pdfalyzer 1.17.2__py3-none-any.whl → 1.17.4__py3-none-any.whl

CHANGELOG.md

@@ -1,5 +1,11 @@
 # NEXT RELEASE
 
+### 1.17.4
+* Make `PIL` a lazy import so installs without `[extract]` extras don't fail
+
+### 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`

pdfalyzer/decorators/pdf_file.py

@@ -20,6 +20,8 @@ from pdfalyzer.helpers.rich_text_helper import (attention_getting_panel, error_t
 from pdfalyzer.helpers.string_helper import exception_str
 from pdfalyzer.util.page_range import PageRange
 
+DEPENDENCY_ERROR_MSG = "Pdfalyzer is missing an optional dependency required to extract text. " + \
+                       "Try 'pip install pdfalyzer[extract]'"
 DEFAULT_PDF_ERRORS_DIR = Path.cwd().joinpath('pdf_errors')
 MIN_PDF_SIZE_TO_LOG_PROGRESS_TO_STDERR = 1024 * 1024 * 20
 
@@ -54,11 +56,11 @@ class PdfFile:
         self.file_size = self.file_path.stat().st_size
 
     def extract_page_range(
-            self,
-            page_range: PageRange,
-            destination_dir: Optional[Path] = None,
-            extra_file_suffix: Optional[str] = None
-        ) -> Path:
+        self,
+        page_range: PageRange,
+        destination_dir: Optional[Path] = None,
+        extra_file_suffix: Optional[str] = None
+    ) -> Path:
         """
         Extract a range of pages to a new PDF file.
 
@@ -86,7 +88,7 @@ class PdfFile:
 
         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)
-        console.print(f"Extracting {page_range.file_suffix()} from '{self.file_path}' to '{extracted_pages_pdf_path}'...")
+        console.print(f"Extracting {page_range.file_suffix()} from '{self.file_path}' to '{extracted_pages_pdf_path}'")
         pdf_writer = PdfWriter()
 
         with open(self.file_path, 'rb') as source_pdf:
@@ -99,11 +101,11 @@ class PdfFile:
         return extracted_pages_pdf_path
 
     def extract_text(
-            self,
-            page_range: Optional[PageRange] = None,
-            logger: Optional[Logger] = None,
-            print_as_parsed: bool = False
-        ) -> Optional[str]:
+        self,
+        page_range: Optional[PageRange] = None,
+        logger: Optional[Logger] = None,
+        print_as_parsed: bool = False
+    ) -> Optional[str]:
         """
         Use PyPDF to extract text page by page and use Tesseract to OCR any embedded images.
 
@@ -167,7 +169,7 @@ class PdfFile:
                 if print_as_parsed:
                     print(f"{page_text}")
         except DependencyError:
-            log.error("Pdfalyzer is missing an optional dependency required to extract text. Try 'pip install pdfalyzer[extract]'")
+            log.error(DEPENDENCY_ERROR_MSG)
         except EmptyFileError:
             log.warning("Skipping empty file!")
         except PdfStreamError as e:
@@ -190,7 +192,8 @@ class PdfFile:
 
         try:
             extracted_file = self.extract_page_range(PageRange(str(page_number)), destination_dir, error_msg)
-        except Exception as e:
+        except Exception:
+            stderr_console.print_exception()
             stderr_console.print(error_text(f"Failed to extract a page for submission to PyPDF team."))
             extracted_file = None
 
@@ -215,10 +218,3 @@ 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/helpers/image_helper.py

@@ -1,6 +1,5 @@
 from typing import Optional
 
-from PIL import Image
 from yaralyzer.output.rich_console import console
 
 from pdfalyzer.helpers.rich_text_helper import warning_text
@@ -9,11 +8,12 @@ from pdfalyzer.helpers.rich_text_helper import warning_text
 def ocr_text(image: Image.Image, image_name: str) -> Optional[str]:
     """Use pytesseract to OCR the text in the image and return it as a string."""
     import pytesseract
+    from PIL import Image
     text = None
 
     try:
         text = pytesseract.image_to_string(image)
-    except pytesseract.pytesseract.TesseractError as e:
+    except pytesseract.pytesseract.TesseractError:
         console.print_exception()
         console.print(warning_text(f"Tesseract OCR failure '{image_name}'! No OCR text extracted..."))
     except OSError as e:

pdfalyzer/util/cli_tools_argument_parser.py

@@ -5,6 +5,7 @@ Argument parsers for the command line tools other than `pdfalyze` that are inclu
 2. extract_pdf_pages
 3. extract_pdf_text
 """
+import logging
 import sys
 from argparse import ArgumentParser, Namespace
 from pathlib import Path
@@ -88,6 +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,
@@ -109,6 +111,7 @@ 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
 
 
@@ -122,6 +125,7 @@ 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,
@@ -129,7 +133,7 @@ extract_text_parser.add_argument('--page-range', '-r',
 
 extract_text_parser.add_argument('--print-as-parsed', '-p',
                                  action='store_true',
-                                 help='print pages as they are parsed instead of waiting until document is fully parsed')
+                                 help='print pages as they are parsed instead of waiting until parsing complete')
 
 
 def parse_text_extraction_args() -> Namespace:
@@ -151,4 +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-1.17.2.dist-info → pdfalyzer-1.17.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pdfalyzer
-Version: 1.17.2
+Version: 1.17.4
 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

{pdfalyzer-1.17.2.dist-info → pdfalyzer-1.17.4.dist-info}/RECORD

@@ -1,5 +1,5 @@
 .pdfalyzer.example,sha256=sh_qkUBw4hfJia_Dx2wB-fsqJInhx2sSgA7WJz3MHYo,3917
-CHANGELOG.md,sha256=Zzq920SR4HeZjCDlqqVoLCPrc1hd5rqJQxih5p3aK1I,13250
+CHANGELOG.md,sha256=dyXJVhpeNYDdeh8Ugfl7co6v86ksu_AtNOYKEm2U5TI,13390
 LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
 pdfalyzer/__init__.py,sha256=2Gikt_-OSXZqeQij4wSwb65g7jycVAupjeFmXBf51lo,6159
 pdfalyzer/__main__.py,sha256=Ko_AoAyYMLIe_cmhiUSl6twheLZrGyT8aOSJ2CP7EZY,43
@@ -7,7 +7,7 @@ pdfalyzer/binary/binary_scanner.py,sha256=gEHHdQ3lKe1P1441fk2OLO8GxJF7FxF8Tq04El
 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=KstGLrBHGio867l-ieVWR_Sps9Yy5z29Q0jBun9g68o,10746
+pdfalyzer/decorators/pdf_file.py,sha256=ryAYzzsO8Fw5_ZMoomruW0Bal8pTb5C0VlLOTjdVqNI,10552
 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
@@ -18,7 +18,7 @@ pdfalyzer/detection/yaralyzer_helper.py,sha256=bfIa18f0zdUoOAJIQcwVDjF52sJNV47Nd
 pdfalyzer/font_info.py,sha256=2R85iETY_1eKCeRrkqeIxfPDqXZyWfCNcHx_-aTyF0s,6682
 pdfalyzer/helpers/dict_helper.py,sha256=2TP0_EJBouaWD6jfnAekrEZ4M5eHKL8Tm61FgXZtBAg,303
 pdfalyzer/helpers/filesystem_helper.py,sha256=QCdUcZlufBWaV38LlrQEGUGOGUtZEozMVSRkoTjwKlU,5046
-pdfalyzer/helpers/image_helper.py,sha256=QjoAUcKKEtpmuEyOmEfmaUN-lzNykQ1SzqgNn9-R4Y0,1120
+pdfalyzer/helpers/image_helper.py,sha256=E3Mby-KG-1eIYThuYqXEkwG1mnhY0imvrpiO8N8otfQ,1119
 pdfalyzer/helpers/number_helper.py,sha256=8IlRmaOVLJsUV18VLvWRZU8SzRxL0XZjrY3sjmk2Ro4,292
 pdfalyzer/helpers/pdf_object_helper.py,sha256=65BlUgnDM9brxJFw_WF8QLomWHaNh-pj88NWoxcMkoQ,1160
 pdfalyzer/helpers/rich_text_helper.py,sha256=Q5Zj0I96ymQmDWHkOX4lWEvkizOMMgzYNx4CF35t_7w,3561
@@ -36,7 +36,7 @@ pdfalyzer/pdf_object_relationship.py,sha256=tOJTp73m82oNZJB7NxvTLv167kqthH8PRbVn
 pdfalyzer/pdfalyzer.py,sha256=T5U8MZRlL0Kn-GJVqfIIoL7eBUdQeteu50VhQ-IoYh0,11214
 pdfalyzer/util/adobe_strings.py,sha256=eF4K1RhhR_qgMBT58MzCxWkqQj17OWLCNmG3SjZ9BUs,5045
 pdfalyzer/util/argument_parser.py,sha256=9ixQMEZz00IPK8xRxuS7DMrQgXIrqhB2ve5W8XTZ1S8,9732
-pdfalyzer/util/cli_tools_argument_parser.py,sha256=8bW0B4UXXkwuxNwDRe9MyXucTFm0pZRyOq98CO8D_Hs,5925
+pdfalyzer/util/cli_tools_argument_parser.py,sha256=HyZhztyrPtbvOswmG975M0tK5KPon37lV3fxVA0OwYo,6277
 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-1.17.2.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-pdfalyzer-1.17.2.dist-info/METADATA,sha256=y8x6ka9yoCPuU98_oLBzaNK4wXBWXy_2NLA7jYp4l9U,27294
-pdfalyzer-1.17.2.dist-info/WHEEL,sha256=d2fvjOD7sXsVzChCqf0Ty0JbHKBaLYwDbGQDwQTnJ50,88
-pdfalyzer-1.17.2.dist-info/entry_points.txt,sha256=5ve7Ydx0p33ZuQWol6wIFAPPUgQrEQoJkOy06mD5t9Y,237
-pdfalyzer-1.17.2.dist-info/RECORD,,
+pdfalyzer-1.17.4.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+pdfalyzer-1.17.4.dist-info/METADATA,sha256=plr6KKGy51GfRWhsqIku4u4nkMoHwM5xMLmV9Lm38ak,27294
+pdfalyzer-1.17.4.dist-info/WHEEL,sha256=d2fvjOD7sXsVzChCqf0Ty0JbHKBaLYwDbGQDwQTnJ50,88
+pdfalyzer-1.17.4.dist-info/entry_points.txt,sha256=5ve7Ydx0p33ZuQWol6wIFAPPUgQrEQoJkOy06mD5t9Y,237
+pdfalyzer-1.17.4.dist-info/RECORD,,