mirror of
https://github.com/bestnite/slide-translate.git
synced 2025-10-28 01:11:17 +00:00
nite
3eef042111
The main.py script was becoming monolithic, containing all the logic for PDF conversion, image path simplification, and content refinement. This change extracts these core functionalities into a new `pdf_convertor` module. This refactoring improves the project structure by: - Enhancing modularity and separation of concerns. - Making the main.py script a cleaner, high-level orchestrator. - Improving code readability and maintainability. The functions `convert_pdf_to_markdown`, `save_md_images`, and `refine_content` are now imported from the `pdf_convertor` module and called from the main execution block.
38 lines
969 B
Python
Executable File
38 lines
969 B
Python
Executable File
import os
|
|
from pdf_convertor import (
|
|
convert_pdf_to_markdown,
|
|
save_md_images,
|
|
refine_content,
|
|
)
|
|
from pathlib import Path
|
|
|
|
|
|
def main():
|
|
input_dir = Path("input")
|
|
output_dir = Path("output")
|
|
|
|
output_dir.mkdir(parents=True, exist_ok=True)
|
|
|
|
for filename in os.listdir(input_dir):
|
|
if not filename.endswith(".pdf"):
|
|
continue
|
|
|
|
pdf_path = input_dir.joinpath(filename)
|
|
current_output_dir = output_dir.joinpath(
|
|
pdf_path.name.removesuffix(pdf_path.suffix)
|
|
)
|
|
|
|
current_output_dir.mkdir(parents=True, exist_ok=True)
|
|
|
|
print(f"Processing {pdf_path} -> {current_output_dir}")
|
|
|
|
with open(pdf_path, "rb") as pdf_file:
|
|
pdf_content = pdf_file.read()
|
|
md, images = convert_pdf_to_markdown(pdf_content)
|
|
md = refine_content(md, images, pdf_content)
|
|
save_md_images(current_output_dir, md, images)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|