0

代码试用：

#coding=utf-8

from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import Select, WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import time
import pandas as pd 

# Below is to crawl data from a webpage with two different dropdown
try:
    driver = webdriver.Chrome('./chromedriver')


    driver.get('https://price.joinsland.joins.com/theme/index_theme.asp?sisaegbn=T05')

    select1 = Select(WebDriverWait(driver, 5).until(EC.element_to_be_clickable((By.XPATH, "//select[@name='sido']"))))
    for item1 in select1.options:
        item1.click()
        select2 = Select(WebDriverWait(driver, 5).until(EC.element_to_be_clickable((By.XPATH, "//select[@name='gugun']"))))
        for item2 in select2.options:
            item2.click()
            time.sleep(2)

            # below is to get the attained date into excel file
            table = driver.find_element_by_class_name('tbl_box')
            tbody = table.find_element_by_tag_name('tbody')
            rows=tbody.find_elements_by_tag_name('tr')


            total = []
            result = []
            for index, value in enumerate(rows):
                body = value.find_elements_by_tag_name('td')

                for i in range(len(body)):
                    data = body[i].text
                    result.append(data)

            total.append(result)
            result=[]

        df = pd.DataFrame.from_records(total)
        df.to_excel('text.xlsx')



except Exception as e:
    print(e)

finally:
    driver.quit()

由于下面可爱的评论，我已经编辑了这段代码，但我得到了同样的错误，如下所示：

Message: stale element reference: element is not attached to the page document

我大致了解为什么会出现此消息，但仍不清楚如何解决此问题。我将非常感谢任何评论！提前谢谢了！

在此处输入图像描述

4

2 回答 2

1

这是我想出来的。但我不确定代码是否正确。我不知道蟒蛇。

#get select
select1 = Select(driver.find_element_by_xpath('//select[@name="sido"]'))

#get all options from select
options1 = select1.options

for opt1 is options1:

    #select the option which has the value of opt1
    select1.select_by_value(opt1.get_attribute("value"))
    time.sleep(5)

    select2 = Select(driver.find_element_by_xpath('//select[@name="gugu"]'))
    options2 = select2.options

    for opt2 in options2:
        select1.select_by_value(opt2.get_attribute("value"))
        time.sleep(4)
于 2020-06-09T11:05:18.333 回答
1

要从多个例如网站https://price.joinsland.joins.com/theme/index_theme.asp?sisaegbn=T05<option>中的两 (2) 个不同元素，您需要为您可以使用以下基于的Locator Strategies：element_to_be_clickable()

driver.get('https://price.joinsland.joins.com/theme/index_theme.asp?sisaegbn=T05')
select1 = Select(WebDriverWait(driver, 20).until(EC.element_to_be_clickable((By.XPATH, "//select[@name='sido']"))))
for item1 in select1.options:
    item1.click()
    select2 = Select(WebDriverWait(driver, 20).until(EC.element_to_be_clickable((By.XPATH, "//select[@name='gugun']"))))
    for item2 in select2.options:
        item2.click()
        time.sleep(3) # perform your web-crawling here
于 2020-06-09T11:59:50.137 回答