diff --git a/tests/test_pdf.py b/tests/test_pdf.py
index 9c0bca67..80310cc8 100644
--- a/tests/test_pdf.py
+++ b/tests/test_pdf.py
@@ -25,6 +25,26 @@ def test_tesseract_cli(self):
             method='tesseract',
         )
 
+    def test_tesseract_cli(self):
+        """confirm fallback to pdf extraction with tesseract if no text is found"""
+        d = self.get_extension_directory()
+        self.compare_cli_output(
+            os.path.join(d, "ocr_text.pdf"),
+            expected_filename=os.path.join(d, "ocr_text.txt")
+        )
+    def test_large_pdf(self):
+        """Make sure extraction does not hang (issue #33)"""
+
+        # download the file
+        filename = os.path.join(self.get_extension_directory(), "large.pdf")
+        self.download_file(
+            "https://openknowledge.worldbank.org/bitstream/handle/10986/16091/9780821399378.pdf",
+            filename,
+        )
+
+        # make sure textract can successfully run
+        self.assertSuccessfulTextract(filename)
+
     def test_two_column(self):
         """Preserve two column layout in extraction"""
         filename = os.path.join(self.get_extension_directory(), 'two_column.pdf')
diff --git a/textract/parsers/pdf_parser.py b/textract/parsers/pdf_parser.py
index 9fe74e13..effabaed 100644
--- a/textract/parsers/pdf_parser.py
+++ b/textract/parsers/pdf_parser.py
@@ -18,22 +18,23 @@ class Parser(ShellParser):
     def extract(self, filename, method='', **kwargs):
         if method == '' or method == 'pdftotext':
             try:
-                return self.extract_pdftotext(filename, **kwargs)
+                text = self.extract_pdftotext(filename, **kwargs)
             except ShellError as ex:
                 # If pdftotext isn't installed and the pdftotext method
                 # wasn't specified, then gracefully fallback to using
                 # pdfminer instead.
                 if method == '' and ex.is_not_installed():
-                    return self.extract_pdfminer(filename, **kwargs)
+                    text = self.extract_pdfminer(filename, **kwargs)
                 else:
                     raise ex
 
         elif method == 'pdfminer':
-            return self.extract_pdfminer(filename, **kwargs)
+            text = self.extract_pdfminer(filename, **kwargs)
         elif method == 'tesseract':
-            return self.extract_tesseract(filename, **kwargs)
+            text = self.extract_tesseract(filename, **kwargs)
         else:
             raise UnknownMethod(method)
+        return text if text.strip() else self.extract_tesseract(filename, **kwargs)
 
     def extract_pdftotext(self, filename, **kwargs):
         """Extract text from pdfs using the pdftotext command line utility."""