html2markdown

from selenium.webdriver.support.ui import WebDriverWait
from selenium import webdriver
from markdownify import markdownify as md


def parse_url(title,link_url):
    chromedriver_path = "/Users/user/chrome/chromedriver"
    options = webdriver.ChromeOptions()
    options.add_experimental_option("prefs", {"profile.managed_default_content_settings.images": 2})  # 不加载图片,加快访问速度
    options.add_experimental_option('excludeSwitches', ['enable-automation'])  # 此步骤很重要，设置为开发者模式，防止被各大网站识别出来使用了Selenium
    browser = webdriver.Chrome(executable_path=chromedriver_path, options=options)
    browser.get(link_url)
    WebDriverWait(browser, 10)

    s1 = browser.find_element_by_class_name("post-content")
    content = md(s1.get_attribute("outerHTML"))
    with open('doc/{}.md'.format(title), 'w+') as f:
        f.write("# " + title)
        f.write("\n")
        f.write("## 来源")
        f.write("\n")
        f.write(link_url)
        f.write("\n")
        f.write(content)
        f.write("\n\n")
        browser.close()