e1fbd31c64
- 高危词库从 process.py 抽到 config.toml [security] section - process.py 改为 _get_high_risk_words() 动态加载（配置优先） - 新增 15 个 QQ 操作脚本（已脱敏：QQ号/IP/Token → 占位符） - 新增 8 个 SKILL.md（qq-messenger/management/resolver/napcat-extras 等） - 新增 SKILL.md 入口（完整部署方案文档） - 保留 SDK 框架（plugin_modules.py, file_store_api.py, package.py 等）
76 lines
2.5 KiB
Python
76 lines
2.5 KiB
Python
#!/usr/bin/env python3
|
||
"""
|
||
Headless browser tool for qq-agent.
|
||
Usage:
|
||
python3 browse.py https://example.com # 获取页面文字内容
|
||
python3 browse.py https://example.com --screenshot # 截图保存
|
||
python3 browse.py https://example.com --wait 3 # 等待3秒再抓取（用于JS渲染页面）
|
||
"""
|
||
|
||
import sys
|
||
import os
|
||
import argparse
|
||
|
||
from playwright.sync_api import sync_playwright, TimeoutError as PlaywrightTimeout
|
||
|
||
BASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
|
||
SAVE_DIR = os.path.join(BASE_DIR, "files")
|
||
|
||
CHROMIUM_PATH = "/usr/local/bin/chromium"
|
||
|
||
|
||
def browse(url: str, wait_sec: int = 0, screenshot: bool = False):
|
||
with sync_playwright() as p:
|
||
browser = p.chromium.launch(
|
||
executable_path=CHROMIUM_PATH,
|
||
headless=True,
|
||
args=["--no-sandbox", "--disable-setuid-sandbox"]
|
||
)
|
||
page = browser.new_page(viewport={"width": 1280, "height": 720})
|
||
page.set_default_timeout(15000)
|
||
|
||
try:
|
||
page.goto(url, wait_until="domcontentloaded")
|
||
except PlaywrightTimeout:
|
||
print("⚠️ 页面加载超时，使用已获取的内容")
|
||
|
||
if wait_sec > 0:
|
||
page.wait_for_timeout(wait_sec * 1000)
|
||
|
||
title = page.title()
|
||
print(f"标题: {title}")
|
||
print(f"URL: {url}")
|
||
print()
|
||
|
||
if screenshot:
|
||
os.makedirs(SAVE_DIR, exist_ok=True)
|
||
safe_name = "".join(c if c.isalnum() or c in '-_' else '_' for c in url[:50])
|
||
path = os.path.join(SAVE_DIR, f"screenshot_{safe_name}.png")
|
||
page.screenshot(path=path, full_page=True)
|
||
print(f"📸 截图已保存: {path}")
|
||
print()
|
||
|
||
# 提取正文文字
|
||
content = page.inner_text("body")
|
||
# 清理过长的空白行
|
||
lines = [l.strip() for l in content.split("\n")]
|
||
text = "\n".join(l for l in lines if l)
|
||
|
||
if len(text) > 5000:
|
||
print(text[:5000])
|
||
print(f"\n...（内容过长，仅显示前5000字符，共{len(text)}字符）")
|
||
else:
|
||
print(text)
|
||
|
||
browser.close()
|
||
|
||
|
||
if __name__ == "__main__":
|
||
parser = argparse.ArgumentParser(description="无头浏览器工具")
|
||
parser.add_argument("url", help="要访问的网页URL")
|
||
parser.add_argument("--screenshot", action="store_true", help="截图保存")
|
||
parser.add_argument("--wait", type=int, default=0, help="等待秒数（用于JS渲染页面）")
|
||
args = parser.parse_args()
|
||
|
||
browse(args.url, wait_sec=args.wait, screenshot=args.screenshot)
|