实现浏览器方式互联网搜索功能
- 使用 agent-browser 浏览器自动化进行 Bing 搜索 - 解析 accessibility tree 提取搜索结果 - 自动获取每个结果的 URL - 支持设置最大结果数量
This commit is contained in:
+133
-5
@@ -4,6 +4,10 @@
|
||||
import requests
|
||||
from bs4 import BeautifulSoup
|
||||
import json
|
||||
import subprocess
|
||||
import os
|
||||
import re
|
||||
import urllib.parse
|
||||
from datetime import datetime
|
||||
from config import Config
|
||||
from models.database import db
|
||||
@@ -13,19 +17,143 @@ class SearchService:
|
||||
self.timeout = Config.SEARCH_TIMEOUT
|
||||
self.max_results = Config.SEARCH_MAX_RESULTS
|
||||
|
||||
def _run_browser(self, *args, timeout=30000):
|
||||
"""运行 agent-browser 命令"""
|
||||
env = os.environ.copy()
|
||||
env['XDG_RUNTIME_DIR'] = '/tmp/agent-browser-runtime'
|
||||
os.makedirs(env['XDG_RUNTIME_DIR'], exist_ok=True)
|
||||
|
||||
cmd = ['agent-browser'] + list(args)
|
||||
result = subprocess.run(
|
||||
cmd,
|
||||
capture_output=True,
|
||||
text=True,
|
||||
env=env,
|
||||
timeout=timeout // 1000 + 5
|
||||
)
|
||||
return result.stdout, result.stderr, result.returncode
|
||||
|
||||
def search_internet(self, keyword, max_results=None):
|
||||
"""
|
||||
从互联网搜索(使用搜索API或爬虫)
|
||||
这里暂时使用简单的搜索模拟
|
||||
从互联网搜索(使用 agent-browser 浏览器自动化)
|
||||
"""
|
||||
max_results = max_results or self.max_results
|
||||
|
||||
# TODO: 接入真实的搜索API(如Google Custom Search、Bing等)
|
||||
# 这里先返回空列表,等待后续接入真实API
|
||||
results = []
|
||||
|
||||
try:
|
||||
# 1. 打开 Bing 搜索
|
||||
encoded_keyword = urllib.parse.quote(keyword)
|
||||
search_url = f"https://www.bing.com/search?q={encoded_keyword}"
|
||||
|
||||
stdout, stderr, code = self._run_browser('open', search_url, '--timeout', '20000')
|
||||
if code != 0:
|
||||
print(f"打开搜索页面失败: {stderr}")
|
||||
return results
|
||||
|
||||
# 等待页面加载
|
||||
stdout, stderr, code = self._run_browser('wait', '5000')
|
||||
|
||||
# 2. 获取搜索结果页面结构 (JSON 格式)
|
||||
stdout, stderr, code = self._run_browser('snapshot', '--json', '--timeout', '30000')
|
||||
if code != 0:
|
||||
print(f"获取页面结构失败: {stderr}")
|
||||
return results
|
||||
|
||||
# 3. 解析 JSON 提取搜索结果
|
||||
try:
|
||||
data = json.loads(stdout)
|
||||
except json.JSONDecodeError:
|
||||
print(f"解析 JSON 失败: {stdout[:500]}")
|
||||
return results
|
||||
|
||||
# 4. 从 accessibility tree 中提取搜索结果
|
||||
# Bing 搜索结果在 main[aria-label="搜索结果"] 区域内
|
||||
results = self._parse_bing_results(data, max_results)
|
||||
|
||||
# 5. 关闭浏览器
|
||||
self._run_browser('close')
|
||||
|
||||
except subprocess.TimeoutExpired:
|
||||
print(f"搜索超时: {keyword}")
|
||||
except Exception as e:
|
||||
print(f"搜索出错: {str(e)}")
|
||||
# 尝试关闭浏览器
|
||||
try:
|
||||
self._run_browser('close')
|
||||
except:
|
||||
pass
|
||||
|
||||
return results
|
||||
|
||||
def _parse_bing_results(self, snapshot_data, max_results=10):
|
||||
"""
|
||||
从 Bing 搜索结果的 snapshot 中解析出标题和链接
|
||||
|
||||
snapshot_data 是 agent-browser snapshot --json 的输出
|
||||
结构: {success, data: {snapshot: "文本格式的 accessibility tree"}, error}
|
||||
"""
|
||||
results = []
|
||||
|
||||
# 获取 snapshot 文本
|
||||
snapshot = snapshot_data.get('data', {}).get('snapshot', '')
|
||||
if not snapshot:
|
||||
return results
|
||||
|
||||
# 解析 accessibility tree 文本
|
||||
in_results = False
|
||||
refs = [] # 存储 (title, ref) 元组
|
||||
lines = snapshot.split('\n')
|
||||
|
||||
for i, line in enumerate(lines):
|
||||
line = line.strip()
|
||||
|
||||
# 进入搜索结果区域
|
||||
if 'main "搜索结果"' in line:
|
||||
in_results = True
|
||||
continue
|
||||
|
||||
# 离开搜索结果区域
|
||||
if in_results and line.startswith('- ') and 'main' in line and '搜索结果' not in line:
|
||||
break
|
||||
|
||||
if not in_results:
|
||||
continue
|
||||
|
||||
# 匹配标题链接:link "标题文字" [ref=eXX]
|
||||
# 需要过滤域名链接(如 "zhihu.com")和短链接
|
||||
if 'link "' in line and '[ref=' in line:
|
||||
match = re.search(r'link "([^"]+)" \[ref=(e\d+)\]', line)
|
||||
if match:
|
||||
title = match.group(1)
|
||||
ref = match.group(2)
|
||||
# 过滤短标题(域名链接如 "zhihu.com")
|
||||
if len(title) > 20 and '.' not in title[:10]: # 不是域名格式
|
||||
refs.append((title, ref))
|
||||
|
||||
# 获取每个结果的 URL
|
||||
for title, ref in refs[:max_results]:
|
||||
url = self._get_link_url(ref)
|
||||
if url and 'bing.com/search' not in url: # 过滤搜索结果页本身的链接
|
||||
results.append({
|
||||
'title': title,
|
||||
'url': url,
|
||||
'snippet': '',
|
||||
'source': 'bing'
|
||||
})
|
||||
|
||||
return results
|
||||
|
||||
def _get_link_url(self, ref):
|
||||
"""通过 agent-browser 获取链接的 URL"""
|
||||
try:
|
||||
stdout, stderr, code = self._run_browser('get', 'attr', f'@{ref}', 'href', '--json', '--timeout', '5000')
|
||||
if code == 0 and stdout:
|
||||
data = json.loads(stdout)
|
||||
return data.get('data', {}).get('value', '')
|
||||
except Exception as e:
|
||||
print(f"获取 URL 失败 (ref={ref}): {e}")
|
||||
return None
|
||||
|
||||
def fetch_url_content(self, url):
|
||||
"""抓取网页内容"""
|
||||
try:
|
||||
|
||||
Reference in New Issue
Block a user