0].get_text().replace('\n','').replace(' ','')
            jianjie = td_tag.find('span',{'class':'inq'}).get_text()
            dd = name + '\n' + info + '\n' + rating_nums + '\n' + jianjie + '\n'
            #print(dd)
            with open('E:/douban_book/douban_book.txt','a+',encoding='utf-8') as f:
                f.write(dd + '\n')
        except:
            continue

如果报错 no module named requests
可以 pip install requests安装

no module named beautifulsoup
可以pip install beautifulsoup4 安装

查看装了那些扩展，成功与否

执行文件结果