网址链接:http://bang.dangdang.com/books/bestsellers/
• 导包
import pymysql
import requests
from bs4 import BeautifulSoup
• 放入网址链接,转换格式
url = 'http://bang.dangdang.com/books/bestsellers/'
html = requests.get(url).text
• 连接数据库
db = pymysql.connect(host='localhost', user='root', password='123456', port=3306, db='xxx')
• 获取游标
cursor = db.cursor() # 获取游标
• 创建数据表(如果表不存在则创建)
sql = 'CREATE TABLE IF NOT EXISTS xxxxx(' \
'title VARCHAR(255) NOT NULL ,' \
'level1 VARCHAR(255) NOT NULL ,' \
'smmm VARCHAR(255) NOT NULL )'
• 执行命令
cursor.execute(sql)
• 运用bs4爬取数据,添加数据
soup = BeautifulSoup(html,'html.parser')
div2 = soup.find('ul', class_='bang_list clearfix bang_list_mode')
div = div2.find_all('li')
for i in div:
title = i.find('div', class_='name').text
level1 = i.find('div', class_='star').text
sm = i.find_all('div',class_='publisher_info')
smm = sm[0].text
smmm =sm[1].text
sql = 'INSERT INTO xxxxx(title,level1,smmm) VALUE("{}","{}","{}")'.format(
title, level1, smmm)
cursor.execute(sql) # 执行SQL语句字符串
db.commit() # 提交事务
来看看完整的代码:
import pymysql
import requests
from bs4 import BeautifulSoup
url = 'http://bang.dangdang.com/books/bestsellers/'
html = requests.get(url).text
db = pymysql.connect(host='localhost', user='root', password='123456', port=3306, db='xxx')
cursor = db.cursor() # 获取游标
sql = 'CREATE TABLE IF NOT EXISTS xxxxx(' \
'title VARCHAR(255) NOT NULL ,' \
'level1 VARCHAR(255) NOT NULL ,' \
'smmm VARCHAR(255) NOT NULL )'
cursor.execute(sql)
soup = BeautifulSoup(html,'html.parser')
div2 = soup.find('ul', class_='bang_list clearfix bang_list_mode')
div = div2.find_all('li')
for i in div:
title = i.find('div', class_='name').text
level1 = i.find('div', class_='star').text
sm = i.find_all('div',class_='publisher_info')
smm = sm[0].text
smmm =sm[1].text
sql = 'INSERT INTO xxxxx(title,level1,smmm) VALUE("{}","{}","{}")'.format(
title, level1, smmm)
cursor.execute(sql) # 执行SQL语句字符串
db.commit() # 提交事务
运行结果:
完成啦,希望有帮助到大家,有疑问或问题也可在评论区留言~