Spaces:
Sleeping
Sleeping
gth commited on
Commit ·
038cc08
0
Parent(s):
init
Browse files- README.md +60 -0
- app.py +162 -0
- requirements.txt +4 -0
README.md
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Document Converter Pro
|
| 2 |
+
|
| 3 |
+
Une application web moderne et efficace pour convertir vos documents dans différents formats.
|
| 4 |
+
|
| 5 |
+
## Fonctionnalités
|
| 6 |
+
|
| 7 |
+
- Interface utilisateur intuitive et ergonomique
|
| 8 |
+
- Support de multiples formats de documents
|
| 9 |
+
- Conversion rapide et efficace
|
| 10 |
+
- Gestion des erreurs robuste
|
| 11 |
+
|
| 12 |
+
## Installation
|
| 13 |
+
|
| 14 |
+
1. Clonez ce dépôt :
|
| 15 |
+
```bash
|
| 16 |
+
git clone <repository-url>
|
| 17 |
+
cd convert-anything
|
| 18 |
+
```
|
| 19 |
+
|
| 20 |
+
2. Installez les dépendances :
|
| 21 |
+
```bash
|
| 22 |
+
pip install -r requirements.txt
|
| 23 |
+
```
|
| 24 |
+
|
| 25 |
+
## Utilisation
|
| 26 |
+
|
| 27 |
+
1. Lancez l'application :
|
| 28 |
+
```bash
|
| 29 |
+
python app.py
|
| 30 |
+
```
|
| 31 |
+
|
| 32 |
+
2. Ouvrez votre navigateur et accédez à l'URL locale affichée dans le terminal
|
| 33 |
+
|
| 34 |
+
3. Utilisez l'interface pour :
|
| 35 |
+
- Télécharger votre document
|
| 36 |
+
- Sélectionner le format de sortie souhaité
|
| 37 |
+
- Cliquer sur "Convert Document"
|
| 38 |
+
- Télécharger le document converti
|
| 39 |
+
|
| 40 |
+
## Formats supportés
|
| 41 |
+
|
| 42 |
+
### Documents
|
| 43 |
+
- PDF
|
| 44 |
+
- DOCX
|
| 45 |
+
- DOC
|
| 46 |
+
- ODT
|
| 47 |
+
- RTF
|
| 48 |
+
- TXT
|
| 49 |
+
|
| 50 |
+
### Images
|
| 51 |
+
- PNG
|
| 52 |
+
- JPEG
|
| 53 |
+
- TIFF
|
| 54 |
+
- BMP
|
| 55 |
+
|
| 56 |
+
## Technologies utilisées
|
| 57 |
+
|
| 58 |
+
- Gradio : Interface utilisateur web
|
| 59 |
+
- Docling : Moteur de conversion de documents
|
| 60 |
+
- Python-Magic : Détection des types de fichiers
|
app.py
ADDED
|
@@ -0,0 +1,162 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import gradio as gr
|
| 2 |
+
import tempfile
|
| 3 |
+
import os
|
| 4 |
+
import json
|
| 5 |
+
import yaml
|
| 6 |
+
from pathlib import Path
|
| 7 |
+
from docling.datamodel.base_models import InputFormat
|
| 8 |
+
from docling.datamodel.pipeline_options import (
|
| 9 |
+
PdfPipelineOptions,
|
| 10 |
+
TesseractCliOcrOptions
|
| 11 |
+
)
|
| 12 |
+
from docling.document_converter import (
|
| 13 |
+
DocumentConverter,
|
| 14 |
+
PdfFormatOption,
|
| 15 |
+
WordFormatOption
|
| 16 |
+
)
|
| 17 |
+
from docling.pipeline.standard_pdf_pipeline import StandardPdfPipeline
|
| 18 |
+
from docling.pipeline.simple_pipeline import SimplePipeline
|
| 19 |
+
from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
|
| 20 |
+
|
| 21 |
+
# Initialize the document converter with advanced options
|
| 22 |
+
doc_converter = DocumentConverter(
|
| 23 |
+
allowed_formats=[
|
| 24 |
+
InputFormat.PDF,
|
| 25 |
+
InputFormat.IMAGE,
|
| 26 |
+
InputFormat.DOCX,
|
| 27 |
+
InputFormat.HTML,
|
| 28 |
+
InputFormat.PPTX,
|
| 29 |
+
InputFormat.ASCIIDOC,
|
| 30 |
+
InputFormat.MD,
|
| 31 |
+
InputFormat.XLSX,
|
| 32 |
+
],
|
| 33 |
+
format_options={
|
| 34 |
+
InputFormat.PDF: PdfFormatOption(
|
| 35 |
+
pipeline_cls=StandardPdfPipeline,
|
| 36 |
+
backend=PyPdfiumDocumentBackend,
|
| 37 |
+
pipeline_options=PdfPipelineOptions(
|
| 38 |
+
do_ocr=True,
|
| 39 |
+
ocr_options=TesseractCliOcrOptions(lang=["auto"])
|
| 40 |
+
)
|
| 41 |
+
),
|
| 42 |
+
InputFormat.DOCX: WordFormatOption(
|
| 43 |
+
pipeline_cls=SimplePipeline
|
| 44 |
+
),
|
| 45 |
+
}
|
| 46 |
+
)
|
| 47 |
+
|
| 48 |
+
def convert_document(input_file, output_format):
|
| 49 |
+
try:
|
| 50 |
+
# Get the input file path
|
| 51 |
+
temp_dir = tempfile.mkdtemp()
|
| 52 |
+
input_path = Path(input_file.name)
|
| 53 |
+
|
| 54 |
+
# Generate output path
|
| 55 |
+
output_filename = f"converted_document.{output_format.lower()}"
|
| 56 |
+
output_path = Path(temp_dir) / output_filename
|
| 57 |
+
|
| 58 |
+
# Convert the document
|
| 59 |
+
result = doc_converter.convert(str(input_path))
|
| 60 |
+
|
| 61 |
+
# Export to desired format
|
| 62 |
+
if output_format.lower() == "html":
|
| 63 |
+
with open(output_path, "w", encoding="utf-8") as f:
|
| 64 |
+
f.write(result.document.export_to_html())
|
| 65 |
+
elif output_format.lower() == "text":
|
| 66 |
+
with open(output_path, "w", encoding="utf-8") as f:
|
| 67 |
+
f.write(result.document.export_to_text())
|
| 68 |
+
elif output_format.lower() in ["md", "markdown"]:
|
| 69 |
+
with open(output_path, "w", encoding="utf-8") as f:
|
| 70 |
+
f.write(result.document.export_to_markdown())
|
| 71 |
+
elif output_format.lower() == "json":
|
| 72 |
+
with open(output_path, "w", encoding="utf-8") as f:
|
| 73 |
+
json.dump(result.document.export_to_dict(), f, indent=2)
|
| 74 |
+
elif output_format.lower() == "yaml":
|
| 75 |
+
with open(output_path, "w", encoding="utf-8") as f:
|
| 76 |
+
yaml.safe_dump(result.document.export_to_dict(), f)
|
| 77 |
+
elif output_format.lower() == "doctags":
|
| 78 |
+
with open(output_path, "w", encoding="utf-8") as f:
|
| 79 |
+
f.write(result.document.export_to_document_tokens())
|
| 80 |
+
else:
|
| 81 |
+
raise ValueError(f"Format de sortie non supporté: {output_format}")
|
| 82 |
+
|
| 83 |
+
return str(output_path)
|
| 84 |
+
except Exception as e:
|
| 85 |
+
return f"Erreur lors de la conversion: {str(e)}"
|
| 86 |
+
|
| 87 |
+
# Define available formats
|
| 88 |
+
SUPPORTED_OUTPUT_FORMATS = [
|
| 89 |
+
"HTML", "Markdown", "JSON", "Text", "YAML", "Doctags"
|
| 90 |
+
]
|
| 91 |
+
|
| 92 |
+
# Create the Gradio interface
|
| 93 |
+
with gr.Blocks(theme=gr.themes.Soft(primary_hue="blue")) as demo:
|
| 94 |
+
gr.Markdown(
|
| 95 |
+
"""
|
| 96 |
+
# 📄 Document Converter Pro
|
| 97 |
+
|
| 98 |
+
Convertissez facilement vos documents dans différents formats avec support OCR automatique.
|
| 99 |
+
"""
|
| 100 |
+
)
|
| 101 |
+
|
| 102 |
+
with gr.Row():
|
| 103 |
+
with gr.Column(scale=1):
|
| 104 |
+
input_file = gr.File(
|
| 105 |
+
label="Télécharger un document",
|
| 106 |
+
file_types=[
|
| 107 |
+
"pdf", "docx", "doc", "pptx", "xlsx",
|
| 108 |
+
"md", "html", "htm", "txt", "rtf",
|
| 109 |
+
"png", "jpg", "jpeg", "tiff", "bmp",
|
| 110 |
+
"adoc", "asciidoc"
|
| 111 |
+
],
|
| 112 |
+
)
|
| 113 |
+
output_format = gr.Dropdown(
|
| 114 |
+
choices=SUPPORTED_OUTPUT_FORMATS,
|
| 115 |
+
value="HTML",
|
| 116 |
+
label="Convertir en",
|
| 117 |
+
info="Sélectionnez le format de sortie"
|
| 118 |
+
)
|
| 119 |
+
convert_btn = gr.Button("Convertir le document", variant="primary")
|
| 120 |
+
|
| 121 |
+
with gr.Column(scale=1):
|
| 122 |
+
output = gr.File(label="Document converti")
|
| 123 |
+
|
| 124 |
+
convert_btn.click(
|
| 125 |
+
fn=convert_document,
|
| 126 |
+
inputs=[input_file, output_format],
|
| 127 |
+
outputs=output
|
| 128 |
+
)
|
| 129 |
+
|
| 130 |
+
gr.Markdown(
|
| 131 |
+
"""
|
| 132 |
+
### 📝 Instructions
|
| 133 |
+
1. Téléchargez votre document
|
| 134 |
+
2. Choisissez le format de sortie souhaité
|
| 135 |
+
3. Cliquez sur "Convertir le document"
|
| 136 |
+
|
| 137 |
+
### ℹ️ Formats supportés
|
| 138 |
+
|
| 139 |
+
#### Formats d'entrée
|
| 140 |
+
- Documents Office : PDF, DOCX, XLSX, PPTX
|
| 141 |
+
- Documents Web : HTML, XHTML
|
| 142 |
+
- Documents texte : Markdown, AsciiDoc, TXT, RTF
|
| 143 |
+
- Images : PNG, JPEG, TIFF, BMP
|
| 144 |
+
|
| 145 |
+
#### Formats de sortie
|
| 146 |
+
- HTML (avec support des images intégrées)
|
| 147 |
+
- Markdown
|
| 148 |
+
- Text (texte brut sans formatage)
|
| 149 |
+
- JSON (sérialisation sans perte)
|
| 150 |
+
- YAML
|
| 151 |
+
- Doctags
|
| 152 |
+
|
| 153 |
+
### 🔍 Fonctionnalités
|
| 154 |
+
- Détection automatique de la langue pour l'OCR
|
| 155 |
+
- Support complet des tableaux
|
| 156 |
+
- Extraction des images
|
| 157 |
+
- Conversion multi-format
|
| 158 |
+
"""
|
| 159 |
+
)
|
| 160 |
+
|
| 161 |
+
if __name__ == "__main__":
|
| 162 |
+
demo.launch(share=False)
|
requirements.txt
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
gradio>=4.19.2
|
| 2 |
+
docling>=2.0.0
|
| 3 |
+
pyyaml>=6.0.1
|
| 4 |
+
tesseract-ocr>=5.3.3
|