pdfalyzer 1.17.1__py3-none-any.whl → 1.17.3__py3-none-any.whl

CHANGELOG.md

@@ -1,7 +1,14 @@
 # NEXT RELEASE
 
+### 1.17.3
+* Put back `--debug` arg for CLI tools
+
+### 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/__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/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)

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/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/util/cli_tools_argument_parser.py

@@ -2,8 +2,10 @@
 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 logging
 import sys
 from argparse import ArgumentParser, Namespace
 from pathlib import Path
@@ -87,6 +89,7 @@ extract_pdf_parser = ArgumentParser(
 )
 
 extract_pdf_parser.add_argument('pdf_file', metavar='PDF_FILE', help='PDF to extract pages from')
+extract_pdf_parser.add_argument('--debug', action='store_true', help='turn on debug level logging')
 
 extract_pdf_parser.add_argument('--page-range', '-r',
                                 type=page_range_validator,
@@ -97,8 +100,6 @@ 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()
@@ -110,12 +111,13 @@ def parse_pdf_page_extraction_args() -> Namespace:
         log.error(f"Destination dir '{args.destination_dir}' does not exist.")
         sys.exit(1)
 
+    _set_log_level(args)
     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.",
@@ -153,4 +155,10 @@ def parse_text_extraction_args() -> Namespace:
         log.error(f"--page-range can only be specified for a single PDF")
         sys.exit(-1)
 
+    _set_log_level(args)
     return args
+
+
+def _set_log_level(args: Namespace):
+    if args.debug:
+        log.setLevel(logging.DEBUG)

{pdfalyzer-1.17.1.dist-info → pdfalyzer-1.17.3.dist-info}/METADATA

@@ -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: 1.17.3
+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.dist-info → pdfalyzer-1.17.3.dist-info}/RECORD

@@ -1,13 +1,13 @@
 .pdfalyzer.example,sha256=sh_qkUBw4hfJia_Dx2wB-fsqJInhx2sSgA7WJz3MHYo,3917
-CHANGELOG.md,sha256=KtprK6EZ8FhdPWHs9E-YzGSqHxV_w0GnShvIJ6kMPss,13132
+CHANGELOG.md,sha256=ZFP4uDoiYT-kNa7XJuyNKhIjcvY5DU4CeMSGn0braPU,13301
 LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-pdfalyzer/__init__.py,sha256=TgCkfaaWuxv3sNMHcMZjh5lAw0oPNYKqJYRXVy9hPKo,6181
+pdfalyzer/__init__.py,sha256=2Gikt_-OSXZqeQij4wSwb65g7jycVAupjeFmXBf51lo,6159
 pdfalyzer/__main__.py,sha256=Ko_AoAyYMLIe_cmhiUSl6twheLZrGyT8aOSJ2CP7EZY,43
 pdfalyzer/binary/binary_scanner.py,sha256=gEHHdQ3lKe1P1441fk2OLO8GxJF7FxF8Tq04ElB8ilU,10748
 pdfalyzer/config.py,sha256=RBtp3Q6IvOW922rcanB4mVceJEM0BEjNybc6_vC7efY,2122
 pdfalyzer/decorators/document_model_printer.py,sha256=2tjJItZltukmOD2wjGvl2IsBM7Gug59wMHGLpzGDbV0,2682
 pdfalyzer/decorators/indeterminate_node.py,sha256=QLJr-nGKih8gPZcIqxLU028OwWWD5VjNHYMUjniwT_k,6586
-pdfalyzer/decorators/pdf_file.py,sha256=CHXyM8RIvnjKnsDOJxUhk-sfRzLLW50MJpKKTax6Eqk,10274
+pdfalyzer/decorators/pdf_file.py,sha256=Az3TL_Ttj_pDOHoHsiwpNlrCckCgKTp0VuGevJIi_5c,10481
 pdfalyzer/decorators/pdf_object_properties.py,sha256=Il3RObxQ4XUf0Ei-nd4tjJO0LeaxC6u7yFa3cQs_jVY,5485
 pdfalyzer/decorators/pdf_tree_node.py,sha256=4LReGJUtG8iEcLUQD1jW-yp3xPWsHrC-3Anbkt7XZ3A,11134
 pdfalyzer/decorators/pdf_tree_verifier.py,sha256=2hVe9APsAWQZ7ra8AGndHQnGWmmxmb3ZwfJHZuLvsvc,4714
@@ -17,7 +17,7 @@ pdfalyzer/detection/javascript_hunter.py,sha256=_wT2vkKTMlm_RGCjYsmwcmV-ag1qep3E
 pdfalyzer/detection/yaralyzer_helper.py,sha256=bfIa18f0zdUoOAJIQcwVDjF52sJNV47NdsDasg01uiQ,2194
 pdfalyzer/font_info.py,sha256=2R85iETY_1eKCeRrkqeIxfPDqXZyWfCNcHx_-aTyF0s,6682
 pdfalyzer/helpers/dict_helper.py,sha256=2TP0_EJBouaWD6jfnAekrEZ4M5eHKL8Tm61FgXZtBAg,303
-pdfalyzer/helpers/filesystem_helper.py,sha256=onXhSMhxo0YkvdKdosRwUo_RGdW6yNzZF5hfjgZ3GBE,5085
+pdfalyzer/helpers/filesystem_helper.py,sha256=QCdUcZlufBWaV38LlrQEGUGOGUtZEozMVSRkoTjwKlU,5046
 pdfalyzer/helpers/image_helper.py,sha256=QjoAUcKKEtpmuEyOmEfmaUN-lzNykQ1SzqgNn9-R4Y0,1120
 pdfalyzer/helpers/number_helper.py,sha256=8IlRmaOVLJsUV18VLvWRZU8SzRxL0XZjrY3sjmk2Ro4,292
 pdfalyzer/helpers/pdf_object_helper.py,sha256=65BlUgnDM9brxJFw_WF8QLomWHaNh-pj88NWoxcMkoQ,1160
@@ -35,8 +35,8 @@ pdfalyzer/output/tables/stream_objects_table.py,sha256=PgQj8oTtW5_X8SMQb3FvCWDS-
 pdfalyzer/pdf_object_relationship.py,sha256=tOJTp73m82oNZJB7NxvTLv167kqthH8PRbVnev_4uEk,5291
 pdfalyzer/pdfalyzer.py,sha256=T5U8MZRlL0Kn-GJVqfIIoL7eBUdQeteu50VhQ-IoYh0,11214
 pdfalyzer/util/adobe_strings.py,sha256=eF4K1RhhR_qgMBT58MzCxWkqQj17OWLCNmG3SjZ9BUs,5045
-pdfalyzer/util/argument_parser.py,sha256=OdvGCowGnVNyulqC5968myCxY4gRu6--WmCIdkiXoWA,9732
-pdfalyzer/util/cli_tools_argument_parser.py,sha256=EE-lk1ZMv3JlZlZ9N3rAndIlYl1__C0iYG0Ti6MEHjM,6107
+pdfalyzer/util/argument_parser.py,sha256=9ixQMEZz00IPK8xRxuS7DMrQgXIrqhB2ve5W8XTZ1S8,9732
+pdfalyzer/util/cli_tools_argument_parser.py,sha256=RqK_5AWC7qm9Zy7pvDb-J1WSEGBkIyxzNDcFJwSmuX4,6285
 pdfalyzer/util/debugging.py,sha256=hjYGxptJmal9TTaAUkkoo0oNu2tdx6ZYSyC0WjvzHh0,156
 pdfalyzer/util/exceptions.py,sha256=XLFFTdx1n6i_VCmvuzvIOCa-djJvGEitfo9lhy3zq0k,98
 pdfalyzer/util/page_range.py,sha256=NMNh3_TojxTxBIpvUYK1AmvID_m8qOP6AihZrLWZF2I,1652
@@ -47,8 +47,8 @@ pdfalyzer/yara_rules/__init.py__,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hS
 pdfalyzer/yara_rules/didier_stevens.yara,sha256=4XhqafU09xzYUP7LCygHHBXOpAXUblJf6Tkn37MUy0w,7253
 pdfalyzer/yara_rules/lprat.static_file_analysis.yara,sha256=i0CwRH8pBx_QshKFTQtr1CP5n378EZelsF2FxMY2y5A,21859
 pdfalyzer/yara_rules/pdf_malware.yara,sha256=jDqSTP5BQSi2I_1xZiFZdy68I4oVWDat2j08-qdfbto,91063
-pdfalyzer-1.17.1.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-pdfalyzer-1.17.1.dist-info/METADATA,sha256=nla_K-pZ8XoknqbcCqi90EPydVJ7STe6DDBfOOf_Dso,27309
-pdfalyzer-1.17.1.dist-info/WHEEL,sha256=d2fvjOD7sXsVzChCqf0Ty0JbHKBaLYwDbGQDwQTnJ50,88
-pdfalyzer-1.17.1.dist-info/entry_points.txt,sha256=goHVADdqEFcniu4O0k7kabc2rLf3wvRrENJK6c9IkUw,249
-pdfalyzer-1.17.1.dist-info/RECORD,,
+pdfalyzer-1.17.3.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+pdfalyzer-1.17.3.dist-info/METADATA,sha256=MczhorkJI7ozznrHf72k7a0QELDinDNHhex4ur8kSr8,27294
+pdfalyzer-1.17.3.dist-info/WHEEL,sha256=d2fvjOD7sXsVzChCqf0Ty0JbHKBaLYwDbGQDwQTnJ50,88
+pdfalyzer-1.17.3.dist-info/entry_points.txt,sha256=5ve7Ydx0p33ZuQWol6wIFAPPUgQrEQoJkOy06mD5t9Y,237
+pdfalyzer-1.17.3.dist-info/RECORD,,

{pdfalyzer-1.17.1.dist-info → pdfalyzer-1.17.3.dist-info}/entry_points.txt

@@ -1,7 +1,7 @@
 [console_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