natural-pdf 25.3.16__py3-none-any.whl → 25.3.16.2__py3-none-any.whl

examples/url_pdf_example.py

@@ -0,0 +1,45 @@
+#!/usr/bin/env python3
+"""
+Example demonstrating loading a PDF from a URL.
+"""
+import sys
+import os
+import argparse
+
+# Add the parent directory to the path so we can import the natural_pdf package
+sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
+
+from natural_pdf import PDF
+
+def main():
+    parser = argparse.ArgumentParser(description="Example of loading a PDF from a URL")
+    parser.add_argument('url', nargs='?', 
+                      default="https://arxiv.org/pdf/2103.14749.pdf",
+                      help="URL to a PDF document (default: an arXiv paper)")
+    args = parser.parse_args()
+    
+    print(f"Loading PDF from URL: {args.url}")
+    
+    # Open the PDF from URL
+    with PDF(args.url) as pdf:
+        # Display basic document info
+        print(f"Document loaded successfully: {len(pdf)} pages")
+        
+        # Extract text from the first page
+        if len(pdf) > 0:
+            page = pdf.pages[0]
+            
+            # Get the title (usually large text on the first page)
+            title = page.find_all('text[size>=12]')
+            if title:
+                print("\nTitle candidates:")
+                for i, t in enumerate(title[:3], 1):  # Show top 3 candidates
+                    print(f"{i}. {t.text}")
+            
+            # Extract the first 200 characters of text
+            text = page.extract_text()
+            preview = text[:200] + "..." if len(text) > 200 else text
+            print(f"\nText preview:\n{preview}")
+
+if __name__ == "__main__":
+    main()

natural_pdf/core/pdf.py

@@ -1,5 +1,9 @@
 import pdfplumber
 import logging
+import tempfile
+import os
+import re
+import urllib.request
 from typing import List, Optional, Union, Any, Dict, Callable, Tuple, Type
 
 from natural_pdf.core.page import Page
@@ -28,7 +32,7 @@ class PDF:
     with improved selection, navigation, and extraction capabilities.
     """
     
-    def __init__(self, path: str, reading_order: bool = True, 
+    def __init__(self, path_or_url: str, reading_order: bool = True, 
                  ocr: Optional[Union[bool, str, List, Dict]] = None,
                  ocr_engine: Optional[Union[str, Any]] = None,
                  font_attrs: Optional[List[str]] = None,
@@ -37,7 +41,7 @@ class PDF:
         Initialize the enhanced PDF object.
         
         Args:
-            path: Path to the PDF file
+            path_or_url: Path to the PDF file or a URL to a PDF
             reading_order: Whether to use natural reading order
             ocr: OCR configuration:
                  - None or False: OCR disabled
@@ -58,6 +62,40 @@ class PDF:
                        True: Spaces are part of words, better for multi-word searching
                        False: Break text at spaces, each word is separate (legacy behavior)
         """
+        # Check if the input is a URL
+        is_url = path_or_url.startswith('http://') or path_or_url.startswith('https://')
+        
+        # Initialize path-related attributes
+        self._original_path = path_or_url
+        self._temp_file = None
+        
+        if is_url:
+            logger.info(f"Downloading PDF from URL: {path_or_url}")
+            try:
+                # Create a temporary file to store the downloaded PDF
+                self._temp_file = tempfile.NamedTemporaryFile(suffix='.pdf', delete=False)
+                
+                # Download the PDF
+                with urllib.request.urlopen(path_or_url) as response:
+                    self._temp_file.write(response.read())
+                    self._temp_file.flush()
+                    self._temp_file.close()
+                
+                # Use the temporary file path
+                path = self._temp_file.name
+                logger.info(f"PDF downloaded to temporary file: {path}")
+            except Exception as e:
+                if self._temp_file and hasattr(self._temp_file, 'name'):
+                    try:
+                        os.unlink(self._temp_file.name)
+                    except:
+                        pass
+                logger.error(f"Failed to download PDF from URL: {e}")
+                raise ValueError(f"Failed to download PDF from URL: {e}")
+        else:
+            # Use the provided path directly
+            path = path_or_url
+            
         logger.info(f"Initializing PDF from {path}")
         logger.debug(f"Parameters: reading_order={reading_order}, ocr={ocr}, ocr_engine={ocr_engine}, font_attrs={font_attrs}, keep_spaces={keep_spaces}")
         
@@ -558,10 +596,21 @@ class PDF:
         return self.pages[key]
         
     def close(self):
-        """Close the underlying PDF file."""
+        """Close the underlying PDF file and clean up any temporary files."""
         if hasattr(self, '_pdf') and self._pdf is not None:
             self._pdf.close()
             self._pdf = None
+            
+        # Clean up temporary file if it exists
+        if hasattr(self, '_temp_file') and self._temp_file is not None:
+            try:
+                if os.path.exists(self._temp_file.name):
+                    os.unlink(self._temp_file.name)
+                    logger.debug(f"Removed temporary PDF file: {self._temp_file.name}")
+            except Exception as e:
+                logger.warning(f"Failed to clean up temporary PDF file: {e}")
+            finally:
+                self._temp_file = None
     
     def __enter__(self):
         """Context manager entry."""

{natural_pdf-25.3.16.dist-info → natural_pdf-25.3.16.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: natural-pdf
-Version: 25.3.16
+Version: 25.3.16.2
 Summary: A more intuitive interface for working with PDFs
 Home-page: https://github.com/jsoma/natural-pdf
 Author: Jonathan Soma
@@ -15,6 +15,7 @@ Requires-Dist: pdfplumber>=0.7.0
 Requires-Dist: Pillow>=8.0.0
 Requires-Dist: colour>=0.1.5
 Requires-Dist: numpy>=1.20.0
+Requires-Dist: urllib3>=1.26.0
 Requires-Dist: doclayout_yolo>=0.0.3
 Requires-Dist: torch>=2.0.0
 Requires-Dist: torchvision>=0.15.0
@@ -58,7 +59,8 @@ A friendly library for working with PDFs, built on top of [pdfplumber](https://g
 
 Natural PDF lets you find and extract content from PDFs using simple code that makes sense.
 
-[Complete documentation here](https://jsoma.github.io/natural-pdf)
+- [Complete documentation here](https://jsoma.github.io/natural-pdf)
+- [Live demo here](https://colab.research.google.com/github/jsoma/)
 
 ## Features
 
@@ -96,9 +98,12 @@ pip install natural-pdf[easyocr,paddle]
 ```python
 from natural_pdf import PDF
 
-# Open a PDF
+# Open a local PDF
 pdf = PDF('document.pdf')
 
+# Or open a PDF from a URL
+pdf = PDF('https://example.com/document.pdf')
+
 # Get the first page
 page = pdf.pages[0]
 

{natural_pdf-25.3.16.dist-info → natural_pdf-25.3.16.2.dist-info}/RECORD

@@ -70,6 +70,7 @@ examples/text_style_example.py,sha256=pgLb9rbBrERj18icRsrSIgs0ndKuKcBWycwVPAAynr
 examples/tiny-text.py,sha256=X_SDThngugL8q-XvcKlRe8iNUqouxT3rYCDFqK2MRyo,1693
 examples/until_boundaries_example.py,sha256=rN8YrwDM7rBb1PuxYkpszYVWT-tNMSD-aKF-2zLBoHo,6461
 examples/until_example.py,sha256=4b3GyQxaayGfODiXaCgxcq_92gUgpqaJ0_lMWQnYD_0,4559
+examples/url_pdf_example.py,sha256=WjZMlKyIlcXhJNdSe9uMmWdTHixnRfeacnp64gQkNAo,1545
 examples/very_basics.py,sha256=cNLnr1z701ri0LgE1cVM4gfMMND0C9UnvvWybnwum6g,418
 natural_pdf/__init__.py,sha256=kKHL7SWzk0_ydDDX12X5W3s9-vEKgVYOBubXzp_SCdM,1784
 natural_pdf/analyzers/__init__.py,sha256=XhxlbwiqbGpeIlS88c4P2t7-MLP98U3CcIr-3nGp488,188
@@ -77,7 +78,7 @@ natural_pdf/analyzers/document_layout.py,sha256=VHZTiiEZByhYUBHqOqmNIgj59zhc3ZNK
 natural_pdf/analyzers/text_structure.py,sha256=ZmUsBMNBENjEYcABHqwziDXIHyCVYdUaEyAW0Ohagzc,5208
 natural_pdf/core/__init__.py,sha256=GUuFtj2Apc9biAdUOlnL8leL3BQncEzubvpiAUaU3ss,37
 natural_pdf/core/page.py,sha256=1DqF6mvpFKqsmRnFFrByV6C-MqGJ2MWyOQIwWiCs8PA,106040
-natural_pdf/core/pdf.py,sha256=zeLiOJ8XZ8jPaCR9mhurCiQ6kzesN6lcTXlBjTowi_4,23363
+natural_pdf/core/pdf.py,sha256=sGhn0OaadU74Ozoa9QA_HsAZikUKOncyCSME0mImdLo,25475
 natural_pdf/elements/__init__.py,sha256=6FGHZm2oONd8zErahMEawuB4AvJR5jOZPt4KtEwbj80,40
 natural_pdf/elements/base.py,sha256=QJmhk6sYDKErLGrQ5VYhloytuntufxiP6wTzGfZ__9w,22754
 natural_pdf/elements/collections.py,sha256=vFFeMS0XiBL3p9PyNmwXndKMlPhlwp8os3xKLveN_8k,31558
@@ -102,8 +103,8 @@ natural_pdf/utils/reading_order.py,sha256=1oihH9ZTqQvIVDYc2oVEYqIXyPzi94ERtelp6T
 natural_pdf/utils/visualization.py,sha256=Dujxp5xKbEap6UpoVEpArpkHChJLa_Je7FGz2S3Iwvw,5403
 tests/__init__.py,sha256=34RJiJqy8uDxasGCbzXIaJlHQklHprscPcA4xp2s97g,30
 tests/test_pdf.py,sha256=Ud-DI-GHAvnSJGMJewM_EwHtI_UgWTi7Gn9uIwQcpfE,1001
-natural_pdf-25.3.16.dist-info/LICENSE,sha256=9zfwINwJlarbDmdh6iJV4QUG54QSJlSAUcnC1YiC_Ns,1074
-natural_pdf-25.3.16.dist-info/METADATA,sha256=NzJ4A929jjoBvej1FByUxC9NhI5qGqlbIFos4gElEqQ,8365
-natural_pdf-25.3.16.dist-info/WHEEL,sha256=52BFRY2Up02UkjOa29eZOS2VxUrpPORXg1pkohGGUS8,91
-natural_pdf-25.3.16.dist-info/top_level.txt,sha256=2AueS3xkctrmlcDA_te2-_WG0A0wGhS0UQNwnr_cbFQ,27
-natural_pdf-25.3.16.dist-info/RECORD,,
+natural_pdf-25.3.16.2.dist-info/LICENSE,sha256=9zfwINwJlarbDmdh6iJV4QUG54QSJlSAUcnC1YiC_Ns,1074
+natural_pdf-25.3.16.2.dist-info/METADATA,sha256=3pd3i8n5ZtwJ2oGLSkJJJ61lXKaK93ALGuY9HvENhLg,8548
+natural_pdf-25.3.16.2.dist-info/WHEEL,sha256=52BFRY2Up02UkjOa29eZOS2VxUrpPORXg1pkohGGUS8,91
+natural_pdf-25.3.16.2.dist-info/top_level.txt,sha256=2AueS3xkctrmlcDA_te2-_WG0A0wGhS0UQNwnr_cbFQ,27
+natural_pdf-25.3.16.2.dist-info/RECORD,,