chatgpt-mirai-qq-bot-web-search 0.2.7__py3-none-any.whl → 0.2.9__py3-none-any.whl

{chatgpt_mirai_qq_bot_web_search-0.2.7.dist-info → chatgpt_mirai_qq_bot_web_search-0.2.9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: chatgpt-mirai-qq-bot-web-search
-Version: 0.2.7
+Version: 0.2.9
 Summary: WebSearch adapter for lss233/chatgpt-mirai-qq-bot
 Home-page: https://github.com/chuanSir123/web_search
 Author: chuanSir

{chatgpt_mirai_qq_bot_web_search-0.2.7.dist-info → chatgpt_mirai_qq_bot_web_search-0.2.9.dist-info}/RECORD

@@ -1,11 +1,11 @@
 web_search/__init__.py,sha256=bpu1gpf9tq3mOAoaGMM-8S6GBw2GzRAG6ClHGlp-CVw,4607
 web_search/blocks.py,sha256=QuXt3KMuY4hUW-ucleNYXFvW6YbUAB4Xu4m_SxdCd-U,9152
 web_search/config.py,sha256=DhLiERBJR2V5Boglf7Aq9Rbc4vsvLIh67CrLDIPeqA0,398
-web_search/web_searcher.py,sha256=Bgnc0HGXZkMULZ5BWCJxBUzLFew19LuTL7lmdeqmfWs,21384
+web_search/web_searcher.py,sha256=wjhe6vqhnPvxhK4ssvmCAjvefQP6iE_7CpyhhHdY4a8,21813
 web_search/example/roleplayWithWebSearch.yaml,sha256=C-dGy3z8gcRcmxzurssP-kPRLqMf1TYR-nnNUaJjISE,7468
-chatgpt_mirai_qq_bot_web_search-0.2.7.dist-info/LICENSE,sha256=ILBn-G3jdarm2w8oOrLmXeJNU3czuJvVhDLBASWdhM8,34522
-chatgpt_mirai_qq_bot_web_search-0.2.7.dist-info/METADATA,sha256=88N33AlLdzPyW0GtLU8eDH0qGEKbqmHpl0UYooIU2-E,1734
-chatgpt_mirai_qq_bot_web_search-0.2.7.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-chatgpt_mirai_qq_bot_web_search-0.2.7.dist-info/entry_points.txt,sha256=o3kRDSdSmSdnCKlK6qS57aN0WpI4ab-Nxub2NwUrjf0,64
-chatgpt_mirai_qq_bot_web_search-0.2.7.dist-info/top_level.txt,sha256=PoNm8MJYw_y8RTMaNlY0ePLoNHxVUAE2IHDuL5fFubI,11
-chatgpt_mirai_qq_bot_web_search-0.2.7.dist-info/RECORD,,
+chatgpt_mirai_qq_bot_web_search-0.2.9.dist-info/LICENSE,sha256=ILBn-G3jdarm2w8oOrLmXeJNU3czuJvVhDLBASWdhM8,34522
+chatgpt_mirai_qq_bot_web_search-0.2.9.dist-info/METADATA,sha256=KeMLPnusHjs43C7z7zS-ImyZH5KVVWWuIIMhBzKNuVs,1734
+chatgpt_mirai_qq_bot_web_search-0.2.9.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+chatgpt_mirai_qq_bot_web_search-0.2.9.dist-info/entry_points.txt,sha256=o3kRDSdSmSdnCKlK6qS57aN0WpI4ab-Nxub2NwUrjf0,64
+chatgpt_mirai_qq_bot_web_search-0.2.9.dist-info/top_level.txt,sha256=PoNm8MJYw_y8RTMaNlY0ePLoNHxVUAE2IHDuL5fFubI,11
+chatgpt_mirai_qq_bot_web_search-0.2.9.dist-info/RECORD,,

web_search/web_searcher.py

@@ -31,7 +31,7 @@ class WebSearcher:
         self.video_ids = self._load_video_ids()
         self.search_engines = {
             'bing': {
-                'url': 'https://www.bing.com/search?q={}',
+                'url': 'https://cn.bing.com/search?q={}',
                 'selectors': ['.b_algo', '#b_results .b_algo', 'main .b_algo'],
                 'title_selector': 'h2',
                 'link_selector': 'h2 a',
@@ -163,9 +163,9 @@ class WebSearcher:
             # 创建新标签页获取内容
             page = await context.new_page()
             try:
-                # 设置更严格的资源加载策略
+                # 修改资源加载策略，允许加载必要的CSS
                 await page.route("**/*", lambda route: route.abort()
-                    if route.request.resource_type in ['image', 'stylesheet', 'font', 'media']
+                    if route.request.resource_type in ['image', 'font', 'media']  # 移除 'stylesheet'
                     else route.continue_())
 
                 # 使用 domcontentloaded 而不是 networkidle
@@ -263,22 +263,25 @@ class WebSearcher:
 
             # 使用搜索引擎特定的选择器
             results = None
+            # 等待页面稳定
+            await asyncio.sleep(2)  # 添加短暂延迟
 
             # 对于Google，让页面有更多时间加载
             if engine == 'google':
                 await self.simulate_human_scroll(page)
 
-            timeout = 5000
+            selector_timeout = 5000
             for selector in engine_config['selectors']:
                 try:
                     logger.info(f"Trying selector: {selector}")
-                    await page.wait_for_selector(selector, timeout=timeout)  # 增加等待时间
-                    timeout = 500
+                    await page.wait_for_selector(selector, timeout=selector_timeout)  # 增加等待时间
+                    selector_timeout = 500
                     results = await page.query_selector_all(selector)
                     if results and len(results) > 0:
                         logger.info(f"Found {len(results)} results with selector {selector}")
                         break
                 except Exception as e:
+                    selector_timeout = 500
                     logger.warning(f"Selector {selector} failed: {e}")
                     continue
 
@@ -288,21 +291,26 @@ class WebSearcher:
                 while not results and retry_count < max_results:
                     logger.info(f"Retrying search, attempt {retry_count + 1}/{max_results}")
                     # 刷新页面重试
-                    await page.reload(wait_until='load', timeout=timeout * 1000)
+                    await page.goto(
+                                engine_config['url'].format(encoded_query),
+                                wait_until='load',
+                                timeout=timeout * 1000
+                            )
                     await self.simulate_human_scroll(page)
 
                     # 重新尝试所有选择器
-                    timeout = 5000
+                    selector_timeout = 5000
                     for selector in engine_config['selectors']:
                         try:
                             logger.info(f"Retrying selector: {selector}")
-                            await page.wait_for_selector(selector, timeout=timeout)
-                            timeout = 500
+                            await page.wait_for_selector(selector, timeout=selector_timeout)
+                            selector_timeout = 500
                             results = await page.query_selector_all(selector)
                             if results and len(results) > 0:
                                 logger.info(f"Found {len(results)} results with selector {selector} on retry {retry_count + 1}")
                                 break
                         except Exception as e:
+                            selector_timeout = 500
                             logger.warning(f"Selector {selector} failed on retry {retry_count + 1}: {e}")
                             continue