第三周作业

import requests

import json

import pymysql

import time

conn = pymysql.connect(host='localhost', user='root', passwd='123456', db='mydb', port=3306, charset='utf8')

cursor = conn.cursor()

headers  =  {

    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36 SE 2.X MetaSr 1.0',

    'referer': 'https://item.jd.com/100005270438.html'

}

urls = ['https://sclub.jd.com/comment/productPageComments.action?productId=100005270438&score=0&sortType=5&page={}&pageSize=10'.format(str(i)) for i in range(0,100)]

for url in urls:

    res = requests.get(url,headers=headers)

    json_data = json.loads(res.text)

    comments = json_data['comments']

    for comment in comments:

        content = comment['content']

        creationTime = comment['creationTime']

        nickname = comment['nickname']

        productColor = comment['productColor']

        cursor.execute("insert into jd_info (content,creationTime,nickname,productColor) values(%s,%s,%s,%s)",

                      (content, creationTime, nickname, productColor))

        conn.commit()

    time.sleep(4)

conn.close()


最后编辑于
©著作权归作者所有,转载或内容合作请联系作者
平台声明:文章内容(如有图片或视频亦包括在内)由作者上传并发布,文章内容仅代表作者本人观点,简书系信息发布平台,仅提供信息存储服务。

推荐阅读更多精彩内容