Spaces:
Sleeping
Sleeping
Upload folder using huggingface_hub
Browse files- app.py +29 -0
- apps/pdf_cropper.py +58 -0
- apps/text_tools.py +16 -0
- requirements.txt +4 -0
app.py
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import gradio as gr
|
| 2 |
+
from apps import pdf_cropper, text_tools
|
| 3 |
+
|
| 4 |
+
# --- 主程序入口 ---
|
| 5 |
+
# 这里是“应用集市”的容器。
|
| 6 |
+
# 每次添加新工具,只需要 import 进来,并在 tab_list 中注册即可。
|
| 7 |
+
|
| 8 |
+
def create_main_interface():
|
| 9 |
+
with gr.Blocks(title="我的科研工具箱", theme=gr.themes.Soft()) as main_app:
|
| 10 |
+
gr.Markdown("# 🛠️ 科研效率工具箱")
|
| 11 |
+
|
| 12 |
+
# 使用 Tab 布局来切换不同的工具
|
| 13 |
+
with gr.Tabs():
|
| 14 |
+
|
| 15 |
+
# --- 工具 1: PDF 智能裁边 ---
|
| 16 |
+
with gr.TabItem("📄 PDF 裁边"):
|
| 17 |
+
pdf_cropper.create_ui()
|
| 18 |
+
|
| 19 |
+
# --- 工具 2: 文本分析 (示例) ---
|
| 20 |
+
with gr.TabItem("📝 文本统计"):
|
| 21 |
+
text_tools.create_ui()
|
| 22 |
+
|
| 23 |
+
# --- 可以在这里继续添加更多 Tab ---
|
| 24 |
+
|
| 25 |
+
return main_app
|
| 26 |
+
|
| 27 |
+
if __name__ == "__main__":
|
| 28 |
+
app = create_main_interface()
|
| 29 |
+
app.launch(inbrowser=True)
|
apps/pdf_cropper.py
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import gradio as gr
|
| 2 |
+
from PIL import Image, ImageChops
|
| 3 |
+
import img2pdf
|
| 4 |
+
import io
|
| 5 |
+
|
| 6 |
+
# --- 核心逻辑 (复用之前的代码) ---
|
| 7 |
+
def trim_whitespace(im, fuzz_level=20):
|
| 8 |
+
bg = Image.new(im.mode, im.size, (255, 255, 255))
|
| 9 |
+
diff = ImageChops.difference(im, bg)
|
| 10 |
+
diff = ImageChops.add(diff, diff, 1, -fuzz_level)
|
| 11 |
+
bbox = diff.getbbox()
|
| 12 |
+
if bbox:
|
| 13 |
+
return im.crop(bbox)
|
| 14 |
+
return im
|
| 15 |
+
|
| 16 |
+
def process_pipeline(files, quality, fuzz_level, progress=gr.Progress()):
|
| 17 |
+
if not files: return None
|
| 18 |
+
pdf_components = []
|
| 19 |
+
for filepath in progress.tqdm(files, desc="处理中"):
|
| 20 |
+
try:
|
| 21 |
+
with Image.open(filepath) as img:
|
| 22 |
+
if img.mode in ('RGBA', 'LA') or (img.mode == 'P' and 'transparency' in img.info):
|
| 23 |
+
bg = Image.new('RGB', img.size, (255, 255, 255))
|
| 24 |
+
if img.mode!= 'RGBA': img = img.convert('RGBA')
|
| 25 |
+
bg.paste(img, mask=img.split()[3])
|
| 26 |
+
img = bg
|
| 27 |
+
else:
|
| 28 |
+
img = img.convert('RGB')
|
| 29 |
+
|
| 30 |
+
trimmed = trim_whitespace(img, fuzz_level)
|
| 31 |
+
byte_arr = io.BytesIO()
|
| 32 |
+
trimmed.save(byte_arr, format='JPEG', quality=int(quality))
|
| 33 |
+
pdf_components.append(byte_arr.getvalue())
|
| 34 |
+
except Exception: continue
|
| 35 |
+
|
| 36 |
+
if not pdf_components: return None
|
| 37 |
+
output_filename = "output_document.pdf"
|
| 38 |
+
with open(output_filename, "wb") as f:
|
| 39 |
+
f.write(img2pdf.convert(pdf_components))
|
| 40 |
+
return output_filename
|
| 41 |
+
|
| 42 |
+
# --- 模块化 UI 接口 ---
|
| 43 |
+
def create_ui():
|
| 44 |
+
"""
|
| 45 |
+
每个工具模块都需要暴露这个函数。
|
| 46 |
+
注意:不要在这里创建 gr.Blocks(),直接写 Row/Column 即可,
|
| 47 |
+
因为它们会被嵌入到主程序的 Tab 中。
|
| 48 |
+
"""
|
| 49 |
+
with gr.Row():
|
| 50 |
+
with gr.Column():
|
| 51 |
+
file_input = gr.File(file_count="multiple", file_types=["image"], label="上传图片")
|
| 52 |
+
quality = gr.Slider(10, 100, 90, label="质量")
|
| 53 |
+
fuzz = gr.Slider(0, 100, 30, label="容差")
|
| 54 |
+
btn = gr.Button("开始处理", variant="primary")
|
| 55 |
+
with gr.Column():
|
| 56 |
+
output = gr.File(label="下载 PDF")
|
| 57 |
+
|
| 58 |
+
btn.click(process_pipeline, [file_input, quality, fuzz], output)
|
apps/text_tools.py
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import gradio as gr
|
| 2 |
+
|
| 3 |
+
def analyze_text(text):
|
| 4 |
+
return {
|
| 5 |
+
"字符数": len(text),
|
| 6 |
+
"单词数 (空格分隔)": len(text.split()),
|
| 7 |
+
"行数": len(text.splitlines())
|
| 8 |
+
}
|
| 9 |
+
|
| 10 |
+
def create_ui():
|
| 11 |
+
with gr.Row():
|
| 12 |
+
inp = gr.Textbox(lines=5, label="输入文本")
|
| 13 |
+
out = gr.JSON(label="统计结果")
|
| 14 |
+
|
| 15 |
+
btn = gr.Button("分析")
|
| 16 |
+
btn.click(analyze_text, inp, out)
|
requirements.txt
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
gradio
|
| 2 |
+
Pillow
|
| 3 |
+
img2pdf
|
| 4 |
+
huggingface_hub
|