Spaces:
Running
Running
Commit
·
1e479c7
1
Parent(s):
8ec4ba9
更新 README.md 和 app.py,新增功能與錯誤處理,改善使用者體驗
Browse files- README.md +27 -5
- __pycache__/app.cpython-311.pyc +0 -0
- app.py +36 -15
README.md
CHANGED
|
@@ -1,12 +1,34 @@
|
|
| 1 |
-
---
|
| 2 |
title: Hg Markitdown
|
| 3 |
-
emoji:
|
| 4 |
-
colorFrom:
|
| 5 |
-
colorTo:
|
| 6 |
sdk: gradio
|
| 7 |
sdk_version: 5.25.0
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
---
|
| 11 |
|
| 12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
title: Hg Markitdown
|
| 2 |
+
emoji: �
|
| 3 |
+
colorFrom: blue
|
| 4 |
+
colorTo: green
|
| 5 |
sdk: gradio
|
| 6 |
sdk_version: 5.25.0
|
| 7 |
app_file: app.py
|
| 8 |
pinned: false
|
| 9 |
---
|
| 10 |
|
| 11 |
+
# MarkItDown 檔案轉 Markdown 工具
|
| 12 |
+
|
| 13 |
+
這個專案提供一個基於 Gradio 的網頁介面,支援拖放或選取檔案(PDF、Word、Excel、PowerPoint、圖片、音訊等)並自動轉換為 Markdown 內容,方便快速複製使用。
|
| 14 |
+
|
| 15 |
+
## 功能特色
|
| 16 |
+
|
| 17 |
+
- 支援拖曳或選擇檔案即時轉換
|
| 18 |
+
- 轉換結果以 Markdown 元件呈現,支援語法高亮
|
| 19 |
+
- 內建複製按鈕,可一鍵複製轉換後內容
|
| 20 |
+
- 可手動按「開始轉換」重新觸發、更新結果
|
| 21 |
+
|
| 22 |
+
## 執行方式
|
| 23 |
+
|
| 24 |
+
```bash
|
| 25 |
+
pip install -r requirements.txt
|
| 26 |
+
python app.py
|
| 27 |
+
```
|
| 28 |
+
|
| 29 |
+
執行後於終端機顯示的網址(預設 http://127.0.0.1:7860/)即可打開網頁並進行檔案上傳轉換。
|
| 30 |
+
|
| 31 |
+
## 注意事項
|
| 32 |
+
|
| 33 |
+
- 請確認已安裝 `markitdown[all]` 所需的系統依賴與 NLP 模型。
|
| 34 |
+
- 若遇到特定檔案格式無法解析,請檢查檔案是否完整、未加密,或參考 MarkItDown 官方文件取得額外支援。
|
__pycache__/app.cpython-311.pyc
ADDED
|
Binary file (1.55 kB). View file
|
|
|
app.py
CHANGED
|
@@ -1,26 +1,47 @@
|
|
| 1 |
import gradio as gr
|
| 2 |
from markitdown import MarkItDown
|
| 3 |
-
import os
|
| 4 |
-
import shutil
|
| 5 |
-
from uuid import uuid4
|
| 6 |
|
| 7 |
md = MarkItDown()
|
| 8 |
|
| 9 |
-
def convert_file_to_md(
|
|
|
|
|
|
|
|
|
|
| 10 |
try:
|
| 11 |
-
result = md.convert(
|
| 12 |
-
content = result.text_content
|
| 13 |
except Exception as e:
|
| 14 |
content = f"❌ 轉換失敗:{str(e)}"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
return content
|
| 16 |
|
| 17 |
-
demo = gr.Interface(
|
| 18 |
-
fn=convert_file_to_md,
|
| 19 |
-
inputs=gr.File(label="上傳支援格式檔案(如 PDF、Word、Excel 等)"),
|
| 20 |
-
outputs=gr.Textbox(label="轉換後的 Markdown 結果", lines=25),
|
| 21 |
-
title="📄 MarkItDown 文件轉 Markdown 線上工具",
|
| 22 |
-
description="上傳你的檔案,我們將自動轉換為 Markdown 格式內容,支援 PDF、Word、Excel、PowerPoint、圖片、音訊等格式。",
|
| 23 |
-
allow_flagging="never" # ← 加這行就不會出現 Flag 按鈕了
|
| 24 |
-
)
|
| 25 |
|
| 26 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
import gradio as gr
|
| 2 |
from markitdown import MarkItDown
|
|
|
|
|
|
|
|
|
|
| 3 |
|
| 4 |
md = MarkItDown()
|
| 5 |
|
| 6 |
+
def convert_file_to_md(file_path: str) -> str:
|
| 7 |
+
if not file_path:
|
| 8 |
+
return "⚠️ 未收到檔案,請重新上傳。"
|
| 9 |
+
|
| 10 |
try:
|
| 11 |
+
result = md.convert(file_path)
|
| 12 |
+
content = result.text_content or ""
|
| 13 |
except Exception as e:
|
| 14 |
content = f"❌ 轉換失敗:{str(e)}"
|
| 15 |
+
|
| 16 |
+
if not content.strip():
|
| 17 |
+
return "ℹ️ 轉換完成,但沒有可顯示的 Markdown 內容。"
|
| 18 |
+
|
| 19 |
return content
|
| 20 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
+
with gr.Blocks(title="📄 MarkItDown 文件轉 Markdown 線上工具") as demo:
|
| 23 |
+
gr.Markdown("""
|
| 24 |
+
## 📄 MarkItDown 文件轉 Markdown
|
| 25 |
+
上傳支援格式檔案,系統會自動轉換為 Markdown 內容。也可以按下「開始轉換」手動觸發。
|
| 26 |
+
""")
|
| 27 |
+
|
| 28 |
+
with gr.Row():
|
| 29 |
+
file_input = gr.File(
|
| 30 |
+
label="拖曳或選擇支援格式檔案(PDF、Word、Excel、PowerPoint、圖片、音訊等)",
|
| 31 |
+
file_count="single",
|
| 32 |
+
type="filepath",
|
| 33 |
+
)
|
| 34 |
+
convert_button = gr.Button("開始轉換", variant="primary")
|
| 35 |
+
|
| 36 |
+
gr.Markdown("### 轉換後的 Markdown 結果")
|
| 37 |
+
output = gr.Markdown(
|
| 38 |
+
value="請上傳或轉換檔案,結果將顯示於此。",
|
| 39 |
+
show_copy_button=True,
|
| 40 |
+
)
|
| 41 |
+
|
| 42 |
+
file_input.upload(convert_file_to_md, inputs=file_input, outputs=output)
|
| 43 |
+
convert_button.click(convert_file_to_md, inputs=file_input, outputs=output)
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
if __name__ == "__main__":
|
| 47 |
+
demo.launch()
|