71 lines
2.5 KiB
Python
71 lines
2.5 KiB
Python
"""PDF → Markdown。無文字層（掃描件）回報 needs_ocr 並跳過，不擅自呼叫 OCR。
|
||
|
||
可獨立執行：python tools/convert/from_pdf.py <file.pdf> [-o out.md] [--dry-run]
|
||
"""
|
||
import argparse
|
||
import pathlib
|
||
|
||
import fitz # pymupdf
|
||
|
||
# ponytail: 掃描件偵測用「平均每頁字元數 < 25」的 naive heuristic，
|
||
# 混合型 PDF（部分頁掃描）會整份判為有文字層；升級路徑：逐頁判定 + 逐頁標記。
|
||
_MIN_CHARS_PER_PAGE = 25
|
||
|
||
|
||
def convert(src, assets_dir=None, md_dir=None):
|
||
"""回傳 (markdown, status)。status ∈ {'ok', 'needs_ocr'}。
|
||
|
||
ponytail: 表格輸出為純文字行（不重建表格結構），升級路徑：page.find_tables()。
|
||
"""
|
||
src = pathlib.Path(src)
|
||
md_dir = pathlib.Path(md_dir) if md_dir else src.parent
|
||
doc = fitz.open(str(src))
|
||
pages = [page.get_text("text").strip() for page in doc]
|
||
total = sum(len(p) for p in pages)
|
||
if total < _MIN_CHARS_PER_PAGE * max(len(pages), 1):
|
||
doc.close()
|
||
return "", "needs_ocr"
|
||
|
||
counter = 0
|
||
blocks = []
|
||
for i, page in enumerate(doc):
|
||
blocks.append(f"<!-- page {i + 1} -->\n\n{pages[i]}")
|
||
if assets_dir is None:
|
||
continue
|
||
for img in page.get_images(full=True):
|
||
xref = img[0]
|
||
pix = fitz.Pixmap(doc, xref)
|
||
if pix.n > 4: # CMYK 等 → 轉 RGB
|
||
pix = fitz.Pixmap(fitz.csRGB, pix)
|
||
counter += 1
|
||
name = f"img{counter}.png"
|
||
assets_dir.mkdir(parents=True, exist_ok=True)
|
||
pix.save(str(assets_dir / name))
|
||
rel = (assets_dir / name).relative_to(md_dir).as_posix()
|
||
blocks.append(f"")
|
||
doc.close()
|
||
return "\n\n".join(blocks), "ok"
|
||
|
||
|
||
def main(argv=None):
|
||
ap = argparse.ArgumentParser(description=__doc__)
|
||
ap.add_argument("src")
|
||
ap.add_argument("-o", "--output")
|
||
ap.add_argument("--dry-run", action="store_true")
|
||
a = ap.parse_args(argv)
|
||
if a.dry_run:
|
||
md, status = convert(a.src)
|
||
print(f"[dry-run] {a.src}: status={status}, {len(md)} chars")
|
||
return
|
||
out = pathlib.Path(a.output) if a.output else pathlib.Path(a.src).with_suffix(".md")
|
||
md, status = convert(a.src, assets_dir=out.parent / f"{out.stem}-assets", md_dir=out.parent)
|
||
if status == "needs_ocr":
|
||
print(f"needs_ocr: {a.src} 無文字層，已跳過（不擅自 OCR）")
|
||
raise SystemExit(2)
|
||
out.write_text(md, encoding="utf-8")
|
||
print(out)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
main()
|