上海Python

第五讲作业:爬取京东华为V20评论

2019-06-06  本文已影响0人  Zhaiyx

代码

import requests
import json
import pymysql
import time

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

headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36',
    'referer': 'https://item.jd.com/100002881193.html'
}

urls = ['https://sclub.jd.com/comment/productPageComments.action?productId=100002881193&score=0&sortType=5&page={}&pageSize=10'.format(str(i)) for i in range(0, 32)]

for url in urls:
    res = requests.get(url, headers=headers)
    # print(res.text)
    json_data = json.loads(res.text)
    comments = json_data['comments']
    for comment in comments:
        content = comment['content']
        score = comment['score']
        creationTime = comment['creationTime']
        nickname = comment['nickname']
        productColor = comment['productColor']
        productSize = comment['productSize']
        userClientShow = comment['userClientShow']
        userLevelName = comment['userLevelName']
        cursor.execute("insert into t_comment_new (content, score, creationTime, nickname, productColor, productSize, userClientShow, userLevelName) values(%s, %s, %s, %s, %s, %s, %s, %s)",
                       (content, score, creationTime, nickname, productColor, productSize, userClientShow, userLevelName))
        conn.commit()
    time.sleep(1)
conn.close()


结果

结果

分析

各个版本购买数量 设备来源分布
上一篇 下一篇

猜你喜欢

热点阅读