web抓取selenium python的过时异常

Question

我想从tripadvisor获取信息。我有时会

消息：过时的元素引用：元素未附加到页面文档 （会话信息：chrome=47.0.2526.73） （驱动程序信息：chromedriver=2.20.353124（035346203162d32c80f1dce587c8154a1efa0c3b），平台=Mac OS X 10.10.4 x86_64）

然后元素就是我分配给它的任何东西。如何修复代码以处理该问题，然后找出解决方案，而不是重新运行代码？在

  def getElements(driver):
        elements = []
        for dd in driver.find_elements_by_xpath("//*[contains(@class, 'ui_button original')]"):
            try:
                if dd.text == "Book Now":
                    elements.append(dd)
            except Exception as ee:
                print ee
        return elements 

def getBookingPartner(driver, ibInfo):
    data = []
    i = 0 
    elements = []
    time.sleep(2)
    elements = getElements(driver)
    elementCounter = 0
    while(elements == [] or elementCounter >5):
        elements = getElements(driver)
        elementCounter+=1

    print "Length of elements should be > 0 : " + str(len(elements))
    for ii in ibInfo:
        if ii[0] == "Yes":
            driver.implicitly_wait(3)
            bookingPartner = "Error"    
            print ii    
            driver.implicitly_wait(3)
            try:
                elements[i].click()
                driver.implicitly_wait(3)
                driver.switch_to_window(driver.window_handles[-1])
            except Exception as ee:
                try:
                    driver.refresh()
                    getElements(driver)[i].click()
                    time.sleep(1)
                    driver.switch_to_window(driver.window_handles[-1])
                except Exception as ee:
                    print "Stale Exception...."
                    print ee    
            try:
                driver.implicitly_wait(3)
                driver.find_elements_by_xpath("//*[contains(@class, 'book_now')]")[1].click()
                driver.implicitly_wait(1)
                page = etree.HTML(driver.page_source)
                bookingPartner = page.xpath("//div[contains(@class, 'custServiceMsg')]//text()")[0].split("will")[0].strip()                    
            except:
                try:
                    time.sleep(3)
                    driver.find_elements_by_xpath("//*[contains(@class, 'book_now')]")[1].click()
                    time.sleep(2)
                    page = etree.HTML(driver.page_source)
                    bookingPartner = page.xpath("//div[contains(@class, 'custServiceMsg')]//text()")[0].split("will")[0].strip()                    
                except:
                    try:
                        bookingPartner = page.xpath("//div[contains(@class, 'custServiceMsg')]//text()")[1].split("will")[0].strip()
                    except Exception as ee:
                        bookingPartner = "Error"
                        print "error"
            i+=1

            if bookingPartner == "The remainder":
                bookingPartner = page.xpath("//div[contains(@class, 'custServiceMsg')]//text()")[1].split("will")[0].strip()

            if len(driver.window_handles) > 1:
                driver.close()
                driver.switch_to_window(driver.window_handles[0])

            print bookingPartner

            data.append([ii[0], ii[1], bookingPartner])
        else:
            data.append([ii[0], ii[1], "N/A"])
            ii.extend(["N/A"])

        print data
    return data

Answer 1

当元素：

1. 已被删除
2. 不再附加到DOM（如您的情况）
3. 已经改变了

从文件中：

You should discard the current reference you hold and replace it, possibly by locating the element again once it is attached to the DOM.

即：再次“找到”元素。在

您需要修改代码，以便在适当的步骤中捕获此错误。在

from selenium.common.exceptions import StaleElementReferenceException

elem = driver.find_element_by_xpath('something leaves dom')
# ... do other actions which change the page and then later...
try:
    elem.click()
except StaleElementReferenceException:
    elem = driver.find_element_by_xpath('something leaves dom')
    elem.click()

如果您需要一个可重用的版本来处理多个元素。在

顺便说一句，您不应该在代码中捕捉Exception。明确你想处理哪些问题。在