瑞数系列_商标局公告采集

根据公告期号进行数据采集

import requests
import json
from crawler2.tool.database.MongoDb import MyMongoDB
import time
if __name__ == '__main__':
    mongo = MyMongoDB('root', "123456", '192.168.4.231', 27017, 'xcx_gov_cn', 'sbj_gg')
    get_data_url = "https://service.*****.com/getListData?sendParam={}"
    # 写死公告号1179
    send_param_obj = {"rows":100,"annNum":"1179","annType":"","tmType":"","coowner":"","recUserName":"","allowUserName":"","byAllowUserName":"","appId":"","appIdZhiquan":"","bfchangedAgengedName":"","changeLastName":"","transferUserName":"","acceptUserName":"","regName":"","tmName":"","intCls":"","fileType":"","totalYOrN":"true","appDateBegin":"","appDateEnd":"","agentName":"","page":1}

    for i in range(1,2):
        send_param_obj["page"] = i
        resp = requests.get(get_data_url.format(json.dumps(send_param_obj))).json()
        print("page:{}".format(i))
        rows = resp["data"]["resp_data"]["rows"]
        for row in rows:
            print(row)
        # mongo.insert_many(resp["data"]["resp_data"]["rows"])
        time.sleep(5)

调用流程