硒，python 动态 table

Question

我正在用 selenium 创建一个机器人，它可以从巴西的机构获取所有信息，我已经完成了所有州和县之间的排列点击，我现在要做的就是点击所有机构并获取信息，例如: "telefone","endereço","HORÁRIO DE ATENDIMENTO"。我怎样才能做到这一点？？到目前为止，这是我的代码：

 # -*- coding: UTF-8 -*-
from selenium import webdriver
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support.select import Select
import time     
import urllib
import urllib.request
from bs4 import BeautifulSoup
import request


def make_soup(url):
    thepage = urllib.request.urlopen(url)
    soupdata = BeautifulSoup(thepage,'html.parser')
    return soupdata

chrome_path = r"D:\Users\gbenites\Desktop\Inovação\arquivos py\WebDriver\chromedriver.exe"
url = 'http://www2.correios.com.br/sistemas/agencias/'
driver = webdriver.Chrome(chrome_path)
driver.get("http://www2.correios.com.br/sistemas/agencias/")
#WebDriverWait(driver, 20).until(EC.presence_of_element_located((By.ID, 'municipioAgencia')))
driver.maximize_window()


time.sleep(3) 
estadoList = Select(driver.find_element_by_name('estadoAgencia'))
for index in range(3,len(estadoList.options)):
    select = Select(driver.find_element_by_name('estadoAgencia'))
    print("selecting Estado: ",select.options[index].text)    
    print("selecting Index: ",index)    
    select.select_by_index(index)
    time.sleep(2)
    municípioList = Select(driver.find_element_by_name('municipioAgencia'))
    for index_b in range(1,len(municípioList.options)):
        select_b = Select(driver.find_element_by_name('municipioAgencia'))
        print("...selecting Municipio",select_b.options[index_b].text.replace("'",""))
        print("...selecting Municipio Index: ",index_b)
        select_b.select_by_index(index_b)
        time.sleep(3)
        get_info_list =  WebDriverWait(driver, 10).until(EC.presence_of_all_elements_located((By.XPATH, "//table[@class = 'dadosAgencia']//td")))
        info_list = driver.find_elements_by_xpath("//table[@class = 'dadosAgencia']//span")
        print(range(len(info_list)))
        for record in range(0,len(info_list)):
            print(record.get_attribute('innerText'))

这就是我的输出：

selecting Estado:  AMAPÁ
selecting Index:  3
...selecting Municipio AMAPA
...selecting Municipio Index:  1
range(0, 27)
0
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26

Answer 1

试试这个 xPath：

//table[@class = 'dadosAgencia']//tr

会是这样的：

elements = WebDriverWait(driver, 10).until(EC.presence_of_all_elements_located(
            (By.XPATH, "//table[@class = 'dadosAgencia']//tr")))

它为您提供了所有找到的元素的列表。要打印每个元素的文本，您可以使用：

for element in elements:
    print(element.text)

注意：您必须添加一些导入：

from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By
from selenium.webdriver.support.wait import WebDriverWait

Answer 2

为 table 尝试此 XPath：

//table[@class = 'dadosAgencia']

首先，找到table个元素：

table_elements = WebDriverWait(driver, 10).until(EC.presence_of_all_elements_located(
        (By.XPATH, "//table[@class = 'dadosAgencia']")))

遍历 table:

for table_element in table_elements:
    for row in table_element.find_elements_by_xpath(".//tr"):
        print(row.text)

硒，python 动态 table

Selenium, python dynamic table

python

selenium

dynamic-tables