如何使用Selenium Python爬取动态表格中的多语言和编码格式

# 导入所需的库和模块
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import csv
import time

# 创建一个webdriver对象，指定使用firefox浏览器，并设置代理服务器和验证信息
# 亿牛云 爬虫代理加强版 
proxyHost = "www.16yun.cn"
proxyPort = "3111"
proxyUser = "16YUN"
proxyPass = "16IP"

profile = webdriver.FirefoxProfile()
profile.set_preference("network.proxy.type", 1)
profile.set_preference("network.proxy.http", proxyHost)
profile.set_preference("network.proxy.http_port", int(proxyPort))
profile.set_preference("network.proxy.ssl", proxyHost)
profile.set_preference("network.proxy.ssl_port", int(proxyPort))
profile.set_preference("network.proxy.no_proxies_on", "localhost, 127.0.0.1")
profile.update_preferences()
driver = webdriver.Firefox(firefox_profile=profile)

# 打开目标网址，并等待页面加载完成
url = "https://example.com/population-table"
driver.get(url)
wait = WebDriverWait(driver, 10)
wait.until(EC.presence_of_element_located((By.ID, "table")))

# 定义一个函数，用于获取表格中的数据
def get_table_data():
    # 定位表格元素，并获取表头和表体的数据
    table = driver.find_element_by_id("table")
    header = table.find_element_by_tag_name("thead")
    header_data = [item.text for item in header.find_elements_by_tag_name("th")]
    body = table.find_element_by_tag_name("tbody")
    body_data = []
    rows = body.find_elements_by_tag_name("tr")
    for row in rows:
        cols = row.find_elements_by_tag_name("td")
        cols_data = [item.text for item in cols]
        body_data.append(cols_data)
    # 返回表头和表体的数据
    return header_data, body_data

# 定义一个列表，用于存储所有的数据
all_data = []

# 循环点击分页按钮，并获取每一页的数据
pages = driver.find_elements_by_class_name("page-item")
for page in pages:
    page.click()
    time.sleep(1)
    header_data, body_data = get_table_data()
    all_data.extend(body_data)

# 切换语言选项，并重复步骤4和5
language = driver.find_element_by_id("language")
language.click()
time.sleep(1)
pages = driver.find_elements_by_class_name("page-item")
for page in pages:
    page.click()
    time.sleep(1)
    header_data, body_data = get_table_data()
    all_data.extend(body_data)

# 切换编码格式选项，并重复步骤4和5
encoding = driver.find_element_by_id("encoding")
encoding.click()
time.sleep(1)
pages = driver.find_elements_by_class_name("page-item")
for page in pages:
    page.click()
    time.sleep(1)
    header_data, body_data = get_table_data()
    all_data.extend(body_data)

# 将所有数据保存为CSV文件，并关闭浏览器
with open("population.csv", "w", newline="", encoding="utf-8") as f:
    writer = csv.writer(f)
    writer.writerow(header_data)
    writer.writerows(all_data)
driver.quit()