Duckduckgosearch

graph/component/__init__.py

@@ -10,6 +10,7 @@
 from .rewrite import RewriteQuestion, RewriteQuestionParam
 from .keyword import KeywordExtract, KeywordExtractParam
 from .baidu import Baidu, BaiduParam
+from .duckduckgosearch import DuckDuckGoSearch, DuckDuckGoSearchParam
 
 
 def component_class(class_name):

graph/component/baidu.py

@@ -50,12 +50,12 @@ def _run(self, history, **kwargs):
             'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.104 Safari/537.36'}
         response = requests.get(url=url, headers=headers)
 
-        baidu_res = re.findall(r'"contentText":"(.*?)"', response.text)
         url_res = re.findall(r"'url': \\\"(.*?)\\\"}", response.text)
-        for i in range(min(len(baidu_res), len(url_res))):
-            baidu_res[i] += '<a>' + url_res[i] + '</a>'
-
-        del url_res
+        title_res = re.findall(r"'title': \\\"(.*?)\\\",\\n", response.text)
+        body_res = re.findall(r"\"contentText\":\"(.*?)\"", response.text)
+        baidu_res = [re.sub('<em>|</em>', '', '<a href="' + url + '">' + title + '</a>    ' + body) for url, title, body
+                     in zip(url_res, title_res, body_res)]
+        del body_res, url_res, title_res
 
         br = pd.DataFrame(baidu_res, columns=['content'])
         print(">>>>>>>>>>>>>>>>>>>>>>>>>>\n", br)

graph/component/duckduckgosearch.py

@@ -0,0 +1,62 @@
+#
+#  Copyright 2024 The InfiniFlow Authors. All Rights Reserved.
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+#
+import random
+from abc import ABC
+from functools import partial
+from duckduckgosearch import DDGS
+import pandas as pd
+
+from graph.component.base import ComponentBase, ComponentParamBase
+
+
+class DuckDuckGoSearchParam(ComponentParamBase):
+    """
+    Define the DuckDuckGoSearch component parameters.
+    """
+
+    def __init__(self):
+        super().__init__()
+        self.top_n = 10
+        self.channel = "text"
+
+    def check(self):
+        self.check_positive_integer(self.top_n, "Top N")
+        self.check_valid_value(self.channel, "Web Search or News", ["text", "news"])
+
+
+class DuckDuckGoSearch(ComponentBase, ABC):
+    component_name = "DuckDuckGoSearch"
+
+    def _run(self, history, **kwargs):
+        ans = self.get_input()
+        ans = " - ".join(ans["content"]) if "content" in ans else ""
+        if not ans:
+            return Baidu.be_output(self._param.no)
+
+        if self.channel == "text":
+            with DDGS() as ddgs:
+                # {'title': '', 'href': '', 'body': ''}
+                duck_res = ['<a href="' + i["href"] + '">' + i["title"] + '</a>    ' + i["body"] for i in
+                            ddgs.text(ans, max_results=self._param.top_n)]
+        elif self.channel == "news":
+            with DDGS() as ddgs:
+                # {'date': '', 'title': '', 'body': '', 'url': '', 'image': '', 'source': ''}
+                duck_res = ['<a href="' + i["url"] + '">' + i["title"] + '</a>    ' + i["body"] for i in
+                            ddgs.news(ans, max_results=self._param.top_n)]
+
+        dr = pd.DataFrame(duck_res, columns=['content'])
+        print(">>>>>>>>>>>>>>>>>>>>>>>>>>\n", dr)
+        return dr