| import os
|
| from pathlib import Path
|
| from typing import Callable, Dict, Any
|
|
|
| import markdown
|
| import fitz
|
| from docx import Document
|
| from bs4 import BeautifulSoup
|
|
|
|
|
| class DocumentConverter:
|
|
|
| def convert(self, input_path:str, output_path:str,
|
| options:Dict[str,Any]|None=None,
|
| progress_callback:Callable|None=None)->bool:
|
|
|
| try:
|
| input_ext = Path(input_path).suffix.lower()
|
| output_ext = Path(output_path).suffix.lower()
|
|
|
| self._update(progress_callback, 10)
|
|
|
| Path(output_path).parent.mkdir(parents=True, exist_ok=True)
|
|
|
| success = False
|
|
|
|
|
| if input_ext == ".txt" and output_ext == ".pdf":
|
| success = self.txt_to_pdf(input_path, output_path)
|
|
|
| elif input_ext == ".txt" and output_ext == ".html":
|
| success = self.txt_to_html(input_path, output_path)
|
|
|
| elif input_ext == ".txt" and output_ext == ".md":
|
| success = self.txt_to_md(input_path, output_path)
|
|
|
|
|
| elif input_ext == ".md" and output_ext == ".html":
|
| success = self.md_to_html(input_path, output_path)
|
|
|
| elif input_ext == ".md" and output_ext == ".txt":
|
| success = self.md_to_text(input_path, output_path)
|
|
|
|
|
| elif input_ext == ".html" and output_ext == ".txt":
|
| success = self.html_to_text(input_path, output_path)
|
|
|
| elif input_ext == ".html" and output_ext == ".md":
|
| success = self.html_to_md(input_path, output_path)
|
|
|
|
|
| elif input_ext == ".docx" and output_ext == ".txt":
|
| success = self.docx_to_text(input_path, output_path)
|
|
|
|
|
| elif input_ext == ".pdf" and output_ext == ".txt":
|
| success = self.pdf_to_text(input_path, output_path)
|
|
|
| elif input_ext == ".pdf" and output_ext == ".html":
|
| success = self.pdf_to_html(input_path, output_path)
|
|
|
| else:
|
| raise ValueError(f"Unsupported conversion: {input_ext} -> {output_ext}")
|
|
|
| self._update(progress_callback, 100)
|
|
|
| return success
|
|
|
| except Exception as e:
|
| print(f"Document conversion error: {e}")
|
| return False
|
|
|
| def txt_to_pdf(self, input_path, output_path):
|
| pdf = fitz.open()
|
| page = pdf.new_page()
|
|
|
| text = Path(input_path).read_text(
|
| encoding="utf-8",
|
| errors="ignore"
|
| )
|
|
|
| page.insert_text((72, 72), text[:5000])
|
|
|
| pdf.save(output_path)
|
| return True
|
|
|
| def txt_to_html(self, input_path, output_path):
|
| text = Path(input_path).read_text(
|
| encoding="utf-8",
|
| errors="ignore"
|
| )
|
|
|
| html = f"<html><body><pre>{text}</pre></body></html>"
|
|
|
| Path(output_path).write_text(
|
| html,
|
| encoding="utf-8"
|
| )
|
|
|
| return True
|
|
|
| def txt_to_md(self, input_path, output_path):
|
| text = Path(input_path).read_text(
|
| encoding="utf-8",
|
| errors="ignore"
|
| )
|
|
|
| Path(output_path).write_text(
|
| text,
|
| encoding="utf-8"
|
| )
|
|
|
| return True
|
|
|
| def md_to_html(self, input_path, output_path):
|
| md = Path(input_path).read_text(
|
| encoding="utf-8",
|
| errors="ignore"
|
| )
|
|
|
| html = markdown.markdown(md)
|
|
|
| Path(output_path).write_text(
|
| html,
|
| encoding="utf-8"
|
| )
|
|
|
| return True
|
|
|
| def md_to_text(self, input_path, output_path):
|
| md = Path(input_path).read_text(
|
| encoding="utf-8",
|
| errors="ignore"
|
| )
|
|
|
| html = markdown.markdown(md)
|
| soup = BeautifulSoup(html, "html.parser")
|
|
|
| Path(output_path).write_text(
|
| soup.get_text(),
|
| encoding="utf-8"
|
| )
|
|
|
| return True
|
|
|
| def html_to_text(self, input_path, output_path):
|
| html = Path(input_path).read_text(
|
| encoding="utf-8",
|
| errors="ignore"
|
| )
|
|
|
| soup = BeautifulSoup(html, "html.parser")
|
|
|
| Path(output_path).write_text(
|
| soup.get_text(),
|
| encoding="utf-8"
|
| )
|
|
|
| return True
|
|
|
| def html_to_md(self, input_path, output_path):
|
| html = Path(input_path).read_text(
|
| encoding="utf-8",
|
| errors="ignore"
|
| )
|
|
|
| soup = BeautifulSoup(html, "html.parser")
|
|
|
| text = soup.get_text()
|
|
|
| Path(output_path).write_text(
|
| text,
|
| encoding="utf-8"
|
| )
|
|
|
| return True
|
|
|
| def docx_to_text(self, input_path, output_path):
|
| doc = Document(input_path)
|
|
|
| text = "\n".join(
|
| [p.text for p in doc.paragraphs]
|
| )
|
|
|
| Path(output_path).write_text(
|
| text,
|
| encoding="utf-8"
|
| )
|
|
|
| return True
|
|
|
| def pdf_to_text(self, input_path, output_path):
|
| doc = fitz.open(input_path)
|
|
|
| text = ""
|
|
|
| for page in doc:
|
| text += page.get_text()
|
|
|
| Path(output_path).write_text(
|
| text,
|
| encoding="utf-8"
|
| )
|
|
|
| return True
|
|
|
| def pdf_to_html(self, input_path, output_path):
|
| doc = fitz.open(input_path)
|
|
|
| html = ""
|
|
|
| for page in doc:
|
| html += page.get_text("html")
|
|
|
| Path(output_path).write_text(
|
| html,
|
| encoding="utf-8"
|
| )
|
|
|
| return True
|
|
|
| def _update(self, callback, value):
|
| try:
|
| if callback:
|
| callback(value)
|
| except:
|
| pass |
