【Python】selenium本地网页内容代码保存demo

功能介绍

打开本地html，定位到特定内容，然后保存该内容对应的html到txt中

代码

from selenium import webdriver
from tqdm import tqdm

def write_txt(txt_list, txt_name):
    with open(txt_name, 'a+', encoding='utf-8') as f:
        for txt in txt_list:
            f.write(txt+'\n\n')

def login(web_address):
    # 若不打开网页
    # option = webdriver.ChromeOptions()
    # option.add_argument('headless')  # 设置option
    # driver = webdriver.Chrome(options=option)  # 调用带参数的谷歌浏览器
    # 若要打开网页显示过程
    driver = webdriver.Chrome()  # 调用带参数的谷歌浏览器
    # 2. 打开保存在本地的html
    driver.get(web_address)
    return driver

def change_web(web_address):
    driver.get(web_address)
    return driver

def save_keyinfo(driver, xpath, txt_name):
    # 3. 定位元素，并得到html代码
    try:
        table_list = driver.find_elements_by_xpath(xpath)
        keyinfo = []
        for i, table in enumerate(tqdm(table_list)):
            keyinfo.append(table.get_attribute('outerHTML'))

        # 写入到txt中
        write_txt(keyinfo, txt_name)
    except:
        # 最好能记录下报错的网页地址
        pass

if __name__ == '__main__':
    # 获取所有要读取的网页地址
    web_address_list = [""]
    # 内容保存的txt文件名
    txt_name = 'xxx.txt'
    # 用于关键信息定位的xpath
    xpath = ''

    for i, web_address in enumerate(web_address_list):
        print("【{}】:{}".format(i, web_address))
        # 进入网页
        if i==0:
            # 创建webdriver
            driver = login(web_address)
        else:
            driver = change_web(web_address)

         # 得到单个网页下，需要保存的内容，并且写入到txt中
        save_keyinfo(driver, xpath, txt_name)

        # 退出访问的实例网站。
        if i==len(web_address_list)-1:
            driver.quit()