zj-unicom-ai/uniemployee/tencent-ima-wiki

import seed_browser_use as bu
# 同步连接浏览器
bu.resync()
# 确认页面已加载
bu.wait_for_load(timeout=15)
page_info = bu.page_info()
print("当前页面:", page_info.get("url"))

js_code = """
(async () => {
    const results = [];
    const count = arguments[0] || 10;  // 要提取的条数
    
    for (let i = 0; i < count; i++) {
        const item = document.querySelector(`[data-index="${i}"]`);
        if (!item) continue;
        
        const fiberKey = Object.keys(item).find(k => k.startsWith('__reactFiber'));
        let fiber = item[fiberKey];
        
        let foundPath = null;
        let foundTitle = null;
        let depth = 0;
        
        function searchObj(obj, path, depth2) {
            if (!obj || depth2 > 8 || foundPath) return;
            if (typeof obj !== 'object') return;
            
            for (let key in obj) {
                try {
                    if ((key === 'sourcePath' || key === 'source_path') && typeof obj[key] === 'string') {
                        foundPath = obj[key];
                    }
                    if ((key === 'title' || key === 'name') && typeof obj[key] === 'string' && obj[key].length > 5) {
                        foundTitle = obj[key];
                    }
                    if (typeof obj[key] === 'object' && obj[key] !== null) {
                        searchObj(obj[key], path + '.' + key, depth2 + 1);
                    }
                } catch(e) {}
            }
        }
        
        while (fiber && depth < 30 && !foundPath) {
            if (fiber.memoizedProps) {
                searchObj(fiber.memoizedProps, 'props', 0);
            }
            fiber = fiber.return;
            depth++;
        }
        
        results.push({
            index: i,
            title: foundTitle || item.innerText.split('\\n')[0],
            sourcePath: foundPath
        });
    }
    return results;
})()
"""
# 传入要提取的条数
result = bu.js(js_code.replace('arguments[0] || 10', '5'))

import time
for article in result:
    if not article.get('sourcePath'):
        continue
    
    # 关闭上一个标签页（可选，节省资源）
    # bu.close_tab()
    # time.sleep(1)
    
    # 打开新标签页
    bu.new_tab(article['sourcePath'])
    time.sleep(3)
    bu.wait_for_load(timeout=10)
    
    # 获取文章正文
    content = bu.get_page_text()
    print(f"标题: {article['title']}")
    print(f"内容: {content[:500]}...")
    
    # 处理完后关闭
    bu.close_tab()
    time.sleep(1)

# 滚动列表区域
bu.scroll(500, 500, "down", amount=5)
time.sleep(1)
# 然后重新提取 data-index 更大的项