Initial commit

pdf_merge.py

@@ -0,0 +1,45 @@
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Iterable, List, Optional
+
+from pypdf import PdfReader, PdfWriter
+
+
+def merge_pdfs(pdf_paths: Iterable[str | Path], out_pdf_path: str | Path) -> dict:
+    out_pdf_path = Path(out_pdf_path)
+    out_pdf_path.parent.mkdir(parents=True, exist_ok=True)
+
+    writer = PdfWriter()
+
+    merged: List[str] = []
+    skipped: List[str] = []
+
+    for p in pdf_paths:
+        path = Path(p)
+        try:
+            reader = PdfReader(str(path))
+            # просто добавляем страницы подряд
+            for page in reader.pages:
+                writer.add_page(page)
+            merged.append(str(path))
+        except Exception:
+            skipped.append(str(path))
+
+    if merged:
+        with out_pdf_path.open("wb") as f:
+            writer.write(f)
+
+    return {
+        "out_pdf": str(out_pdf_path),
+        "merged_count": len(merged),
+        "skipped_count": len(skipped),
+        "merged_files": merged,
+        "skipped_files": skipped,
+    }
+
+
+def merge_all_pdfs_in_dir(files_dir: str | Path, out_pdf_path: str | Path) -> dict:
+    files_dir = Path(files_dir)
+    pdfs = sorted(files_dir.rglob("*.pdf")) + sorted(files_dir.rglob("*.PDF"))
+    return merge_pdfs(pdfs, out_pdf_path)