第四个爬虫 selenium chrome

import xlrd
import xlwt
import time
import requests
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.common.keys import Keys

mailnums = []

path = 'D:\EMS83Search\Chrome\chromedriver.exe'
options = webdriver.ChromeOptions()
options.add_argument('--headless')
options.add_argument('--disable-gpu')
options.add_argument('blink-settings=imagesEnabled=false')
options.add_argument('--ignore-certificate-errors')
options.add_argument('--log-level=5')
options.add_argument('--disable-infobars')
options.add_argument('--no-sandbox')
options.add_argument('--disable-dev-shm-usage')
options.add_argument('--disable-logging')
options.add_argument('--hide-logging')
options.add_argument('--disable-devtools')



options.add_argument('user-agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/537.36 Edge/18.17763"')

# browser = webdriver.Chrome(executable_path=path,options=chrome_options)

nums = []
sjtimes = []
sjplaces = []
status = []
lstimes = []
lsplaces = []

def get_nums():
    with xlrd.open_workbook('D:\EMS83Search\Emsnum.xls', 'r') as K:
        num = K.sheets()[0]
        lie = num.nrows
    for l in range(lie):
        mailnum = int(num.row_values(l)[0])
        mailnums.append(mailnum)


def get_info():
    count = 1

    headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) \
    AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.80 Safari/537.36'
    ,'Connection': 'keep-alive'}




    browser = webdriver.Chrome(executable_path=path,options=options)

    for i in mailnums:
        try:
            browser.get('http://10.3.10.83/ems/newsystem/thesecond/ttq/ttqMailquery.jsp')
            browser.implicitly_wait(5)
            input = browser.find_element_by_id('mailNum')
            input.send_keys(i)
            input.send_keys(Keys.ENTER)

            html = browser.find_element_by_xpath('//*').get_attribute('outerHTML')
            soup = BeautifulSoup(html,'html.parser')
            realweb = soup.find(attrs={'target':'ajaxFrameArea'})
            web2 = realweb['action']
            web2 = web2[8:]
            web1 = 'http://10.3.10.83/ems'
            web666 = web1 + web2

            rsp = requests.get(web666,headers=headers)
            rep = rsp.text
            soup = BeautifulSoup(rep,'html.parser')
            soup = soup.body

            sjtime = soup.find(attrs={'width':'47%'})
            sjplace = soup.find(attrs={'width':'25%'})
			
            # print(sjtime.text)
            # print(sjplace.text)
            sjtimes.append(sjtime.text)
            sjplaces.append(sjplace.text)

            soup2 = soup.find(attrs={'id':'frameTrackStatueInfo'})
            # print(soup2.td.string)
            nums.append(soup2.td.string)

            qq = browser.find_element_by_xpath('//*[@id="trackStatueInfo"]/table/tbody/tr/td[3]')

            # print(qq.text)
            lstimes.append(qq.text)

            qq2 =browser.find_element_by_xpath('//*[@id="trackStatueInfo"]/table/tbody/tr/td[5]')
            qq3 =browser.find_element_by_xpath('//*[@id="trackStatueInfo"]/table/tbody/tr/td[7]')

            # print(qq2.text[6:])
            # print(qq3.text[3:])
            status.append(qq2.text[6:])
            lsplaces.append(qq3.text[3:])
        except:
            nums.append(i)
            sjtimes.append('邮件号不对??')
            sjplaces.append('网络出问题了??')
            lstimes.append('A股又跌了??')
            status.append('今天心情不美丽??')
            lsplaces.append('我方水晶正在被攻击???')
            browser = webdriver.Chrome(executable_path=path,options=options)

        print(f'正在查询第{count}件: {i}')
        count += 1

    browser.close()
    browser.quit()

def get_excel():

    wjtime = time.strftime('%Y-%m-%d_%H-%M',time.localtime(time.time()))
    tt = []
    tt.append(wjtime)
    ttt1 = tt[0]
    ttt3 = '件'
    ttt4 = f'---{len(nums)}'
    ttt2 = '.xlsx'
    tttt = ttt1 + ttt4 + ttt3 + ttt2

    a = 1
    b = 0

    c = 1
    d = 1

    e = 1
    f = 2

    g = 1
    h = 3

    i = 1
    j = 4

    k = 1
    l = 5

    wb = xlwt.Workbook()
    sheet1 = wb.add_sheet('查询结果')
    
    sheet1.write(0,0,'邮件号码')
    sheet1.write(0,1,'收寄日期')
    sheet1.write(0,2,'收寄地点')
    sheet1.write(0,3,'最后时间')
    sheet1.write(0,4,'最后地点')
    sheet1.write(0,5,'最后状态')

    for v in nums:
        sheet1.write(a,b,str(v))
        a += 1

    for vv in sjtimes:
        sheet1.write(c,d,vv)
        c += 1

    for vvv in sjplaces:
        sheet1.write(e,f,vvv)
        e += 1

    for vvvv in lstimes:
        sheet1.write(g,h,vvvv)
        g += 1

    for vvvvv in lsplaces:
        sheet1.write(i,j,vvvvv)
        i += 1

    for vvvvvv in status:
        sheet1.write(k,l,vvvvvv)
        k += 1

    wb.save(f'D:\EMS83Search\{tttt}.xls')

get_nums()
get_info()
get_excel()