add yt, web

app.py

@@ -1,5 +1,8 @@
 import gradio as gr
 import pandas as pd
+import requests
+from bs4 import BeautifulSoup
+from docx import Document
 import os
 from openai import OpenAI
 import json
@@ -11,8 +14,14 @@ def process_file(file):
     # 读取文件
     if file.name.endswith('.csv'):
         df = pd.read_csv(file)
-    else:
+        text = df_to_text(df)
+    elif file.name.endswith('.xlsx'):
         df = pd.read_excel(file)
+        text = df_to_text(df)
+    elif file.name.endswith('.docx'):
+        text = docx_to_text(file)
+    else:
+        raise ValueError("Unsupported file type")
 
     df_string = df.to_string()
     # 宜蘭：移除@XX@符号 to |
@@ -29,6 +38,26 @@ def process_file(file):
            df_summarise, \
            df_string
 
+def df_to_text(df):
+    # 将 DataFrame 转换为纯文本
+    return df.to_string()
+
+def docx_to_text(file):
+    # 将 Word 文档转换为纯文本
+    doc = Document(file)
+    return "\n".join([para.text for para in doc.paragraphs])
+
+def process_youtube_link(link):
+    # 从 YouTube 链接中提取视频 ID
+    return link.split("=")[-1]
+
+def process_web_link(link):
+    # 抓取和解析网页内容
+    response = requests.get(link)
+    soup = BeautifulSoup(response.content, 'html.parser')
+    return soup.get_text()
+
+
 def generate_df_summarise(df_string):
     # 使用 OpenAI 生成基于上传数据的问题
     sys_content = "你是一個資料分析師，服務對象為老師，請精讀資料，使用 zh-TW"
@@ -131,7 +160,9 @@ def respond(user_message, df_string_output, chat_history):
 with gr.Blocks() as demo:
     with gr.Row():
         with gr.Column():
-            file_upload = gr.File(label="Upload your file")
+            file_upload = gr.File(label="Upload your CSV or Word file")
+            youtube_link = gr.Textbox(label="Enter YouTube Link")
+            web_link = gr.Textbox(label="Enter Web Page Link")
             chatbot = gr.Chatbot()
             msg = gr.Textbox(label="Message")
             send_button = gr.Button("Send")
@@ -163,6 +194,11 @@ with gr.Blocks() as demo:
     # file_upload.change(process_file, inputs=file_upload, outputs=df_string_output)
     file_upload.change(process_file, inputs=file_upload, outputs=[btn_1, btn_2, btn_3, df_summarise, df_string_output])
 
+    # 当输入 YouTube 链接时触发
+    youtube_link.change(process_youtube_link, inputs=youtube_link, outputs=[btn_1, btn_2, btn_3, df_summarise, df_string_output])
+
+    # 当输入网页链接时触发
+    web_link.change(process_web_link, inputs=web_link, outputs=[btn_1, btn_2, btn_3, df_summarise, df_string_output])
 
     
 

requirements.txt

@@ -1,3 +1,6 @@
 gradio
 pandas
-openai >= 1.0.0
+openai>=1.0.0
+requests
+beautifulsoup4
+python-docx