attachments 0.5.2__tar.gz → 0.5.4__tar.gz

{attachments-0.5.2/src/attachments.egg-info → attachments-0.5.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: attachments
-Version: 0.5.2
+Version: 0.5.4
 Summary: The Python funnel for LLM context - turn any file into model-ready text + images, in one line.
 Author-email: Maxime Rivest <mrive052@gmail.com>
 License-Expression: MIT
@@ -27,6 +27,7 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: requests>=2.25.0
 Requires-Dist: beautifulsoup4>=4.9.0
+Requires-Dist: playwright>=1.52.0
 Provides-Extra: dev
 Requires-Dist: pytest>=8.0.0; extra == "dev"
 Requires-Dist: pytest-randomly>=3.15.0; extra == "dev"
@@ -243,6 +244,42 @@ result = rag(
 print(result.answer)
 ```
 
+### Optional: CSS Selector Highlighting 🎯
+
+For advanced web scraping with visual element highlighting in screenshots:
+
+```bash
+# Install Playwright for CSS selector highlighting
+pip install playwright
+playwright install chromium
+
+# Or with uv
+uv add playwright
+uv run playwright install chromium
+
+# Or install with browser extras
+pip install attachments[browser]
+playwright install chromium
+```
+
+**What this enables:**
+- 🎯 Visual highlighting of selected elements with animations
+- 📸 High-quality screenshots with JavaScript rendering  
+- 🎨 Professional styling with glowing borders and badges
+- 🔍 Perfect for extracting specific page elements
+
+```python
+# CSS selector highlighting examples
+title = Attachments("https://example.com[select:h1]")  # Highlights H1 elements
+content = Attachments("https://example.com[select:.content]")  # Highlights .content class
+main = Attachments("https://example.com[select:#main]")  # Highlights #main ID
+
+# Multiple elements with counters and different colors
+multi = Attachments("https://example.com[select:h1, .important][viewport:1920x1080]")
+```
+
+*Note: Without Playwright, CSS selectors still work for text extraction, but no visual highlighting screenshots are generated.*
+
 ### Advanced Pipeline Processing
 
 For power users, use the full grammar system with composable pipelines:

{attachments-0.5.2 → attachments-0.5.4}/README.md

@@ -147,6 +147,42 @@ result = rag(
 print(result.answer)
 ```
 
+### Optional: CSS Selector Highlighting 🎯
+
+For advanced web scraping with visual element highlighting in screenshots:
+
+```bash
+# Install Playwright for CSS selector highlighting
+pip install playwright
+playwright install chromium
+
+# Or with uv
+uv add playwright
+uv run playwright install chromium
+
+# Or install with browser extras
+pip install attachments[browser]
+playwright install chromium
+```
+
+**What this enables:**
+- 🎯 Visual highlighting of selected elements with animations
+- 📸 High-quality screenshots with JavaScript rendering  
+- 🎨 Professional styling with glowing borders and badges
+- 🔍 Perfect for extracting specific page elements
+
+```python
+# CSS selector highlighting examples
+title = Attachments("https://example.com[select:h1]")  # Highlights H1 elements
+content = Attachments("https://example.com[select:.content]")  # Highlights .content class
+main = Attachments("https://example.com[select:#main]")  # Highlights #main ID
+
+# Multiple elements with counters and different colors
+multi = Attachments("https://example.com[select:h1, .important][viewport:1920x1080]")
+```
+
+*Note: Without Playwright, CSS selectors still work for text extraction, but no visual highlighting screenshots are generated.*
+
 ### Advanced Pipeline Processing
 
 For power users, use the full grammar system with composable pipelines:

{attachments-0.5.2 → attachments-0.5.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "attachments"
-version = "0.5.2"  
+version = "0.5.4"  
 authors = [
   { name="Maxime Rivest", email="mrive052@gmail.com" },
 ]
@@ -31,8 +31,9 @@ keywords = ["llm", "ai", "pdf", "document", "multimodal", "openai", "claude" , "
 # Core dependencies for the modular architecture
 dependencies = [
     # Core file processing
-    "requests>=2.25.0",       # HTTP library for URL processing and web content
-    "beautifulsoup4>=4.9.0",  # HTML parsing for web content and HTML files
+    "requests>=2.25.0", # HTTP library for URL processing and web content
+    "beautifulsoup4>=4.9.0", # HTML parsing for web content and HTML files
+    "playwright>=1.52.0",
 ]
 
 [project.urls]

{attachments-0.5.2 → attachments-0.5.4}/src/attachments/__init__.py

@@ -31,7 +31,7 @@ adapt = SmartVerbNamespace(_adapters)
 refine = SmartVerbNamespace(_refiners)
 split = SmartVerbNamespace(_modifiers)  # Split functions are also modifiers
 
-__version__ = "0.5.2"
+__version__ = "0.5.4"
 
 __all__ = [
     # Core classes and functions

{attachments-0.5.2 → attachments-0.5.4}/src/attachments/presenters/visual/images.py

@@ -597,8 +597,33 @@ def images(att: Attachment, soup: 'bs4.BeautifulSoup') -> Attachment:
     try:
         from playwright.async_api import async_playwright
     except ImportError:
-        att.metadata['screenshot_error'] = "Playwright not available. Install with: pip install playwright && playwright install chromium"
-        return att
+        # Check if CSS selector was requested (which requires Playwright for highlighting)
+        css_selector = att.commands.get('select')
+        if css_selector:
+            # CSS selector highlighting was requested but Playwright isn't available
+            error_msg = (
+                f"🎯 CSS Selector Highlighting Unavailable: You requested CSS selector highlighting "
+                f"with [select:{css_selector}], but Playwright is not installed.\n\n"
+                f"To enable CSS selector highlighting and webpage screenshots:\n"
+                f"  pip install playwright\n"
+                f"  playwright install chromium\n\n"
+                f"Alternative installation methods:\n"
+                f"  # With uv:\n"
+                f"  uv add playwright\n"
+                f"  uv run playwright install chromium\n\n"
+                f"  # With attachments browser extras:\n"
+                f"  pip install attachments[browser]\n"
+                f"  playwright install chromium\n\n"
+                f"CSS selector highlighting provides:\n"
+                f"  🎯 Visual highlighting of selected elements with animations\n"
+                f"  📸 High-quality screenshots with JavaScript rendering\n"
+                f"  🎨 Professional styling with glowing borders and badges\n"
+                f"  🔍 Perfect for extracting specific page elements"
+            )
+            raise ImportError(error_msg)
+        else:
+            # Regular screenshot was requested
+            raise ImportError("Playwright not available. Install with: pip install playwright && playwright install chromium")
     
     try:
         import asyncio

{attachments-0.5.2 → attachments-0.5.4/src/attachments.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: attachments
-Version: 0.5.2
+Version: 0.5.4
 Summary: The Python funnel for LLM context - turn any file into model-ready text + images, in one line.
 Author-email: Maxime Rivest <mrive052@gmail.com>
 License-Expression: MIT
@@ -27,6 +27,7 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: requests>=2.25.0
 Requires-Dist: beautifulsoup4>=4.9.0
+Requires-Dist: playwright>=1.52.0
 Provides-Extra: dev
 Requires-Dist: pytest>=8.0.0; extra == "dev"
 Requires-Dist: pytest-randomly>=3.15.0; extra == "dev"
@@ -243,6 +244,42 @@ result = rag(
 print(result.answer)
 ```
 
+### Optional: CSS Selector Highlighting 🎯
+
+For advanced web scraping with visual element highlighting in screenshots:
+
+```bash
+# Install Playwright for CSS selector highlighting
+pip install playwright
+playwright install chromium
+
+# Or with uv
+uv add playwright
+uv run playwright install chromium
+
+# Or install with browser extras
+pip install attachments[browser]
+playwright install chromium
+```
+
+**What this enables:**
+- 🎯 Visual highlighting of selected elements with animations
+- 📸 High-quality screenshots with JavaScript rendering  
+- 🎨 Professional styling with glowing borders and badges
+- 🔍 Perfect for extracting specific page elements
+
+```python
+# CSS selector highlighting examples
+title = Attachments("https://example.com[select:h1]")  # Highlights H1 elements
+content = Attachments("https://example.com[select:.content]")  # Highlights .content class
+main = Attachments("https://example.com[select:#main]")  # Highlights #main ID
+
+# Multiple elements with counters and different colors
+multi = Attachments("https://example.com[select:h1, .important][viewport:1920x1080]")
+```
+
+*Note: Without Playwright, CSS selectors still work for text extraction, but no visual highlighting screenshots are generated.*
+
 ### Advanced Pipeline Processing
 
 For power users, use the full grammar system with composable pipelines:

{attachments-0.5.2 → attachments-0.5.4}/src/attachments.egg-info/requires.txt

@@ -1,5 +1,6 @@
 requests>=2.25.0
 beautifulsoup4>=4.9.0
+playwright>=1.52.0
 
 [all]
 pandas>=1.3.0