Change Text extraction is not allowed error to warning (#453)

* Changed error to warning for 'Text extraction is not allowed'

* updated changelog

* fix lint

* made changes suggested in review

* Update CHANGELOG.md

* Add regression test for failing pdf

* Reduce line length to <80

Co-authored-by: Pieter Marsman <pietermarsman@gmail.com>

CHANGELOG.md

@@ -10,6 +10,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
 ### Changed
 - Hiding fallback xref by default from dumppdf.py output ([#431](https://github.com/pdfminer/pdfminer.six/pull/431))
+- Raise a warning instead of an error when extracting text from a non-extractable PDF ([#350](https://github.com/pdfminer/pdfminer.six/issues/350))
   
 ## [20200517]
 

pdfminer/high_level.py

@@ -80,8 +80,7 @@ def extract_text_to_fp(inf, outfp, output_type='text', codec='utf-8',
                                   page_numbers,
                                   maxpages=maxpages,
                                   password=password,
-                                  caching=not disable_caching,
+                                  caching=not disable_caching):
-                                  check_extractable=True):
         page.rotate = (page.rotate + rotation) % 360
         interpreter.process_page(page)
 
@@ -118,7 +117,6 @@ def extract_text(pdf_file, password='', page_numbers=None, maxpages=0,
                 maxpages=maxpages,
                 password=password,
                 caching=caching,
-                check_extractable=True,
         ):
             interpreter.process_page(page)
 

pdfminer/pdfdocument.py

@@ -44,7 +44,11 @@ class PDFPasswordIncorrect(PDFEncryptionError):
     pass
 
 
-class PDFTextExtractionNotAllowed(PDFEncryptionError):
+class PDFTextExtractionNotAllowedWarning(UserWarning):
+    pass
+
+
+class PDFTextExtractionNotAllowedError(PDFEncryptionError):
     pass
 
 

pdfminer/pdfpage.py

@@ -1,4 +1,5 @@
 import logging
+import warnings
 from . import settings
 from .psparser import LIT
 from .pdftypes import PDFObjectNotFound
@@ -8,7 +9,8 @@ from .pdftypes import list_value
 from .pdftypes import dict_value
 from .pdfparser import PDFParser
 from .pdfdocument import PDFDocument
-from .pdfdocument import PDFTextExtractionNotAllowed
+from .pdfdocument import PDFTextExtractionNotAllowedWarning
+from .pdfdocument import PDFTextExtractionNotAllowedError
 
 
 log = logging.getLogger(__name__)
@@ -120,15 +122,23 @@ class PDFPage:
     @classmethod
     def get_pages(cls, fp,
                   pagenos=None, maxpages=0, password='',
-                  caching=True, check_extractable=True):
+                  caching=True, check_extractable=False):
         # Create a PDF parser object associated with the file object.
         parser = PDFParser(fp)
         # Create a PDF document object that stores the document structure.
         doc = PDFDocument(parser, password=password, caching=caching)
-        # Check if the document allows text extraction. If not, abort.
+        # Check if the document allows text extraction.
-        if check_extractable and not doc.is_extractable:
+        # If not, warn the user and proceed.
+        if not doc.is_extractable:
+            if check_extractable:
                 error_msg = 'Text extraction is not allowed: %r' % fp
-            raise PDFTextExtractionNotAllowed(error_msg)
+                raise PDFTextExtractionNotAllowedError(error_msg)
+            else:
+                warning_msg = 'The PDF %r contains a metadata field '\
+                            'indicating that it should not allow '   \
+                            'text extraction. Ignoring this field '  \
+                            'and proceeding.' % fp
+                warnings.warn(warning_msg, PDFTextExtractionNotAllowedWarning)
         # Process each page contained in the document.
         for (pageno, page) in enumerate(cls.create_pages(doc)):
             if pagenos and (pageno not in pagenos):

tests/test_tools_pdf2txt.py

@@ -60,12 +60,17 @@ class TestPdf2Txt():
     def test_contrib_2b(self):
         run('contrib/2b.pdf', '-A -t xml')
 
+    def test_contrib_issue_350(self):
+        """Regression test for
+        https://github.com/pdfminer/pdfminer.six/issues/350"""
+        run('contrib/issue-00352-asw-oct96-p41.pdf')
+
     def test_scancode_patchelf(self):
         """Regression test for # https://github.com/euske/pdfminer/issues/96"""
         run('scancode/patchelf.pdf')
 
     def test_contrib_hash_two_complement(self):
-        """Check that unsigned integer is added correctly to encryption hash.
+        """Check that unsigned integer is added correctly to encryption hash.et
 
         See https://github.com/pdfminer/pdfminer.six/issues/186
         """