python3爬虫豆瓣top250图书（并保存到mysql数据库）

参考上篇文章

附上代码：

import requests
from bs4 import BeautifulSoup
import mysql.connector


def get_pages_link():
    # 插入到数据库
    conn = mysql.connector.connect(user='root', password='root', database='test')
    cursor = conn.cursor()

    header = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.92 Safari/537.36',
        'Connection': 'keep-alive'
    }

    for item in range(0, 250, 25):
        url = "https://book.douban.com/top250?start={}".format(item)
        web_data = requests.get(url, headers=header)
        soup = BeautifulSoup(web_data.content, 'lxml')
        for movie in soup.select('.item'):
            href = movie.find('a')["href"]
            name = movie.get_text().strip()[:20].strip()  # 片名