python+playwright如何自主搜集整理新闻打开浏览器自主填写表单发布?
网友回复
这是一个playwright自动打开一个新闻网站后台,输入内容的示例代码:
from playwright.sync_api import sync_playwright, expect import time import platform # 用于判断操作系统 def get_dom_and_paste(url: str, target_selector: str, text_to_paste: str): """ 打开网页,获取 DOM,并在指定元素中模拟粘贴操作。 Args: url: 目标网页 URL。 target_selector: 要粘贴内容的目标元素的 CSS 选择器。 text_to_paste: 要模拟粘贴的文本。 """ with sync_playwright() as p: browser = p.chromium.launch(headless=False) # 重要:授予浏览器访问剪贴板的权限 context = browser.new_context(permissions=["clipboard-read", "clipboard-write"]) page = context.new_page() try: print(f"正在导航到: {url}") page.goto(url, wait_until='domcontentloaded') print("页面加载完成。") # --- 1. 获取 DOM 树结构 --- print("\n--- 获取页面 DOM 结构 ---") dom_content = page.content() print("DOM 结构 (前 500 字符):") print(dom_content[:500] + "...") # 你可以将 dom_content 保存到文件或进行进一步分析 # with open("page_dom.html", "w", encoding="utf-8") as f: ...
点击查看剩余70%