pdfalyzer 1.17.1__tar.gz → 1.17.2__tar.gz

{pdfalyzer-1.17.1 → pdfalyzer-1.17.2}/CHANGELOG.md

@@ -1,7 +1,11 @@
 # NEXT RELEASE
 
+### 1.17.2
+* Remove unused `--debug` args for CLI tools
+* Rename `extract_text_from_pdfs` to `extract_pdf_text`
+
 ### 1.17.1
-* Fix issue where `combine_pdfs` page ranges were indexed from 0 instead of 1
+* Fix issue where `extract_pdf_pages` page ranges were indexed from 0 instead of 1
 
 # 1.17.0
 * Add `extract_pdf_pages` command line tool (imported from `clown_sort`)

{pdfalyzer-1.17.1 → pdfalyzer-1.17.2}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.1
 Name: pdfalyzer
-Version: 1.17.1
-Summary: PDF analysis tool. Scan a PDF with YARA rules, visualize its inner tree-like data structure in living color (lots of colors), force decodes of suspicious font binaries, and more.
+Version: 1.17.2
+Summary: Analyze PDFs with colors (and YARA). Visualize a PDF's inner tree-like data structure, check it against a library of YARA rules, force decodes of suspicious font binaries, and more.
 Home-page: https://github.com/michelcrypt4d4mus/pdfalyzer
 License: GPL-3.0-or-later
 Keywords: ascii art,binary,color,cybersecurity,DFIR,encoding,font,infosec,maldoc,malicious pdf,malware,malware analysis,pdf,pdfs,pdf analysis,pypdf,threat assessment,threat hunting,threat intelligence,threat research,threatintel,visualization,yara
@@ -252,9 +252,9 @@ The Pdfalyzer comes with a few command line tools:
 
 * `combine_pdfs` - Combines multiple PDFs into a single PDF. Run `combine_pdfs --help` for more info.
 * `extract_pdf_pages` - Extracts page ranges (e.g. "10-25") from a PDF and writes them to a new PDF. Run `extract_pdf_pages --help` for more info.
-* `extract_text_from_pdfs` - Extracts text from a PDF, including applying OCR to all embedded images. Run `extract_text_from_pdfs --help` for more info.
+* `extract_pdf_text` - Extracts text from a PDF, including applying OCR to all embedded images. Run `extract_pdf_text --help` for more info.
 
-Running `extract_text_from_pdfs` requires that you install The Pdfalyzer's optional dependencies:
+Running `extract_pdf_text` requires that you install The Pdfalyzer's optional dependencies:
 
 ```bash
 pipx install pdfalyzer[extract]

{pdfalyzer-1.17.1 → pdfalyzer-1.17.2}/README.md

@@ -218,9 +218,9 @@ The Pdfalyzer comes with a few command line tools:
 
 * `combine_pdfs` - Combines multiple PDFs into a single PDF. Run `combine_pdfs --help` for more info.
 * `extract_pdf_pages` - Extracts page ranges (e.g. "10-25") from a PDF and writes them to a new PDF. Run `extract_pdf_pages --help` for more info.
-* `extract_text_from_pdfs` - Extracts text from a PDF, including applying OCR to all embedded images. Run `extract_text_from_pdfs --help` for more info.
+* `extract_pdf_text` - Extracts text from a PDF, including applying OCR to all embedded images. Run `extract_pdf_text --help` for more info.
 
-Running `extract_text_from_pdfs` requires that you install The Pdfalyzer's optional dependencies:
+Running `extract_pdf_text` requires that you install The Pdfalyzer's optional dependencies:
 
 ```bash
 pipx install pdfalyzer[extract]

{pdfalyzer-1.17.1 → pdfalyzer-1.17.2}/pdfalyzer/__init__.py

@@ -32,8 +32,8 @@ from pdfalyzer.output.pdfalyzer_presenter import PdfalyzerPresenter
 from pdfalyzer.output.styles.rich_theme import PDFALYZER_THEME_DICT
 from pdfalyzer.pdfalyzer import Pdfalyzer
 from pdfalyzer.util.argument_parser import ask_to_proceed, output_sections, parse_arguments
-from pdfalyzer.util.cli_tools_argument_parser import (MAX_QUALITY, ask_to_proceed,
-     parse_combine_pdfs_args, parse_pdf_page_extraction_args, parse_text_extraction_args)
+from pdfalyzer.util.cli_tools_argument_parser import (MAX_QUALITY, parse_combine_pdfs_args,
+     parse_pdf_page_extraction_args, parse_text_extraction_args)
 from pdfalyzer.util.pdf_parser_manager import PdfParserManager
 
 # For the table shown by running pdfalyzer_show_color_theme
@@ -141,7 +141,7 @@ def extract_pdf_pages() -> None:
     PdfFile(args.pdf_file).extract_page_range(args.page_range, destination_dir=args.destination_dir)
 
 
-def extract_text_from_pdfs() -> None:
+def extract_pdf_text() -> None:
     """Extract text from a list of file or from all PDF files in a list of directories."""
     args: Namespace = parse_text_extraction_args()
     console.line()

{pdfalyzer-1.17.1 → pdfalyzer-1.17.2}/pdfalyzer/decorators/pdf_file.py

@@ -30,9 +30,9 @@ class PdfFile:
 
     Attributes:
         file_path (Path): The path to the PDF file.
-        dirname (Path): The directory containing the PDF file.
         basename (str): The base name of the PDF file (with extension).
         basename_without_ext (str): The base name of the PDF file (without extension).
+        dirname (Path): The directory containing the PDF file.
         extname (str): The file extension of the PDF file.
         file_size (int): The size of the file in bytes.
     """
@@ -74,11 +74,15 @@ class PdfFile:
         """
         destination_dir = Path(destination_dir or self.dirname)
         create_dir_if_it_does_not_exist(destination_dir)
+        pdf_reader = PdfReader(self.file_path)
+        page_count = len(pdf_reader.pages)
+        file_suffix = page_range.file_suffix()
+
+        if page_count < (page_range.last_page - 1):
+            raise ValueError(f"PDF only has {page_count} pages but you asked for pages {page_range}!")
 
-        if extra_file_suffix is None:
-            file_suffix = page_range.file_suffix()
-        else:
-            file_suffix = f"{page_range.file_suffix()}__{extra_file_suffix}"
+        if extra_file_suffix is not None:
+            file_suffix += f"__{extra_file_suffix}"
 
         extracted_pages_pdf_basename = insert_suffix_before_extension(self.file_path, file_suffix).name
         extracted_pages_pdf_path = destination_dir.joinpath(extracted_pages_pdf_basename)
@@ -211,3 +215,10 @@ class PdfFile:
             return
 
         stderr_console.print(msg, style=style or "")
+
+    # def _num_pages(self) -> int:
+    #     pdf_reader = PdfReader(self.file_path)
+    #     page_count = len(pdf_reader.pages)
+    #         log.debug(f"PDF Page count: {page_count}")
+
+    #         for page_number, page in enumerate(pdf_reader.pages, start=1):

{pdfalyzer-1.17.1 → pdfalyzer-1.17.2}/pdfalyzer/helpers/filesystem_helper.py

@@ -6,7 +6,6 @@ from pathlib import Path
 from typing import Optional, Union
 
 from yaralyzer.output.rich_console import console
-from yaralyzer.util.logging import log
 
 from pdfalyzer.helpers.rich_text_helper import print_highlighted
 

{pdfalyzer-1.17.1 → pdfalyzer-1.17.2}/pdfalyzer/util/argument_parser.py

@@ -196,7 +196,7 @@ def output_sections(args: Namespace, pdfalyzer: 'Pdfalyzer') -> List[OutputSecti
 
 
 def all_sections_chosen(args):
-    """Returns true if all flags are set or no flags are set."""
+    """Returns True if all flags are set or no flags are set."""
     return len([s for s in ALL_SECTIONS if vars(args)[s]]) == len(ALL_SECTIONS)
 
 

{pdfalyzer-1.17.1 → pdfalyzer-1.17.2}/pdfalyzer/util/cli_tools_argument_parser.py

@@ -2,7 +2,8 @@
 Argument parsers for the command line tools other than `pdfalyze` that are included with The Pdfalyzer.
 
 1. combine_pdfs
-2.
+2. extract_pdf_pages
+3. extract_pdf_text
 """
 import sys
 from argparse import ArgumentParser, Namespace
@@ -97,8 +98,6 @@ extract_pdf_parser.add_argument('--destination-dir', '-d',
                                 help="directory to write the new PDF to",
                                 default=Path.cwd())
 
-extract_pdf_parser.add_argument('--debug', action='store_true', help='turn on debug level logging')
-
 
 def parse_pdf_page_extraction_args() -> Namespace:
     args = extract_pdf_parser.parse_args()
@@ -113,9 +112,9 @@ def parse_pdf_page_extraction_args() -> Namespace:
     return args
 
 
-############################
-#  extract_text_from_pdfs  #
-############################
+######################
+#  extract_pdf_text  #
+######################
 extract_text_parser = ArgumentParser(
     formatter_class=RichHelpFormatterPlus,
     description="Extract the text from one or more files or directories.",
@@ -123,7 +122,6 @@ extract_text_parser = ArgumentParser(
 )
 
 extract_text_parser.add_argument('file_or_dir', nargs='+', metavar='FILE_OR_DIR')
-extract_text_parser.add_argument('--debug', action='store_true', help='turn on debug level logging')
 
 extract_text_parser.add_argument('--page-range', '-r',
                                  type=page_range_validator,

{pdfalyzer-1.17.1 → pdfalyzer-1.17.2}/pyproject.toml

@@ -1,7 +1,7 @@
 [tool.poetry]
 name = "pdfalyzer"
-version = "1.17.1"
-description = "PDF analysis tool. Scan a PDF with YARA rules, visualize its inner tree-like data structure in living color (lots of colors), force decodes of suspicious font binaries, and more."
+version = "1.17.2"
+description = "Analyze PDFs with colors (and YARA). Visualize a PDF's inner tree-like data structure, check it against a library of YARA rules, force decodes of suspicious font binaries, and more."
 authors = ["Michel de Cryptadamus <michel@cryptadamus.com>"]
 license = "GPL-3.0-or-later"
 readme = "README.md"
@@ -91,7 +91,7 @@ pytest-skip-slow = "^0.0.3"
 [tool.poetry.scripts]
 combine_pdfs = 'pdfalyzer:combine_pdfs'
 extract_pdf_pages = 'pdfalyzer:extract_pdf_pages'
-extract_text_from_pdfs = 'pdfalyzer:extract_text_from_pdfs'
+extract_pdf_text = 'pdfalyzer:extract_pdf_text'
 pdfalyze = 'pdfalyzer:pdfalyze'
 pdfalyzer_show_color_theme = 'pdfalyzer:pdfalyzer_show_color_theme'