Selenium Python: execute_script 循环问题

Question

我想运行 execute_script 循环获取网站的详细信息。

这是我的完整代码：

import requests
from selenium import webdriver
from lxml import html
from urllib2 import urlopen
from bs4 import BeautifulSoup
import pandas as pd
import time

driver = webdriver.Chrome('C:\Users\Administrator\Documents\chromedriver.exe')
driver.get("https://www.ffbatiment.fr/federation-francaise-du-batiment/laffb/annuaire.html?Typ=2&Dep=03&Acti=724&Comm=0")
button = driver.find_element_by_id('ctl00_ctl00_ContentPlaceHolderGlobal_ContentPlaceHolderContenu_Button1')
href = button.get_attribute("href")
driver.execute_script(href, button)

listdata = driver.find_elements_by_xpath('//tr[@class="rgRow"]/td[1]/a')

for i in listdata:
    href = i.get_attribute("href")
    driver.execute_script(href, i)
    if(href):
        page_source = driver.page_source
        soup = BeautifulSoup(page_source, 'lxml')
        name = soup.find('span', {"id": "ctl00_ctl00_ContentPlaceHolderGlobal_ContentPlaceHolderContenu_FormView1_Ent_NomLabel"}).get_text()
        address = soup.find('span', {"id": "ctl00_ctl00_ContentPlaceHolderGlobal_ContentPlaceHolderContenu_FormView1_Ent_AdresseLabel"}).get_text()
        print(name)
        print(address)
        backbutton = driver.find_element_by_id('ctl00_ctl00_ContentPlaceHolderGlobal_ContentPlaceHolderContenu_FormView1_LButtonRetour')
        href2 = backbutton.get_attribute("href")
        driver.execute_script(href2, backbutton)
        time.sleep(5)

打印姓名和地址成功，但 execute_script 对下一个循环不起作用。

错误：

StaleElementReferenceExceptionTraceback (most recent call last)
<ipython-input-19-67f221094497> in <module>()
     16 
     17 for i in listdata:
---> 18     href = i.get_attribute("href")
     19     driver.execute_script(href, i)
     20     if(href):

......

StaleElementReferenceException: Message: stale element reference: element is not attached to the page document
  (Session info: chrome=83.0.4103.116)

谢谢。

Answer 1

试试这个代码：

import requests
from selenium import webdriver
from lxml import html
from urllib2 import urlopen
from bs4 import BeautifulSoup
import pandas as pd
import time

driver = webdriver.Chrome('chromedriver.exe')
driver.get("https://www.ffbatiment.fr/federation-francaise-du-batiment/laffb/annuaire.html?Typ=2&Dep=03&Acti=724&Comm=0")
button = driver.find_element_by_id('ctl00_ctl00_ContentPlaceHolderGlobal_ContentPlaceHolderContenu_Button1')
href = button.get_attribute("href")
driver.execute_script(href, button)

listdata = driver.find_elements_by_xpath('//tr[@class="rgRow"]/td[1]/a')

for i in range(len(listdata)):
    temp = driver.find_elements_by_xpath('//tr[@class="rgRow"]/td[1]/a')
    href = temp[i].get_attribute("href")
    driver.execute_script(href, temp[i])
    if(href):
        page_source = driver.page_source
        soup = BeautifulSoup(page_source, 'lxml')
        name = soup.find('span', {"id": "ctl00_ctl00_ContentPlaceHolderGlobal_ContentPlaceHolderContenu_FormView1_Ent_NomLabel"}).get_text()
        address = soup.find('span', {"id": "ctl00_ctl00_ContentPlaceHolderGlobal_ContentPlaceHolderContenu_FormView1_Ent_AdresseLabel"}).get_text()
        print(name)
        print(address)
        backbutton = driver.find_element_by_id('ctl00_ctl00_ContentPlaceHolderGlobal_ContentPlaceHolderContenu_FormView1_LButtonRetour')
        href2 = backbutton.get_attribute("href")
        driver.execute_script(href2, backbutton)
        time.sleep(5)

Selenium Python: execute_script 循环问题

Selenium Python: execute_script in a loop problem

python

selenium

webdriver

selenium-webdriver