File size: 5,914 Bytes
8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 8470fc3 b169283 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 | 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
# TXT
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)
# MD
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)
# HTML
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)
# DOCX
elif input_ext == ".docx" and output_ext == ".txt":
success = self.docx_to_text(input_path, output_path)
# PDF
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 |