pdf2md.py als fester Name, v1–v4 nach History/ verschoben
- pdf2md_v5.py → pdf2md.py; Verweise in Doku und Tests angepasst - pdf2md_v1.py … pdf2md_v4.py nach History/ verschoben - ljutsch_meta.xml entfernt (nicht mehr verwendet) Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Dieter Schlüter
parent
37ea397a29
commit
b4b911d37f
1 changed files with 22 additions and 49 deletions
249
pdf2md_v3.py
249
pdf2md_v3.py
|
|
@ -1,249 +0,0 @@
|
|||
#!/usr/bin/env python3
|
||||
"""PDF nach Markdown konvertieren und Fließtext nach Satzenden gliedern."""
|
||||
|
||||
import argparse
|
||||
import re
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
import pymupdf4llm
|
||||
from pymupdf4llm.ocr import tesseract_api
|
||||
|
||||
|
||||
HEADING = re.compile(r"^\s{0,3}#{1,6}\s+\S")
|
||||
|
||||
# Punkt, Fragezeichen, Ausrufezeichen oder Auslassungspunkte;
|
||||
# danach dürfen schließende Anführungszeichen/Klammern folgen.
|
||||
SENTENCE_END = re.compile(r"""[.!?…]+[”’"'»›)\]]*$""")
|
||||
|
||||
FENCE = re.compile(r"^\s{0,3}(`{3,}|~{3,})")
|
||||
LIST_ITEM = re.compile(r"^\s{0,3}(?:[-+*]|\d+[.)])\s+")
|
||||
BLOCKQUOTE = re.compile(r"^\s{0,3}>\s?")
|
||||
RULE = re.compile(r"^\s{0,3}(?:-\s*){3,}$|^\s{0,3}(?:\*\s*){3,}$")
|
||||
IMAGE = re.compile(r"^\s*!\[.*?\]\(.*\)\s*$")
|
||||
|
||||
# Beispiel:
|
||||
# **==> picture [426 x 480] intentionally omitted <==**
|
||||
OMITTED_IMAGE = re.compile(
|
||||
r"^\s*(?:\*\*|__)?\s*==>\s*"
|
||||
r"(?:picture|image|bild)\b.*?"
|
||||
r"(?:intentionally omitted|omitted|ausgelassen)\s*"
|
||||
r"<==\s*(?:\*\*|__)?\s*$",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
|
||||
CONTENTS_TITLE = re.compile(
|
||||
r"^\s*(?:#{1,6}\s+)?"
|
||||
r"(?:inhaltsverzeichnis|inhalt|contents|table of contents)"
|
||||
r"\s*$",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
|
||||
# Inhaltsverzeichnis mit Füllpunkten oder Abstand vor einer Seitenzahl:
|
||||
# Kapitel 1 .......... 12
|
||||
# Kapitel 1 12
|
||||
# Kapitel 1 xiv
|
||||
TOC_WITH_PAGE = re.compile(
|
||||
r"^\s*(?:[-*]\s+)?\S.+?"
|
||||
r"(?:\.{2,}|\s{2,})"
|
||||
r"(?:\d+|[ivxlcdm]+)\s*$",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
|
||||
# Einträge ohne Seitenzahl, sofern bereits ein Inhaltsverzeichnis erkannt wurde:
|
||||
# 1 Einleitung
|
||||
# 1.2 Vorgeschichte
|
||||
# Kapitel 3 – Die Reise
|
||||
TOC_NUMBERED = re.compile(
|
||||
r"^\s*(?:[-*]\s+)?"
|
||||
r"(?:\d+(?:\.\d+)*\.?\s+|Kapitel\s+\d+\b|Chapter\s+\d+\b)"
|
||||
r".+",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
|
||||
HTML_BLOCK = re.compile(
|
||||
r"^\s*</?(?:table|tr|td|th|div|pre|p|h[1-6])\b",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
|
||||
|
||||
def ends_sentence(text: str) -> bool:
|
||||
return bool(SENTENCE_END.search(text.rstrip()))
|
||||
|
||||
|
||||
def is_other_structure(line: str) -> bool:
|
||||
"""Markdown-Strukturen, die nicht zu Fließtext verbunden werden."""
|
||||
return bool(
|
||||
LIST_ITEM.match(line)
|
||||
or BLOCKQUOTE.match(line)
|
||||
or RULE.match(line)
|
||||
or IMAGE.match(line)
|
||||
or HTML_BLOCK.match(line)
|
||||
or line.lstrip().startswith("|")
|
||||
or line.startswith((" ", "\t"))
|
||||
)
|
||||
|
||||
|
||||
def normalize_markdown(markdown: str) -> str:
|
||||
result: list[str] = []
|
||||
paragraph: list[str] = []
|
||||
|
||||
in_fence = False
|
||||
fence_char = ""
|
||||
fence_length = 0
|
||||
in_contents = False
|
||||
|
||||
def blank_line() -> None:
|
||||
if result and result[-1] != "":
|
||||
result.append("")
|
||||
|
||||
def flush_paragraph() -> None:
|
||||
if paragraph:
|
||||
result.append(" ".join(paragraph))
|
||||
paragraph.clear()
|
||||
|
||||
def standalone(line: str) -> None:
|
||||
flush_paragraph()
|
||||
blank_line()
|
||||
result.append(line)
|
||||
result.append("")
|
||||
|
||||
lines = markdown.replace("\r\n", "\n").replace("\r", "\n").split("\n")
|
||||
|
||||
for original in lines:
|
||||
line = original.rstrip()
|
||||
marker = FENCE.match(line)
|
||||
|
||||
if in_fence:
|
||||
result.append(line)
|
||||
if marker:
|
||||
token = marker.group(1)
|
||||
if token[0] == fence_char and len(token) >= fence_length:
|
||||
in_fence = False
|
||||
continue
|
||||
|
||||
if marker:
|
||||
flush_paragraph()
|
||||
blank_line()
|
||||
result.append(line)
|
||||
in_fence = True
|
||||
fence_char = marker.group(1)[0]
|
||||
fence_length = len(marker.group(1))
|
||||
continue
|
||||
|
||||
if not line.strip():
|
||||
# Leerzeile nur dann als Absatzgrenze behandeln,
|
||||
# wenn der bisherige Fließtext mit einem Satzende endet.
|
||||
if paragraph and ends_sentence(paragraph[-1]):
|
||||
flush_paragraph()
|
||||
blank_line()
|
||||
elif not paragraph:
|
||||
blank_line()
|
||||
continue
|
||||
|
||||
if CONTENTS_TITLE.match(line):
|
||||
standalone(line)
|
||||
in_contents = True
|
||||
continue
|
||||
|
||||
if HEADING.match(line):
|
||||
standalone(line)
|
||||
in_contents = False
|
||||
continue
|
||||
|
||||
if OMITTED_IMAGE.match(line):
|
||||
standalone(line)
|
||||
continue
|
||||
|
||||
if TOC_WITH_PAGE.match(line):
|
||||
standalone(line)
|
||||
continue
|
||||
|
||||
if in_contents and TOC_NUMBERED.match(line):
|
||||
standalone(line)
|
||||
continue
|
||||
|
||||
if in_contents and ends_sentence(line):
|
||||
# Erster normaler Satz nach einem erkannten Inhaltsverzeichnis.
|
||||
in_contents = False
|
||||
|
||||
if is_other_structure(line):
|
||||
flush_paragraph()
|
||||
result.append(line)
|
||||
continue
|
||||
|
||||
# Einfache Zeilenumbrüche und nicht bestätigte Absatzgrenzen
|
||||
# werden beim späteren Flush durch Leerzeichen ersetzt.
|
||||
paragraph.append(line.strip())
|
||||
|
||||
flush_paragraph()
|
||||
return "\n".join(result).strip() + "\n"
|
||||
|
||||
|
||||
def main() -> int:
|
||||
parser = argparse.ArgumentParser(
|
||||
description="PDF in Markdown umwandeln; Fließtext nur nach Satzende trennen."
|
||||
)
|
||||
parser.add_argument("pdf", type=Path, help="Eingabe-PDF")
|
||||
parser.add_argument(
|
||||
"markdown",
|
||||
type=Path,
|
||||
nargs="?",
|
||||
help="Ausgabe-Datei; Standard: gleicher Name mit .md",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--ocr-language",
|
||||
default="deu",
|
||||
help="Tesseract-Sprachcode bei OCR (Standard: deu)",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--no-ocr",
|
||||
action="store_true",
|
||||
help="OCR deaktivieren",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--keep-headers",
|
||||
action="store_true",
|
||||
help="Wiederkehrende Seitenköpfe übernehmen",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--keep-footers",
|
||||
action="store_true",
|
||||
help="Wiederkehrende Seitenfüße übernehmen",
|
||||
)
|
||||
args = parser.parse_args()
|
||||
|
||||
source = args.pdf.expanduser()
|
||||
target = (args.markdown or source.with_suffix(".md")).expanduser()
|
||||
|
||||
if not source.is_file():
|
||||
parser.error(f"Eingabedatei nicht gefunden: {source}")
|
||||
if source.resolve() == target.resolve():
|
||||
parser.error("Eingabe- und Ausgabedatei müssen verschieden sein.")
|
||||
|
||||
try:
|
||||
markdown = pymupdf4llm.to_markdown(
|
||||
str(source),
|
||||
header=args.keep_headers,
|
||||
footer=args.keep_footers,
|
||||
use_ocr=not args.no_ocr,
|
||||
ocr_language=args.ocr_language,
|
||||
ocr_function=(
|
||||
tesseract_api.exec_ocr if not args.no_ocr else None
|
||||
),
|
||||
)
|
||||
|
||||
target.parent.mkdir(parents=True, exist_ok=True)
|
||||
target.write_text(normalize_markdown(markdown), encoding="utf-8")
|
||||
|
||||
except Exception as exc:
|
||||
print(f"Fehler bei der Konvertierung: {exc}", file=sys.stderr)
|
||||
return 1
|
||||
|
||||
print(f"Markdown geschrieben: {target}")
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
|
||||
Loading…
Reference in a new issue