ENH: Add metadata extractor (#3)

Author: MartinThoma

.github/workflows/code-quality.yaml

@@ -32,13 +32,17 @@ jobs:
       run: |
         pip install -r requirements/ci.txt
 
+    - name: Install cpdf
+      run: |
+        pip install .
+
     - name: Test with black
       run: black --check .
 
     - name: Test with flake8
       run: |
-        flake8
+        flake8 . --exclude build
 
     - name: Test with mypy
       run: |
-        mypy . --ignore-missing-imports
+        mypy . --ignore-missing-imports --exclude build

.isort.cfg

@@ -5,4 +5,4 @@ multi_line_output=3
 length_sort=0
 include_trailing_comma=True
 skip=docs
-known_third_party = PIL,PyPDF2,setuptools,typer
+known_third_party = PIL,PyPDF2,pydantic,setuptools,typer

.pre-commit-config.yaml

@@ -31,6 +31,8 @@ repos:
     rev: v0.942
     hooks:
     -   id: mypy
+        additional_dependencies:
+          - 'pydantic'
 -   repo: https://github.com/asottile/seed-isort-config
     rev: v2.2.0
     hooks:

cpdf/cli.py

@@ -5,6 +5,7 @@
 
 import cpdf.cat
 import cpdf.extract_images
+import cpdf.metadata
 import cpdf.up2
 
 
@@ -52,6 +53,21 @@ def cat(
     cpdf.cat.main(filename, fn_pgrgs, output, verbose)
 
 
+@entry_point.command(name="meta")  # type: ignore[misc]
+def metadata(
+    pdf: Path,
+    output: cpdf.metadata.OutputOptions = typer.Option(  # noqa
+        ...,
+        "--output",
+        "-o",
+        help="output format",
+        show_default=True,
+    ),
+) -> None:
+    cpdf.metadata.main(pdf, output)
+
+
 up2.__doc__ = cpdf.up2.__doc__
 extract_images.__doc__ = cpdf.extract_images.__doc__
 cat.__doc__ = cpdf.cat.__doc__
+metadata.__doc__ = cpdf.metadata.__doc__

cpdf/metadata.py

@@ -0,0 +1,66 @@
+"""Show metadata of a PDF file"""
+
+from enum import Enum
+from pathlib import Path
+from typing import Optional, Tuple
+
+from pydantic import BaseModel
+from PyPDF2 import PdfFileReader
+
+
+class MetaInfo(BaseModel):
+    title: Optional[str] = None
+    producer: Optional[str] = None
+    pages: int
+    encrypted: bool
+    file_size: int  # in bytes
+    page_size: Tuple[float, float]  # (width, height)
+    pdf_file_version: str
+
+
+class OutputOptions(Enum):
+    json = "json"
+    text = "text"
+
+
+def main(pdf: Path, output: OutputOptions) -> None:
+    with open(pdf, "rb") as f:
+        reader = PdfFileReader(f)
+        info = reader.getDocumentInfo()
+        x1, y1, x2, y2 = reader.getPage(0).mediaBox
+
+        reader.stream.seek(0)
+        pdf_file_version = reader.stream.readline().decode()
+
+        meta = MetaInfo(
+            title=info.title,
+            producer=info.producer,
+            pages=reader.getNumPages(),
+            encrypted=reader.isEncrypted,
+            file_size=pdf.stat().st_size,
+            page_size=(x2 - x1, y2 - y1),
+            pdf_file_version=pdf_file_version,
+        )
+
+    if output == OutputOptions.json:
+        print(meta.json())
+    else:
+        from rich.console import Console
+        from rich.table import Table
+
+        table = Table(title=f"{pdf}")
+        table.add_column("Attribute", justify="right", style="cyan", no_wrap=True)
+        table.add_column("Value", style="white")
+
+        table.add_row("Title", meta.title)
+        table.add_row("Producer", meta.producer)
+        table.add_row("Pages", f"{meta.pages:,}")
+        table.add_row("Encrypted", f"{meta.encrypted}")
+        table.add_row("File size", f"{meta.file_size:,} bytes")
+        table.add_row(
+            "Page size", f"{meta.page_size[0]} x {meta.page_size[1]} pts (w x h)"
+        )
+        table.add_row("PDF File Version", meta.pdf_file_version)
+
+        console = Console()
+        console.print(table)

mypy.ini

@@ -0,0 +1,2 @@
+[mypy]
+plugins = pydantic.mypy

setup.cfg

@@ -37,6 +37,8 @@ install_requires =
     PyPDF2
     typer
     pillow
+    pydantic
+    rich
 
 [options.entry_points]
 console_scripts =