Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
|
@@ -8,6 +8,7 @@ import gradio as gr
|
|
| 8 |
from PIL import Image
|
| 9 |
from PyPDF2 import PdfReader
|
| 10 |
from ebooklib import epub
|
|
|
|
| 11 |
from transformers import AutoProcessor, Qwen2VLForConditionalGeneration
|
| 12 |
|
| 13 |
from olmocr.data.renderpdf import render_pdf_to_base64png
|
|
@@ -59,6 +60,34 @@ def ocr_page(pdf_path, page_num):
|
|
| 59 |
decoded = processor.tokenizer.batch_decode(new_tokens, skip_special_tokens=True)
|
| 60 |
return decoded[0] if decoded else ""
|
| 61 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
def convert_pdf_to_epub(pdf_file, title, author, language):
|
| 63 |
# Save the uploaded file to a temporary path
|
| 64 |
tmp_pdf_path = "/tmp/uploaded.pdf"
|
|
|
|
| 8 |
from PIL import Image
|
| 9 |
from PyPDF2 import PdfReader
|
| 10 |
from ebooklib import epub
|
| 11 |
+
from pdf2image import convert_from_path
|
| 12 |
from transformers import AutoProcessor, Qwen2VLForConditionalGeneration
|
| 13 |
|
| 14 |
from olmocr.data.renderpdf import render_pdf_to_base64png
|
|
|
|
| 60 |
decoded = processor.tokenizer.batch_decode(new_tokens, skip_special_tokens=True)
|
| 61 |
return decoded[0] if decoded else ""
|
| 62 |
|
| 63 |
+
def create_epub_from_text(text, output_path, title, author, language, cover_image):
|
| 64 |
+
book = epub.EpubBook()
|
| 65 |
+
|
| 66 |
+
# Set metadata
|
| 67 |
+
book.set_title(title)
|
| 68 |
+
book.set_language(language)
|
| 69 |
+
book.add_author(author)
|
| 70 |
+
|
| 71 |
+
# Add cover image
|
| 72 |
+
with open(cover_image, "rb") as cover_file:
|
| 73 |
+
cover_data = cover_file.read()
|
| 74 |
+
cover_item = epub.EpubItem(uid="cover", file_name="cover.jpg", media_type="image/jpeg", content=cover_data)
|
| 75 |
+
book.add_item(cover_item)
|
| 76 |
+
|
| 77 |
+
# Create a chapter for the content
|
| 78 |
+
chapter = epub.EpubHtml(title="Content", file_name="content.xhtml", lang=language)
|
| 79 |
+
chapter.set_content(f"<html><body><h1>{title}</h1><p>{text}</p></body></html>")
|
| 80 |
+
book.add_item(chapter)
|
| 81 |
+
|
| 82 |
+
# Define Table of Contents (TOC)
|
| 83 |
+
book.toc = (epub.Link("content.xhtml", "Content", "content"),)
|
| 84 |
+
|
| 85 |
+
# Add default NCX and OPF files
|
| 86 |
+
book.add_item(epub.EpubNav())
|
| 87 |
+
|
| 88 |
+
# Write the EPUB file
|
| 89 |
+
epub.write_epub(output_path, book)
|
| 90 |
+
|
| 91 |
def convert_pdf_to_epub(pdf_file, title, author, language):
|
| 92 |
# Save the uploaded file to a temporary path
|
| 93 |
tmp_pdf_path = "/tmp/uploaded.pdf"
|