华为交换机学习

商标网信息爬取,网站http://wsgg.sbj.cnipa.gov.cn:9080/tmann/annInfoView/annSearchDG.html

商标网信息爬取

import MySQLdb
import requests
num = 1713
n = 0
url = "http://wsgg.sbj.cnipa.gov.cn:9080/tmann/annInfoView/annSearchDG.html"
headers = {
    'user-agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.80 Safari/537.36'
}
for annnum in range(50):
    data = {
        'page':'1',
        'rows':'400000',
        'annNum':str(num),
        'annType':'',
        'tmType':'',
        'coowner':'',
        'recUserName':'',
        'allowUserName':'',
        'byAllowUserName':'',
        'appId':'',
        'appIdZhiquan':'',
        'bfchangedAgengedName':'',
        'changeLastName':'',
        'transferUserName':'',
        'acceptUserName':'',
        'regName':'',
        'tmName':'',
        'intCls':'',
        'fileType':'',
        'totalYOrN':'true',
        'appDateBegin':'',
        'appDateEnd':'',
        'agentName':'',
    }
    num -= 1
    print(data)
    res = requests.post(url,data=data,headers=headers).json()
    # 1.连接数据库
    conn = MySQLdb.connect(
        host='localhost',
        port=3306,
        user='root',
        password='123456',
        db='spider',
        charset='utf8'
    )
    cursor = conn.cursor()
    for i in res['rows']:
        try:
            # sql1 = 'SELECT count(*) from brand1'
            # cursor.execute(sql1)
            # 2.准备sql语句
            sql = 'INSERT IGNORE INTO brand1 VALUES(%s,%s,%s)'
            # 3.执行sql
            cursor.execute(sql, [i['tm_name'], i['reg_num'], i['reg_name']])
            conn.commit()
            n += 1
            print(n)
        except Exception as e:
            print(f'存入数据失败，原因：{e}')