爬取豆瓣250本书籍

爬虫爬取豆瓣top250书籍并保存进.txt文件

使用的工具：pycharm

使用的包:requests,bs4，time

以下是本次爬取的代码

import requests
from bs4 import BeautifulSoup
import time

#发送请求
def request_dangdang(url,headers):
try:
response = requests.get (url,headers=headers)
if response.status_code==200:
return response.text
except requests.RequestException:
return None

#解析文件
def parse_result(soup):
contents=soup.find(class_=‘article’).find_all(name=‘table’,width=‘100%’)#.get_text().replace(’ ‘, ‘’).replace(’\n’,’ ').strip()

for item in contents:
    item_bookname=item.find(name='div',class_='pl2').find(name='a').get_text().replace('\n','').replace(' ','')
    item_author=item.find(name='p',class_='pl').get_text()
    item_pl=item.find(name='span&#