使用 selenium/python 和 openpyxl 将值从 excel 发送到网页上的输入字段

Question

我有以下代码：

from selenium import webdriver
import sys
import time
import os
import pyautogui
import webbrowser
import openpyxl
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By
from selenium.webdriver.support.select import Select
from openpyxl import Workbook
from openpyxl import load_workbook

chrome_path =r"C:\Users\Desktop\webdriver\chromedriver.exe"
driver = webdriver.Chrome(chrome_path)
driver.get("url string")


def login(driver):

    elem = driver.find_element_by_xpath("""//*[@id="usernameField"]""")
    elem.send_keys("username")
    elem2 = driver.find_element_by_xpath("""//*[@id="passwordField"]""")
    elem2.send_keys("password")
    driver.find_element_by_xpath("""//*        [@id="loginForm"]/table/tbody/tr[4]/td[2]/input""").click()
    driver.find_element_by_xpath("""//*[@id="nav"]/ul/li[2]/a""").click()
    driver.find_element_by_xpath("""//*[@id="check1"]""").click()

def sendvalues(driver):

    wb = load_workbook('prueba.xlsx')
    coma = ","
    ws = wb.active
    buscar = driver.find_element_by_xpath(""" //*[@id="wrapper"]/form/div[2]/input[1]""")
    rut = driver.find_element_by_xpath("""//*[@id="rut"]""")
    dv = driver.find_element_by_xpath("""//*[@id="wrapper"]/form/table[1]/tbody/tr[3]/td[2]/input""")
    nombre = driver.find_element_by_xpath("""//*[@id="wrapper"]/form/table[1]/tbody/tr[4]/td[2]/input""")


    rutvalue = ws.cell(1,1).value
    dvvalue = ws.cell(1,2).value
    nombrevalue = ws.cell(1,3).value


    rut.send_keys(rutvalue)
    dv.send_keys(dvvalue)
    nombre.send_keys(nombrevalue)
    buscar.click()  
    table_elements = WebDriverWait(driver, 10).until(EC.presence_of_all_elements_located((By.XPATH, "//table[@class = 'grilla']")))
    for table_element in table_elements:
        for row in table_element.find_elements_by_xpath(".//tr"):
            text_file = open("Output2.txt", "a")
            text_file.write(str(rutvalue)+str(coma)+str(row.text)+'\n')
            text_file.close()

    clear(driver)

def clear(driver):

    rut = driver.find_element_by_xpath("""//*[@id="rut"]""")
    dv = driver.find_element_by_xpath("""//*[@id="wrapper"]/form/table[1]/tbody/tr[3]/td[2]/input""")
    nombre = driver.find_element_by_xpath("""//*[@id="wrapper"]/form/table[1]/tbody/tr[4]/td[2]/input""")
    rut.clear()
    dv.clear()
    nombre.clear()

login(driver)
sendvalues(driver)

代码将Excel文件的单行值发送到网站后提取表格。我在.xlsx文件中有三列rutvalue、dvvalue和nombrevalue，我需要将每一行的这些值发送到特定的输入字段（rut value、dv value、name value）在网页上并获取结果表。我需要将每个 Excel 行的值发送到输入字段。

有没有办法开发循环迭代每一行并得到结果？

Answer 1

您可以为抓取代码创建一个类，然后在另一个文件中读取 xlsx 文件并在每次迭代中调用该类。 看看这个例子。

class ScrapingCode():
   def __init__(self, rut, dv, name):
       self.rut = rut
       self.dv = dv
       self.name = name

  def run(self):
      #for use the values here, use self.name_var
      rut.send_keys(self.rut)  
      ...code scraping...

** 另一个文件

from app.folder.file import ScrapingCode
# read csv
for row in rows:
    scrapingCode = ScrapingCode(row[0], row[1], row[2])
    scrapingCode.run()

Answer 2

我修改和改进了代码，结果令人满意：

from selenium import webdriver
import sys
import time
import os
import pyautogui
import webbrowser
import openpyxl
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By
from selenium.webdriver.support.select import Select
from openpyxl import Workbook
from openpyxl import load_workbook

chrome_path =r"C:\Users\Desktop\webdriver\chromedriver.exe"
driver = webdriver.Chrome(chrome_path)
driver.get("myurl")


def login(driver):


    elem = driver.find_element_by_xpath("""//*[@id="usernameField"]""")
    elem.send_keys("myusername")
    elem2 = driver.find_element_by_xpath("""//*[@id="passwordField"]""")
    elem2.send_keys("mypassword")
    driver.find_element_by_xpath("""//*[@id="loginForm"]/table/tbody/tr[4]/td[2]/input""").click()
    driver.find_element_by_xpath("""//*[@id="nav"]/ul/li[2]/a""").click()
    driver.find_element_by_xpath("""//*[@id="check1"]""").click()

def sendvalues(driver):

    wb = load_workbook('prueba.xlsx')
    ws = wb.active
    buscar = driver.find_element_by_xpath(""" //*[@id="wrapper"]/form/div[2]/input[1]""")
    rut = driver.find_element_by_xpath("""//*[@id="rut"]""")
    dv = driver.find_element_by_xpath("""//*[@id="wrapper"]/form/table[1]/tbody/tr[3]/td[2]/input""")
    nombre = driver.find_element_by_xpath("""//*[@id="wrapper"]/form/table[1]/tbody/tr[4]/td[2]/input""")
    rutvalue=  ws.cell(row=x, column=1).value
    dvvalue= ws.cell(row=x, column=2).value
    nombrevalue= ws.cell(row=x, column=3).value
    rut.send_keys(rutvalue)
    dv.send_keys(dvvalue)
    nombre.send_keys(nombrevalue)
    buscar.click()
    table(driver)

def table(driver):
    rut = driver.find_element_by_xpath("""//*[@id="rut"]""")
    dv = driver.find_element_by_xpath("""//*[@id="wrapper"]/form/table[1]/tbody/tr[3]/td[2]/input""")
    nombre = driver.find_element_by_xpath("""//*[@id="wrapper"]/form/table[1]/tbody/tr[4]/td[2]/input""")
    coma = ","
    wb = load_workbook('prueba.xlsx')
    ws = wb.active
    rutvalue=  ws.cell(row=x, column=1).value
    table_elements = WebDriverWait(driver, 10).until(EC.presence_of_all_elements_located((By.XPATH, "//table[@class = 'grilla']")))

    for table_element in table_elements:
        for row in table_element.find_elements_by_xpath(".//tr"):
            text_file = open("Output2.txt", "a")
            text_file.write(str(rutvalue)+str(coma)+str(row.text)+'\n')
            text_file.close()
            rut.clear()
            dv.clear()
            nombre.clear()


login(driver)
for x in range(1,1000):
   sendvalues(driver)

我在代码末尾定义了“for循环”，并在sendvalues函数中定义了因子x，如下图所示：

rutvalue=  ws.cell(row=x, column=1).value
dvvalue= ws.cell(row=x, column=2).value
nombrevalue= ws.cell(row=x, column=3).value

感谢cmets！