ENH: Add compress command (#10)

Author: MartinThoma

README.md

@@ -30,7 +30,11 @@ Options:
 Commands:
   2-up            Create a booklet-style PDF from a single input.
   cat             Concatenate pages from PDF files into a single PDF file.
+  compress        Compress a PDF.
   extract-images  Extract images from PDF without resampling or altering.
+  extract-text    Extract text from a PDF file.
+  meta            Show metadata of a PDF file
+
 ```
 
 You can see the help of every subcommand by typing:

cpdf/cli.py

@@ -4,6 +4,7 @@
 import typer
 
 import cpdf.cat
+import cpdf.compress
 import cpdf.extract_images
 import cpdf.metadata
 import cpdf.up2
@@ -57,7 +58,7 @@ def cat(
 def metadata(
     pdf: Path,
     output: cpdf.metadata.OutputOptions = typer.Option(  # noqa
-        cpdf.metadata.OutputOptions.text,
+        cpdf.metadata.OutputOptions.text.value,
         "--output",
         "-o",
         help="output format",
@@ -68,9 +69,7 @@ def metadata(
 
 
 @entry_point.command(name="extract-text")  # type: ignore[misc]
-def extract_text(
-    pdf: Path,
-):
+def extract_text(pdf: Path):
     """Extract text from a PDF file."""
     from PyPDF2 import PdfReader
 
@@ -79,7 +78,13 @@ def extract_text(
         print(page.extract_text())
 
 
+@entry_point.command(name="compress")  # type: ignore[misc]
+def compress(pdf: Path, output: Path):
+    cpdf.compress.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__
+compress.__doc__ = cpdf.compress.__doc__

cpdf/compress.py

@@ -0,0 +1,24 @@
+"""Compress a PDF."""
+
+import os
+from pathlib import Path
+
+from PyPDF2 import PdfReader, PdfWriter
+
+
+def main(pdf: Path, output: Path):
+    reader = PdfReader(pdf)
+    writer = PdfWriter()
+    for page in reader.pages:
+        page.compress_content_streams()
+        writer.add_page(page)
+
+    with open(output, "wb") as fp:
+        writer.write(fp)
+
+    orig_size = os.path.getsize(pdf)
+    comp_size = os.path.getsize(output)
+    ratio = comp_size / orig_size
+
+    print(f"Original Size  : {orig_size:,}")
+    print(f"Compressed Size: {comp_size:,} ({ratio * 100:2.1f}% of original)")