natural-pdf 0.1.0__tar.gz → 1.1.1__tar.gz

{natural_pdf-0.1.0 → natural_pdf-1.1.1}/.github/workflows/docs.yml

@@ -8,6 +8,8 @@ on:
       - 'docs/**'
       - 'mkdocs.yml'
       - '.github/workflows/docs.yml'
+    tags:
+      - 'v*'
 
 permissions:
   contents: write
@@ -27,7 +29,7 @@ jobs:
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
-          pip install mkdocs-material mkdocs pymdown-extensions mkdocstrings mkdocstrings-python mkdocs-jupyter
+          pip install mkdocs-material mkdocs pymdown-extensions mkdocstrings mkdocstrings-python mkdocs-jupyter mkdocs-exclude
           pip install -e .
           
       - name: Build docs

{natural_pdf-0.1.0 → natural_pdf-1.1.1}/.gitignore

@@ -1,3 +1,12 @@
+.notebook_cache.json
+Untitled.ipynb
+conversation.md
+docs/tutorials/pdfs
+install.sh
+notebooks/Examples.md
+transcript.md
+
+
 # Created by https://www.toptal.com/developers/gitignore/api/python,macos,visualstudiocode,jupyternotebooks
 # Edit at https://www.toptal.com/developers/gitignore?templates=python,macos,visualstudiocode,jupyternotebooks
 

natural_pdf-1.1.1/PKG-INFO

@@ -0,0 +1,124 @@
+Metadata-Version: 2.4
+Name: natural-pdf
+Version: 1.1.1
+Summary: A more intuitive interface for working with PDFs
+Author-email: Jonathan Soma <jonathan.soma@gmail.com>
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/jsoma/natural-pdf
+Project-URL: Repository, https://github.com/jsoma/natural-pdf
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+License-File: LICENSE
+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: torch>=2.0.0
+Requires-Dist: torchvision>=0.15.0
+Requires-Dist: transformers>=4.30.0
+Requires-Dist: huggingface_hub>=0.19.0
+Provides-Extra: interactive
+Requires-Dist: ipywidgets<9.0.0,>=7.0.0; extra == "interactive"
+Provides-Extra: easyocr
+Requires-Dist: easyocr; extra == "easyocr"
+Provides-Extra: paddle
+Requires-Dist: paddlepaddle; extra == "paddle"
+Requires-Dist: paddleocr; extra == "paddle"
+Provides-Extra: layout-yolo
+Requires-Dist: doclayout_yolo; extra == "layout-yolo"
+Provides-Extra: surya
+Requires-Dist: surya-ocr; extra == "surya"
+Provides-Extra: qa
+Provides-Extra: all
+Requires-Dist: ipywidgets<9.0.0,>=7.0.0; extra == "all"
+Requires-Dist: easyocr; extra == "all"
+Requires-Dist: paddlepaddle; extra == "all"
+Requires-Dist: paddleocr; extra == "all"
+Requires-Dist: doclayout_yolo; extra == "all"
+Requires-Dist: surya-ocr; extra == "all"
+Dynamic: license-file
+
+# Natural PDF
+
+A friendly library for working with PDFs, built on top of [pdfplumber](https://github.com/jsvine/pdfplumber).
+
+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)
+- [Live demos here](https://colab.research.google.com/github/jsoma/natural-pdf/)
+
+<div style="max-width: 400px; margin: auto"><a href="sample-screen.png"><img src="sample-screen.png"></a></div>
+
+## Installation
+
+```bash
+pip install natural-pdf
+```
+
+For optional features like specific OCR engines, layout analysis models, or the interactive Jupyter widget, you can install extras:
+
+```bash
+# Example: Install with EasyOCR support
+pip install natural-pdf[easyocr]
+pip install natural-pdf[surya]
+pip install natural-pdf[paddle]
+
+# Example: Install with interactive viewer support
+pip install natural-pdf[interactive]
+
+# Install everything
+pip install natural-pdf[all]
+```
+
+See the [installation guide](https://jsoma.github.io/natural-pdf/installation/) for more details on extras.
+
+## Quick Start
+
+```python
+from natural_pdf import PDF
+
+# Open a PDF
+pdf = PDF('document.pdf')
+page = pdf.pages[0]
+
+# Find elements using CSS-like selectors
+heading = page.find('text:contains("Summary"):bold')
+
+# Extract content below the heading
+content = heading.below().extract_text()
+print("Content below Summary:", content[:100] + "...")
+
+# Exclude headers/footers automatically (example)
+# You might define these based on common text or position
+page.add_exclusion(page.find('text:contains("CONFIDENTIAL")').above())
+page.add_exclusion(page.find_all('line')[-1].below())
+
+# Extract clean text from the page
+clean_text = page.extract_text()
+print("\nClean page text:", clean_text[:200] + "...")
+
+# Highlight the heading and view the page
+heading.highlight(color='red')
+page.to_image()
+```
+
+And as a fun bonus, `page.viewer()` will provide an interactive method to explore the PDF.
+
+## Key Features
+
+Natural PDF offers a range of features for working with PDFs:
+
+*   **CSS-like Selectors:** Find elements using intuitive query strings (`page.find('text:bold')`).
+*   **Spatial Navigation:** Select content relative to other elements (`heading.below()`, `element.select_until(...)`).
+*   **Text & Table Extraction:** Get clean text or structured table data, automatically handling exclusions.
+*   **OCR Integration:** Extract text from scanned documents using engines like EasyOCR, PaddleOCR, or Surya.
+*   **Layout Analysis:** Detect document structures (titles, paragraphs, tables) using AI models.
+*   **Document QA:** Ask natural language questions about your document's content.
+*   **Visual Debugging:** Highlight elements and use an interactive viewer or save images to understand your selections.
+
+## Learn More
+
+Dive deeper into the features and explore advanced usage in the [**Complete Documentation**](https://jsoma.github.io/natural-pdf).

natural_pdf-1.1.1/README.md

@@ -0,0 +1,81 @@
+# Natural PDF
+
+A friendly library for working with PDFs, built on top of [pdfplumber](https://github.com/jsvine/pdfplumber).
+
+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)
+- [Live demos here](https://colab.research.google.com/github/jsoma/natural-pdf/)
+
+<div style="max-width: 400px; margin: auto"><a href="sample-screen.png"><img src="sample-screen.png"></a></div>
+
+## Installation
+
+```bash
+pip install natural-pdf
+```
+
+For optional features like specific OCR engines, layout analysis models, or the interactive Jupyter widget, you can install extras:
+
+```bash
+# Example: Install with EasyOCR support
+pip install natural-pdf[easyocr]
+pip install natural-pdf[surya]
+pip install natural-pdf[paddle]
+
+# Example: Install with interactive viewer support
+pip install natural-pdf[interactive]
+
+# Install everything
+pip install natural-pdf[all]
+```
+
+See the [installation guide](https://jsoma.github.io/natural-pdf/installation/) for more details on extras.
+
+## Quick Start
+
+```python
+from natural_pdf import PDF
+
+# Open a PDF
+pdf = PDF('document.pdf')
+page = pdf.pages[0]
+
+# Find elements using CSS-like selectors
+heading = page.find('text:contains("Summary"):bold')
+
+# Extract content below the heading
+content = heading.below().extract_text()
+print("Content below Summary:", content[:100] + "...")
+
+# Exclude headers/footers automatically (example)
+# You might define these based on common text or position
+page.add_exclusion(page.find('text:contains("CONFIDENTIAL")').above())
+page.add_exclusion(page.find_all('line')[-1].below())
+
+# Extract clean text from the page
+clean_text = page.extract_text()
+print("\nClean page text:", clean_text[:200] + "...")
+
+# Highlight the heading and view the page
+heading.highlight(color='red')
+page.to_image()
+```
+
+And as a fun bonus, `page.viewer()` will provide an interactive method to explore the PDF.
+
+## Key Features
+
+Natural PDF offers a range of features for working with PDFs:
+
+*   **CSS-like Selectors:** Find elements using intuitive query strings (`page.find('text:bold')`).
+*   **Spatial Navigation:** Select content relative to other elements (`heading.below()`, `element.select_until(...)`).
+*   **Text & Table Extraction:** Get clean text or structured table data, automatically handling exclusions.
+*   **OCR Integration:** Extract text from scanned documents using engines like EasyOCR, PaddleOCR, or Surya.
+*   **Layout Analysis:** Detect document structures (titles, paragraphs, tables) using AI models.
+*   **Document QA:** Ask natural language questions about your document's content.
+*   **Visual Debugging:** Highlight elements and use an interactive viewer or save images to understand your selections.
+
+## Learn More
+
+Dive deeper into the features and explore advanced usage in the [**Complete Documentation**](https://jsoma.github.io/natural-pdf).

{natural_pdf-0.1.0 → natural_pdf-1.1.1}/check_run_md.sh

@@ -11,9 +11,10 @@ MARKDOWN_FILE=$1
 NOTEBOOK_FILE="${MARKDOWN_FILE%.md}.ipynb"
 
 echo "Converting $MARKDOWN_FILE to notebook..."
+# Jupytext will now automatically add tags based on markdown metadata
 jupytext --to ipynb "$MARKDOWN_FILE" || { echo "Conversion failed"; exit 1; }
 
 echo "Executing notebook $NOTEBOOK_FILE..."
 jupyter execute "$NOTEBOOK_FILE" --inplace || { echo "Execution failed"; exit 1; }
 
-echo "Success! Notebook executed and results saved to $NOTEBOOK_FILE" 
+echo "Success! Notebook executed and results saved to $NOTEBOOK_FILE"

{natural_pdf-0.1.0 → natural_pdf-1.1.1}/docs/assets/stylesheets/custom.css

@@ -1,5 +1,32 @@
 /* Natural PDF - Minimal Custom Styling */
 
+.jp-InputPrompt, .jp-OutputPrompt {
+  display: none !important;
+}
+
+.jupyter-wrapper .CodeMirror {
+  font-size: 0.85em !important;
+}
+
+.highlight-ipynb pre {
+  white-space: pre-wrap !important;
+  word-wrap: break-word !important;
+}
+
+.CodeMirror pre {
+  white-space: pre-wrap !important;
+  word-wrap: break-word !important;
+}
+
+.jp-CodeMirrorEditor {
+  max-width: 100%;
+  overflow-x: auto;
+}
+
+.jupyter-wrapper{ 
+  --jp-code-font-size: 0.85em !important;
+}
+
 /* Typography improvements */
 .md-typeset h1 {
   font-weight: 400;