工作日志:自动查询maven仓库中依赖库的开源协议

import  xml.dom.minidom#打开xml文档dom = xml.dom.minidom.parse('E:\pom-task.xml')#得到文档元素对象root = dom.documentElement#获得标签对之间的数据artifactId = root.getElementsByTagName('artifactId')groupId = root.getElementsByTagName('groupId')# 打印所有artifactId标签的内容for index,i in enumerate(artifactId):    #有些标签内容不符合，需要剔除    if 'se' not in i.firstChild.data and 'low' not in i.firstChild.data  and 'maven' not in i.firstChild.data :        print(i.firstChild.data)

import pandas as pdimport os#文件路径file_dir = r'E:\Pychavn\pom_excel'#构建新的表格名称new_filename = file_dir + '\\new_file.xls'#找到文件路径下的所有表格名称，返回列表file_list = os.listdir(file_dir)new_list = []for file in file_list:    #重构文件路径    file_path = os.path.join(file_dir,file)    #将excel转换成DataFrame    dataframe = pd.read_excel(file_path)    #保存到新列表中    new_list.append(dataframe)#多个DataFrame合并为一个df = pd.concat(new_list)#写入到一个新excel表中df.to_excel(new_filename,index=False)

from aip_demo.my_log import MyLogimport timefrom aip_demo.project_path import test_case_pathlogger=MyLog()class MyExcel:    """    初始化传入文件名和表单名    """    def __init__(self,file_name,sheet_name):        self.file_name=file_name        self.sheet_name=sheet_name    def get_data(self):#获取测试数据        wb=load_workbook(self.file_name)#打开工作簿        sheet=wb[self.sheet_name]#测试用例的表单        test_data=[]        for i in range(2,sheet.max_row+1):#sheet.max_row    sheet.max_column获取表单最大行   列            sub_data = {}            sub_data['id']=sheet.cell(i,1).value#序号            sub_data['name'] = sheet.cell(i, 2).value            sub_data['groupId'] = sheet.cell(i, 3).value            sub_data['artifactId'] = sheet.cell(i, 4).value            sub_data['version'] = sheet.cell(i, 5).value            test_data.append(sub_data)        return test_data    def write_back(self,row,lis,):#写回数据到Excel        wb=load_workbook(self.file_name)        sheet=wb[self.sheet_name]        logger.info("正在写入序号：{}的开源协议{}".format(row-1,lis))        sheet.cell(row,6).value=lis        wb.save(self.file_name)

datas = MyExcel('E:\Pycan.xlsx','Sheet1').get_data()print(datas)list1 =[]for i in datas:    a=''    groupId = i['groupId']    artifactId=i['artifactId']    version=i['version']    url = "https://mvnrepository.com/artifact/"    a=url+str(groupId)+'/'+str(artifactId)+'/'+str(version)    list1.append(a)print(list1)

from selenium import webdriveroptions = webdriver.ChromeOptions()options.debugger_address = "127.0.0.1:9222"driver = webdriver.Chrome(options=options)for index ,j in enumerate(list1):    driver.get(j)    # 获取开源协议元素    ele = driver.find_element_by_xpath('//span[@class="b lic"]')    lis = ele.text #获取元素的问题    MyExcel('E:\PycharmPan.xlsx', 'Sheet1').write_back(index+2, lis)    time.sleep(1)