pdfminer/settings.py for STRICT and added ENFORCE_CHECK_EXTRACTABLE

pdfminer/pdfdocument.py

@@ -19,7 +19,7 @@ from .psparser import PSEOF
 from .psparser import literal_name
 from .psparser import LIT
 from .psparser import KWD
-from .psparser import STRICT
+from .settings import STRICT
 from .pdftypes import PDFException
 from .pdftypes import PDFTypeError
 from .pdftypes import PDFStream

pdfminer/pdffont.py

@@ -12,7 +12,7 @@ from .psparser import PSStackParser
 from .psparser import PSEOF
 from .psparser import LIT
 from .psparser import KWD
-from .psparser import STRICT
+from .settings import STRICT
 from .psparser import PSLiteral
 from .psparser import literal_name
 from .pdftypes import PDFException

pdfminer/pdfinterp.py

@@ -12,7 +12,7 @@ from .psparser import keyword_name
 from .psparser import PSStackParser
 from .psparser import LIT
 from .psparser import KWD
-from .psparser import STRICT
+from .settings import STRICT
 from .pdftypes import PDFException
 from .pdftypes import PDFStream
 from .pdftypes import PDFObjRef

pdfminer/pdfpage.py

@@ -9,6 +9,7 @@ from .pdftypes import dict_value
 from .pdfparser import PDFParser
 from .pdfdocument import PDFDocument
 from .pdfdocument import PDFTextExtractionNotAllowed
+from .settings import ENFORCE_CHECK_EXTRACTABLE
 
 import six # Python 2+3 compatibility
 
@@ -120,6 +121,7 @@ class PDFPage(object):
         # 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.
+        if ENFORCE_CHECK_EXTRACTABLE:
             if check_extractable and not doc.is_extractable:
                 raise PDFTextExtractionNotAllowed('Text extraction is not allowed: %r' % fp)
         # Process each page contained in the document.

pdfminer/pdfparser.py

@@ -5,7 +5,7 @@ from .psparser import PSStackParser
 from .psparser import PSSyntaxError
 from .psparser import PSEOF
 from .psparser import KWD
-from .psparser import STRICT
+from .settings import STRICT
 from .pdftypes import PDFException
 from .pdftypes import PDFStream
 from .pdftypes import PDFObjRef

pdfminer/pdftypes.py

@@ -8,7 +8,7 @@ from .ccitt import ccittfaxdecode
 from .psparser import PSException
 from .psparser import PSObject
 from .psparser import LIT
-from .psparser import STRICT
+from .settings import STRICT
 from .utils import apply_png_predictor
 from .utils import isnumber
 

pdfminer/psparser.py

@@ -5,12 +5,8 @@ import re
 import logging
 
 import six # Python 2+3 compatibility
-try:
-    from django.conf import settings
-except ImportError:
-    # in case it's not a django project
-    settings = None
 
+from .settings import STRICT
 
 def bytesindex(s,i,j=None):
     """implements s[i], s[i:], s[i:j] for Python2 and Python3"""
@@ -21,7 +17,6 @@ def bytesindex(s,i,j=None):
 
 from .utils import choplist
 
-STRICT = getattr(settings, 'PDF_MINER_IS_STRICT', True)
 
 ##  PS Exceptions
 ##

pdfminer/settings.py

@@ -0,0 +1,9 @@
+try:
+    from django.conf import django_settings
+except ImportError:
+    # in case it's not a django project
+    django_settings = None
+
+# Get defaults from django settings
+STRICT = getattr(django_settings, 'PDF_MINER_IS_STRICT', True)
+ENFORCE_CHECK_EXTRACTABLE = True

tools/pdf2txt.py

@@ -5,6 +5,9 @@ Converts PDF text content (though not images containing text) to plain text, htm
 import sys
 import logging
 import six
+import pdfminer.settings
+pdfminer.settings.STRICT = False
+pdfminer.settings.ENFORCE_CHECK_EXTRACTABLE = False
 import pdfminer.high_level
 import pdfminer.layout