Add support for hide-annotations flag

Author: StaticRocket

README.md

@@ -82,6 +82,7 @@ Here are the definitions:
 - `grayscale` parameter allows you to convert images to grayscale (`-gray` in pdftoppm CLI)
 - `single_file` parameter allows you to convert the first PDF page only, without adding digits at the end of the `output_file`
 - Allow the user to specify poppler's installation path with `poppler_path`
+- Allow users to hide attributes when using pdftoppm with `hide_attributes`
 
 ## Performance tips
 

docs/reference.md

@@ -26,6 +26,7 @@ convert_from_path(
     grayscale=False,
     size=None,
     paths_only=False,
+    hide_annotations=False,
 )
 
 convert_from_bytes(
@@ -47,6 +48,7 @@ convert_from_bytes(
     grayscale=False,
     size=None,
     paths_only=False,
+    hide_annotations=False,
 )
 ```
 
@@ -150,7 +152,12 @@ A list of image paths rather than preloaded images are returned.
 
 Provide additional options for jpeg format conversions. Requires `fmt="jpeg"` and is provided as dict, with all
 optinal keywords:
-`jpegopt={"quality": 100, "optimize": True, "progressive": False}
+`jpegopt={"quality": 100, "optimize": True, "progressive": False}`
+
+**hide_annotations**
+
+Hide link bounding boxes and other PDF annotations. This is only implemented in pdftoppm at the moment so it
+cannot be combined with pdftocairo flags.
 
 ## Exceptions
 

pdf2image/pdf2image.py

@@ -55,6 +55,7 @@ def convert_from_path(
     paths_only=False,
     use_pdftocairo=False,
     timeout=None,
+    hide_annotations=False,
 ):
     """
         Description: Convert PDF to Image will throw whenever one of the condition is reached
@@ -115,6 +116,9 @@ def convert_from_path(
     if poppler_version_major == 0 and poppler_version_minor <= 57:
         jpegopt = None
 
+    if poppler_version_major == 0 and poppler_version_minor <= 83:
+        hide_annotations = False
+
     # If output_file isn't a generator, it will be turned into one
     if not isinstance(output_file, types.GeneratorType) and not isinstance(
         output_file, ThreadSafeGenerator
@@ -170,9 +174,12 @@ def convert_from_path(
             single_file,
             grayscale,
             size,
+            hide_annotations,
         )
 
         if use_pdfcairo:
+            if hide_annotations:
+                raise NotImplementedError("Hide annotations flag not implemented in pdftocairo.")
             args = [_get_command_path("pdftocairo", poppler_path)] + args
         else:
             args = [_get_command_path("pdftoppm", poppler_path)] + args
@@ -241,6 +248,7 @@ def convert_from_bytes(
     paths_only=False,
     use_pdftocairo=False,
     timeout=None,
+    hide_annotations=False,
 ):
     """
         Description: Convert PDF to Image will throw whenever one of the condition is reached
@@ -293,6 +301,7 @@ def convert_from_bytes(
                 paths_only=paths_only,
                 use_pdftocairo=use_pdftocairo,
                 timeout=timeout,
+                hide_annotations=hide_annotations,
             )
     finally:
         os.close(fh)
@@ -313,10 +322,14 @@ def _build_command(
     single_file,
     grayscale,
     size,
+    hide_annotations,
 ):
     if use_cropbox:
         args.append("-cropbox")
 
+    if hide_annotations:
+        args.append("-hide-annotations")
+
     if transparent and fmt in TRANSPARENT_FILE_TYPES:
         args.append("-transp")
 

tests.py

@@ -1492,6 +1492,55 @@ def test_conversion_from_path_with_2d_tuple_size_with_None_height(self):
             )
         )
 
+    ## Test hide annotations parameter
+
+    @profile
+    @unittest.skipIf(not POPPLER_INSTALLED, "Poppler is not installed!")
+    def test_conversion_from_path_with_hide_annotations(self):
+        images_from_path = convert_from_path("./tests/test_annotations.pdf", hide_annotations=True)
+        start_time = time.time()
+        self.assertTrue(len(images_from_path) == 1)
+        print(
+            "test_conversion_from_path_with_hide_annotations: {} sec".format(
+                time.time() - start_time
+            )
+        )
+
+    @profile
+    @unittest.skipIf(not POPPLER_INSTALLED, "Poppler is not installed!")
+    def test_conversion_from_bytes_with_hide_annotations(self):
+        start_time = time.time()
+        with open("./tests/test_annotations.pdf", "rb") as pdf_file:
+            images_from_bytes = convert_from_bytes(
+                pdf_file.read(),
+                hide_annotations=True,
+            )
+            self.assertTrue(len(images_from_bytes) == 1)
+        print(
+            "test_conversion_from_bytes_with_hide_annotations: {} sec".format(
+                time.time() - start_time
+            )
+        )
+
+    @profile
+    @unittest.skipIf(not POPPLER_INSTALLED, "Poppler is not installed!")
+    def test_conversion_from_path_with_hide_annotations_with_invalid_arg_combination(self):
+        start_time = time.time()
+        try:
+            images_from_path = convert_from_path(
+                "./tests/test_annotations.pdf",
+                hide_annotations=True,
+                use_pdftocairo=True,
+            )
+            raise Exception("This should not happen")
+        except NotImplementedError:
+            pass
+        print(
+            "test_conversion_from_path_with_hide_annotations_with_invalid_arg_combination: {} sec".format(
+                time.time() - start_time
+            )
+        )
+
     ## Test pdfinfo
 
     @profile