upgrade searxng

crazy_functions/Internet_GPT.py

@@ -4,27 +4,43 @@ import requests
 from bs4 import BeautifulSoup
 from request_llms.bridge_all import model_info
 import urllib.request
+import random
 from functools import lru_cache
+from check_proxy import check_proxy
 
 @lru_cache
 def get_auth_ip():
-    try:
-        external_ip = urllib.request.urlopen('https://v4.ident.me/').read().decode('utf8')
-        return external_ip
-    except:
-        return '114.114.114.114'
+    ip = check_proxy(None, return_ip=True)
+    if ip is None:
+        return '114.114.114.' + str(random.randint(1, 10))
+    return ip
 
-def searxng_request(query, proxies, categories='general', searxng_url=None):
+def searxng_request(query, proxies, categories='general', searxng_url=None, engines=None):
     if searxng_url is None:
         url = get_conf("SEARXNG_URL")
     else:
         url = searxng_url
-    params = {
-        'q': query,         # 搜索查询
-        'format': 'json',   # 输出格式为JSON
-        'language': 'zh',   # 搜索语言
-        'categories': categories
-    }
+
+    if engines is None:
+        engines = 'bing'
+
+    if categories == 'general':
+        params = {
+            'q': query,         # 搜索查询
+            'format': 'json',   # 输出格式为JSON
+            'language': 'zh',   # 搜索语言
+            'engines': engines,
+        }
+    elif categories == 'science':
+        params = {
+            'q': query,         # 搜索查询
+            'format': 'json',   # 输出格式为JSON
+            'language': 'zh',   # 搜索语言
+            'categories': 'science'
+        }
+    else:
+        raise ValueError('不支持的检索类型')
+
     headers = {
         'Accept-Language': 'zh-CN,zh;q=0.9',
         'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36',
@@ -32,12 +48,13 @@ def searxng_request(query, proxies, categories='general', searxng_url=None):
         'X-Real-IP': get_auth_ip()
     }
     results = []
-    response = requests.post(url, params=params, headers=headers, proxies=proxies)
+    response = requests.post(url, params=params, headers=headers, proxies=proxies, timeout=30)
     if response.status_code == 200:
         json_result = response.json()
         for result in json_result['results']:
             item = {
                 "title": result.get("title", ""),
+                "source": result.get("engines", "unknown"),
                 "content": result.get("content", ""),
                 "link": result["url"],
             }
@@ -80,7 +97,7 @@ def scrape_text(url, proxies) -> str:
 def 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
 
     history = []    # 清空历史，以免输入溢出
-    chatbot.append((f"请结合互联网信息回答以下问题：{txt}", None))
+    chatbot.append((f"请结合互联网信息回答以下问题：{txt}", "检索中..."))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
 
     # ------------- < 第1步：爬取搜索引擎的结果 > -------------
@@ -88,11 +105,12 @@ def 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
     proxies = get_conf('proxies')
     categories = plugin_kwargs.get('categories', 'general')
     searxng_url = plugin_kwargs.get('searxng_url', None)
-    urls = searxng_request(txt, proxies, categories, searxng_url)
+    engines = plugin_kwargs.get('engine', None)
+    urls = searxng_request(txt, proxies, categories, searxng_url, engines=engines)
     history = []
     if len(urls) == 0:
         chatbot.append((f"结论：{txt}",
-                        "[Local Message] 受到google限制，无法从google获取信息！"))
+                        "[Local Message] 受到限制，无法从searxng获取信息！请尝试更换搜索引擎。"))
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     # ------------- < 第2步：依次访问网页 > -------------
@@ -100,9 +118,10 @@ def 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
     chatbot.append([f"联网检索中 ...", None])
     for index, url in enumerate(urls[:max_search_result]):
         res = scrape_text(url['link'], proxies)
-        history.extend([f"第{index}份搜索结果：", res])
+        prefix = f"第{index}份搜索结果 [源自{url['source'][0]}搜索] （{url['title'][:25]}）："
+        history.extend([prefix, res])
         res_squeeze = res.replace('\n', '...')
-        chatbot[-1] = [f"第{index}份搜索结果：\n\n" + res_squeeze[:500] + "......", None]
+        chatbot[-1] = [prefix + "\n\n" + res_squeeze[:500] + "......", None]
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
 
     # ------------- < 第3步：ChatGPT综合 > -------------