使用selenium爬取集信达官网服务日志

import json
from time import sleep
from selenium import webdriver
from selenium.webdriver import Keys
from selenium.webdriver.common.by import By

# 2024022211 刘建强
class JiXinDa:
    def __init__(self):
        self.web=webdriver.Edge()
        self.web.maximize_window()
        self.url="https://jxd.itheima.net/#/login"

    def login_to_find(self):
        self.web.get(self.url)
        # 点击登录
        self.web.find_element(By.XPATH, '//*[@id="app"]/div/div/div[2]/div/button').click()
        # 点击短信服务
        self.web.find_element(By.XPATH, '//*[@id="app"]/div/div[1]/ul/li[2]/div/div').click()
        # 点击服务日志
        self.web.find_element(By.XPATH, '//*[@id="app"]/div/div[1]/ul/li[2]/ul/li/ul/li[5]').click()
        # 获取当前浏览器所有窗口句柄，该页面会切换页面句柄
        handles = self.web.window_handles
        # 切换新句柄，不然会导致element not interactable错误
        self.web.switch_to.window(handles[-1])
        # 点击重置
        self.web.find_element(By.XPATH,
                         "//*[@id='app']/div/div[2]/div[1]/div/div/div/div/div[3]/div[1]/form/div/div[5]/div/div/div/button[2]").click()
        # 输入关键词
        search_input = self.web.find_element(By.XPATH,
                                        "//*[@id='app']/div/div[2]/div[1]/div/div/div/div/div[3]/div[1]/form/div/div[1]/div/div/div/input")
        search_input.send_keys("闲云旅游")
        # 点击搜索
        self.web.find_element(By.XPATH,
                         "//*[@id='app']/div/div[2]/div[1]/div/div/div/div/div[3]/div[1]/form/div/div[5]/div/div/div/button[1]").click()

    def get_data(self):
        tables = []
        # 遍历数据
        trs = self.web.find_elements(By.XPATH,
                                "//*[@id='app']/div/div[2]/div[1]/div/div/div/div/div[3]/div[2]/div[1]/div[3]/table/tbody/tr")
        for i in trs:
            ths = i.find_elements(By.TAG_NAME, "td")
            tr_data = []
            for j in ths:
                text = j.text
                tr_data.append(text)
            table_data = {
                "序号": tr_data[0],
                "创建时间": tr_data[1],
                "通道名称": tr_data[2],
                "签名名称": tr_data[3],
                "模板名称": tr_data[4],
                "应用": tr_data[5],
                "耗时（秒）": tr_data[6],
                "状态": tr_data[7]
            }
            tables.append(table_data)
        sleep(5)
        # 下滑页面
        body = self.web.find_element('tag name', 'body')
        body.send_keys(Keys.PAGE_DOWN)
        sleep(2)
        page = self.web.find_element(By.XPATH, "//ul[@class='el-pager']/li[2]")
        page.click()
        sleep(3)
        # 遍历数据
        trs = self.web.find_elements(By.XPATH,
                                "//*[@id='app']/div/div[2]/div[1]/div/div/div/div/div[3]/div[2]/div[1]/div[3]/table/tbody/tr")
        for i in trs:
            ths = i.find_elements(By.TAG_NAME, "td")
            tr_data = []
            for j in ths:
                text = j.text
                tr_data.append(text)
            table_data = {
                "序号": tr_data[0],
                "创建时间": tr_data[1],
                "通道名称": tr_data[2],
                "签名名称": tr_data[3],
                "模板名称": tr_data[4],
                "应用": tr_data[5],
                "耗时（秒）": tr_data[6],
                "状态": tr_data[7]
            }
            tables.append(table_data)
        return tables

    def save_data(self,tables):
        # 输出JSON数据
        with open("jixinda.json", "w", encoding="utf-8") as f:
            json.dump(tables, f, ensure_ascii=False)
        print("保存成功")
        sleep(10)
        self.web.quit()

JiXinDa = JiXinDa()
JiXinDa.login_to_find()
JiXinDa.save_data(JiXinDa.get_data())