Skip to content
image-20250416231626812
python
def start_driver():
    # driver_path = "/Users/wangxiaomin/Documents/selenium_driver/chromedriver_106"  # 替换为你的实际路径
    driver_path = "/Users/wangxiaomin/Documents/selenium_driver/chromedriver_135"  # 替换为你的实际路径
    chrome_options = Options()
    debugger_address = "127.0.0.1:9222"
    chrome_options.add_experimental_option("debuggerAddress", debugger_address)
    service = Service(executable_path=driver_path)  

    st.session_state.driver = webdriver.Chrome(service=service, options=chrome_options)
    
def get_aricle_content(driver):
    texts = []
    for item in driver.find_elements(By.TAG_NAME,'p'):
        line = item.text
        if not line in texts:
            texts.append(line)
            st.write(line)
    for item in driver.find_elements(By.TAG_NAME,'span'):
        line = item.text
        if not line in texts:
            texts.append(line)
            st.write(line)
    return texts