如何在硒中获取结束标签

Question

我正在处理分页，并希望我的脚本抓取一个表格，点击下一个按钮，抓取下一个表格，然后点击下一个，直到它不再可点击。

可点击与不可点击的唯一区别似乎是 disabled> 结束标签。

我的想法是创建一个while循环并单击按钮直到禁用的标签消失，但我不知道如何首先获得该标签。

即使按钮被禁用，Selenium 也不会抛出“元素不可交互”错误，所以我认为我不能走这条路。

airport_list = []
fees_list = []

airports = ["https://www.aopa.org/destinations/business/13035#fees", "https://www.aopa.org/destinations/business/35555#fees"]

for a in airports:
    driver.get(a)
    time.sleep(3)

    # Click dropdown
    driver.find_element_by_xpath('//div[@class = "mat-select-arrow"]').click()
    time.sleep(1)
    # Select "All aircraft"
    driver.find_elements_by_xpath('//span[@class = "mat-option-text"]')[8].click()
    time.sleep(2)

    try:        

        # Check if fees are available
        driver.find_element_by_xpath('//mat-row[@class = "mat-row ng-star-inserted"]')

        #Scrape each row
        fees_table = driver.find_elements_by_xpath('//mat-row[@class = "mat-row ng-star-inserted"]')
            for fee in fees_table:
            fees_list.append(fee.text)
            airport_list.append(a)

        #Click on "Next" button

        driver.find_elements_by_xpath('//span[@class = "mat-button-wrapper"]')[4].click()
        time.sleep(2)

    except:
        fees_list.append("This location has not disclosed fees or does not charge fees.")
        airport_list.append(a)           

driver.close()

Answer 1

我能够从表格底部提取最大数量的项目，将该数字除以 10，然后四舍五入到最接近的数字。然后我使用该数字遍历一个范围。

airport_list = []
fees_list = []

airports = ["https://www.aopa.org/destinations/business/13035#fees"]

for a in airports:
    driver.get(a)
    time.sleep(3)

    # Click dropdown
    driver.find_element_by_xpath('//div[@class = "mat-select-arrow"]').click()
    time.sleep(1)
    # Select "All aircraft"
    driver.find_elements_by_xpath('//span[@class = "mat-option-text"]')[8].click()
    time.sleep(2)

    try:        
        # Check if fees are available
        driver.find_element_by_xpath('//mat-row[@class = "mat-row ng-star-inserted"]')

        # Get number of items
        number_of_items = driver.find_element_by_xpath('//div[@class = "mat-paginator-range-label"]').text.split()[-1]
        #print(number_of_items)

        if float(number_of_items) >= 11:
            number_of_button_clicks = math.ceil(float(number_of_items)/10)
        else:
            number_of_button_clicks = 0
        #print(number_of_button_clicks)

        for click in range(0, number_of_button_clicks):
            #Scrape each row
            fees_table = driver.find_elements_by_xpath('//mat-row[@class = "mat-row ng-star-inserted"]')
            for fee in fees_table:
                fees_list.append(fee.text)
                airport_list.append(a)

            #Click on "Next" button

            driver.find_elements_by_xpath('//span[@class = "mat-button-wrapper"]')[4].click()
            time.sleep(2)

    except:
        fees_list.append("This location has not disclosed fees or does not charge fees.")
        airport_list.append(a)


#print(fee_list)
#print(airport_list)            

driver.close()

Answer 2

使用如下代码所示的最大行数限制，而不是继续下一页。最重要的是，你真的不需要使用 try except 块 -

for a in airports:
    driver.get(a)
    time.sleep(3)

    # Click dropdown
    driver.find_element_by_xpath('//div[@class = "mat-select-arrow"]').click()
    time.sleep(1)
    # Select "All aircraft"
    driver.find_elements_by_xpath('//span[@class = "mat-option-text"]')[8].click()
    time.sleep(3)

    # select 100 Items per page if items are present
    if len(driver.find_elements_by_xpath(".//mat-select[@aria-label='Items per page:']")) > 0 :
        driver.find_element_by_xpath(".//mat-select[@aria-label='Items per page:']").click()
        time.sleep(3)
        driver.find_element_by_xpath(".//span[@class='mat-option-text' and text()='100']/parent::mat-option").click()

    # Scrape each row
    fees_table = driver.find_elements_by_xpath('//mat-row[@class = "mat-row ng-star-inserted"]')
    for fee in fees_table:
        fees_list.append(fee.text)
    print(fees_list)

        # if needed then Click on "Next" button using this xpath and apply same for loop as above
        #driver.find_elements_by_xpath(".//button[@aria-label='Next page']").click()
driver.close()