Commit Message:

- Added examples for Amazon product data extraction methods
  - Updated configuration options and enhance documentation
  - Minor refactoring for improved performance and readability
  - Cleaned up version control settings.

crawl4ai/cache_context.py

@@ -25,8 +25,26 @@ class CacheContext:
     
     This class centralizes all cache-related logic and URL type checking,
     making the caching behavior more predictable and maintainable.
+    
+    Attributes:
+        url (str): The URL being processed.
+        cache_mode (CacheMode): The cache mode for the current operation.
+        always_bypass (bool): If True, bypasses caching for this operation.
+        is_cacheable (bool): True if the URL is cacheable, False otherwise.
+        is_web_url (bool): True if the URL is a web URL, False otherwise.
+        is_local_file (bool): True if the URL is a local file, False otherwise.
+        is_raw_html (bool): True if the URL is raw HTML, False otherwise.
+        _url_display (str): The display name for the URL (web, local file, or raw HTML).
     """
     def __init__(self, url: str, cache_mode: CacheMode, always_bypass: bool = False):
+        """
+        Initializes the CacheContext with the provided URL and cache mode.
+        
+        Args:
+            url (str): The URL being processed.
+            cache_mode (CacheMode): The cache mode for the current operation.
+            always_bypass (bool): If True, bypasses caching for this operation.
+        """
         self.url = url
         self.cache_mode = cache_mode
         self.always_bypass = always_bypass
@@ -37,13 +55,31 @@ class CacheContext:
         self._url_display = url if not self.is_raw_html else "Raw HTML"
     
     def should_read(self) -> bool:
-        """Determines if cache should be read based on context."""
+        """
+        Determines if cache should be read based on context.
+        
+        How it works:
+        1. If always_bypass is True or is_cacheable is False, return False.
+        2. If cache_mode is ENABLED or READ_ONLY, return True.
+        
+        Returns:
+            bool: True if cache should be read, False otherwise.
+        """
         if self.always_bypass or not self.is_cacheable:
             return False
         return self.cache_mode in [CacheMode.ENABLED, CacheMode.READ_ONLY]
     
     def should_write(self) -> bool:
-        """Determines if cache should be written based on context."""
+        """
+        Determines if cache should be written based on context.
+        
+        How it works:
+        1. If always_bypass is True or is_cacheable is False, return False.
+        2. If cache_mode is ENABLED or WRITE_ONLY, return True.
+        
+        Returns:
+            bool: True if cache should be written, False otherwise.
+        """
         if self.always_bypass or not self.is_cacheable:
             return False
         return self.cache_mode in [CacheMode.ENABLED, CacheMode.WRITE_ONLY]