Python 3.x 从动态加载的网站中导出html表

我正在开发一个脚本来从动态网站中提取html表。以下是我的脚本：

from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
import time
import sys

driver = webdriver.Chrome()
driver.implicitly_wait(20)

URL = 'https://www.ccee.org.br/portal/faces/pages_publico/o-que-fazemos/como_ccee_atua/precos/precos_medios?_adf.ctrl-state=7e1fw5zdn_14&_afrLoop=19197915280379#!%40%40%3F_afrLoop%3D19197915280379%26_adf.ctrl-state%3D7e1fw5zdn_18'

driver.get(URL)
time.sleep(50)
soup = BeautifulSoup(driver.page_source, "html.parser")
table = soup.find('html')

list_of_rows = []
for row in table.findAll('tr'):
    list_of_cells = []
    for cell in row.findAll(["td"]):
        text = cell.text
        list_of_cells.append(text)
    list_of_rows.append(list_of_cells)

for item in list_of_rows:
    ' '.join(item)

Data = pd.DataFrame(list_of_rows)

Data.to_csv('Data.csv' ,index = False)

driver.quit()

我已使用Selenium提取，但无法获取URL网页中的表。当我运行此脚本时，得到如下表：

          0         1         2     3     4     5
0                                                
1                                None  None  None
2                                None  None  None
3                  OK        OK              None
4        OK                None  None  None  None
5                                            None
6                          None  None  None  None
7                                None  None  None
8            OKCancel  OKCancel              None
9  OKCancel                None  None  None  None

---

我已经修改了您的代码，现在可以正确导出表了

主要的问题可能是您的表位于iframe中 在进一步与页面交互之前，需要切换到。 BeatifulSoup cell.text包含\n，\t个字符，其中 使用正则表达式删除 查看更多评论，如果您有问题，请告诉我 解决方案：

import pandas as pd
from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
from bs4 import BeautifulSoup
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
import re

driver = webdriver.Chrome()
URL = 'https://www.ccee.org.br/portal/faces/pages_publico/o-que-fazemos/como_ccee_atua/precos/precos_medios?_adf.ctrl-state=7e1fw5zdn_14&_afrLoop=19197915280379#!%40%40%3F_afrLoop%3D19197915280379%26_adf.ctrl-state%3D7e1fw5zdn_18'

driver.get(URL)

WebDriverWait(driver, 60).until(EC.visibility_of_element_located((By.ID,'pt1:myFrame')))   #wait for iframe to load
iframe=driver.switch_to.frame('pt1:myFrame')

WebDriverWait(driver, 60).until(EC.visibility_of_element_located((By.XPATH,"//table//thead/tr/th")))  # wait for table header to load
soup = BeautifulSoup(driver.page_source, "html.parser")
table = soup.find('html')

list_of_rows = []
for row in table.findAll('tr'):
    list_of_cells = []
    for cell in row.findAll(["td"]):
        text = re.sub(r'\n\t+', '', cell.text)   #replace new line and tab with ''
        list_of_cells.append(text)
    list_of_rows.append(list_of_cells)

for item in list_of_rows:
    ' '.join(item)

data = pd.DataFrame(list_of_rows)
data.dropna(axis = 0, how='any', inplace = True)   # drop empty lines
header=['Mes','SE/CO','S','NE','N']
data.to_csv('Datax.csv', header=header, index = False)

driver.quit()