From d5618749c98bded847e94dd22dc1f60e964e815e Mon Sep 17 00:00:00 2001
From: H <43509927+guoyuhao2330@users.noreply.github.com>
Date: Fri, 12 Jul 2024 16:28:24 +0800
Subject: [PATCH] Fix baidusearch and duckduckgosearch (#1488)

### What problem does this PR solve?



### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
---
 graph/component/baidu.py            |  9 +++++----
 graph/component/duckduckgosearch.py | 11 ++++++-----
 2 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/graph/component/baidu.py b/graph/component/baidu.py
index 69319a8fe..5a7779553 100644
--- a/graph/component/baidu.py
+++ b/graph/component/baidu.py
@@ -53,10 +53,11 @@ class Baidu(ComponentBase, ABC):
         url_res = re.findall(r"'url': \\\"(.*?)\\\"}", response.text)
         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)]
+        baidu_res = [{"content": 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
 
-        print(baidu_res, ":::::::::::::::::::::::::::::::::")
-        return Baidu.be_output(baidu_res)
+        df = pd.DataFrame(baidu_res)
+        print(df, ":::::::::::::::::::::::::::::::::")
+
+        return df
 
diff --git a/graph/component/duckduckgosearch.py b/graph/component/duckduckgosearch.py
index 8e287bd46..8f8f20604 100644
--- a/graph/component/duckduckgosearch.py
+++ b/graph/component/duckduckgosearch.py
@@ -44,18 +44,19 @@ class DuckDuckGoSearch(ComponentBase, ABC):
         ans = self.get_input()
         ans = " - ".join(ans["content"]) if "content" in ans else ""
         if not ans:
-            return Baidu.be_output(self._param.no)
+            return DuckDuckGoSearch.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
+                duck_res = [{"content": '<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
+                duck_res = [{"content": '<a href="' + i["url"] + '">' + i["title"] + '</a>    ' + i["body"]} for i in
                             ddgs.news(ans, max_results=self._param.top_n)]
 
-        print(duck_res, ":::::::::::::::::::::::::::::::::")
-        return DuckDuckGoSearch.be_output(duck_res)
\ No newline at end of file
+        df = pd.DataFrame(duck_res)
+        print(df, ":::::::::::::::::::::::::::::::::")
+        return df