​ Python轻量化自动化实战：本地、浏览器与Agent自动化代码教程

import os
import shutil

def organize_files(target_dir: str) -> None:
    # 遍历目标目录下所有文件
    for file_name in os.listdir(target_dir):
        file_path = os.path.join(target_dir, file_name)
        # 跳过目录，仅处理文件
        if os.path.isfile(file_path):
            # 获取文件后缀
            file_suffix = os.path.splitext(file_name)[1][1:] if os.path.splitext(file_name)[1] else "other"
            # 按后缀创建对应文件夹
            suffix_dir = os.path.join(target_dir, file_suffix)
            os.makedirs(suffix_dir, exist_ok=True)
            # 移动文件至对应文件夹
            shutil.move(file_path, os.path.join(suffix_dir, file_name))

if __name__ == "__main__":
    # 替换为目标目录路径
    target_directory = "./auto_organize"
    organize_files(target_directory)

from playwright.sync_api import sync_playwright

def crawl_web_data(url: str, target_selector: str) -> list:
    with sync_playwright() as p:
        # 启动无头浏览器，减少资源占用
        browser = p.chromium.launch(headless=True)
        context = browser.new_context()
        page = context.new_page()
        # 访问目标网页
        page.goto(url)
        # 等待目标元素加载完成
        page.wait_for_selector(target_selector, timeout=5000)
        # 抓取目标元素文本
        target_elements = page.query_selector_all(target_selector)
        data_list = [element.inner_text().strip() for element in target_elements]
        # 关闭浏览器
        browser.close()
        return data_list

if __name__ == "__main__":
    # 替换为目标网页URL和元素选择器
    target_url = "https://example.com"
    target_css_selector = "div.content-item"
    result = crawl_web_data(target_url, target_css_selector)
    print("抓取到的数据：", result)

import os
import json
from playwright.sync_api import sync_playwright

# 复用本地自动化文件整理函数
def organize_files(target_dir: str) -> None:
    for file_name in os.listdir(target_dir):
        file_path = os.path.join(target_dir, file_name)
        if os.path.isfile(file_path):
            file_suffix = os.path.splitext(file_name)[1][1:] if os.path.splitext(file_name)[1] else "other"
            suffix_dir = os.path.join(target_dir, file_suffix)
            os.makedirs(suffix_dir, exist_ok=True)
            shutil.move(file_path, os.path.join(suffix_dir, file_name))

# 复用浏览器自动化数据抓取函数
def crawl_web_data(url: str, target_selector: str) -> list:
    with sync_playwright() as p:
        browser = p.chromium.launch(headless=True)
        context = browser.new_context()
        page = context.new_page()
        page.goto(url)
        page.wait_for_selector(target_selector, timeout=5000)
        target_elements = page.query_selector_all(target_selector)
        data_list = [element.inner_text().strip() for element in target_elements]
        browser.close()
        return data_list

# 封装Agent自动化核心流程
def auto_task_chain(organize_dir: str, crawl_url: str, crawl_selector: str, save_path: str) -> None:
    # 步骤1：执行本地文件整理
    organize_files(organize_dir)
    # 步骤2：执行浏览器数据抓取
    crawl_result = crawl_web_data(crawl_url, crawl_selector)
    # 步骤3：保存抓取结果至本地
    with open(save_path, "w", encoding="utf-8") as f:
        json.dump(crawl_result, f, ensure_ascii=False, indent=2)

if __name__ == "__main__":
    # 替换为实际参数
    organize_directory = "./auto_organize"
    target_url = "https://example.com"
    target_selector = "div.content-item"
    save_file_path = "./crawl_result.json"
    # 执行自动化任务链
    auto_task_chain(organize_directory, target_url, target_selector, save_file_path)