# Release anyparser-core@1.0.1

- Updated branding from \"AnyParser\" to \"Anyparser\" throughout the codebase
- Added empty path validation in path validator
- Added version information to package
- Updated documentation with AI-focused benefits and examples
- Updated URLs from app.anyparser.com to studio.anyparser.com
- Added type improvements for crawl directives
- Added support for unavailable_after in crawl directives
- Added text and images fields to AnyparserUrl

Author: heyaibi

README.md

@@ -14,11 +14,11 @@ https://anyparser.com
 
 **Get Started Quickly:**
 
-1. **Free Access:** Obtain your API credentials and start building your AI data pipelines today at [Anyparser Dashboard](https://app.anyparser.com/).
+1. **Free Access:** Obtain your API credentials and start building your AI data pipelines today at [Anyparser Studio](https://studio.anyparser.com/).
 2. **Installation:** Install the SDK with a simple pip command.
 3. **Run Examples:**  Copy and paste the provided examples to see how easy it is to extract data for your AI projects.
 
-Before starting, add a new API key on the [Anyparser Dashboard](https://app.anyparser.com/).
+Before starting, add a new API key on the [Anyparser Studio](https://studio.anyparser.com/).
 
 
 ```bash
@@ -230,7 +230,7 @@ from anyparser_core import OcrLanguage, OCRPreset
 
 @dataclass
 class AnyparserOption:
-    """Configuration options for the AnyParser API."""
+    """Configuration options for the Anyparser API."""
 
     # API Configuration
     api_url: Optional[str] = None  # API endpoint URL, defaults to environment variable ANYPARSER_API_URL

anyparser_core/__init__.py

@@ -16,6 +16,7 @@
 )
 from .validator import validate_and_parse, validate_option, validate_path
 
+__version__ = "1.0.1"
 __all__ = [
     "Anyparser",
     "AnyparserCrawlDirective",

anyparser_core/options.py

@@ -1,5 +1,5 @@
 """
-Options module for AnyParser configuration and parsing.
+Options module for Anyparser configuration and parsing.
 """
 
 from dataclasses import dataclass, field
@@ -15,7 +15,7 @@
 
 @dataclass
 class AnyparserOption:
-    """Configuration options for the AnyParser API."""
+    """Configuration options for the Anyparser API."""
 
     api_url: Optional[str] = None
     api_key: Optional[str] = None

anyparser_core/parser.py

@@ -2,8 +2,9 @@
 import json
 import uuid
 from dataclasses import dataclass, field
-from typing import Dict, List, Optional, Union
+from typing import Dict, List, Optional, Union, Literal
 from urllib.parse import urljoin, urlparse
+from datetime import datetime
 
 from .form import build_form
 from .options import AnyparserOption
@@ -36,22 +37,22 @@ class AnyparserResultBase:
 class AnyparserCrawlDirectiveBase:
     """Represents Anyparser crawl directive base with type, priority, name, noindex, nofollow, and crawl delay."""
 
-    type: str = field(default="")
+    type: Literal["HTTP Header", "HTML Meta", "Combined"] = field(default="Combined")
     priority: int = field(default=0)
     name: Optional[str] = field(default=None)
     noindex: Optional[bool] = field(default=False)
     nofollow: Optional[bool] = field(default=False)
     crawl_delay: Optional[int] = field(default=None)
+    unavailable_after: Optional[datetime] = field(default=None)
 
 
 @dataclass
 class AnyparserCrawlDirective(AnyparserCrawlDirectiveBase):
     """Represents Anyparser crawl directive with type 'Combined', overriding the name to be None and adding the 'underlying' field."""
 
     underlying: List[AnyparserCrawlDirectiveBase] = field(default_factory=list)
-    type: str = field(default="Combined")
+    type: Literal["Combined"] = field(default="Combined")
     name: Optional[None] = field(default=None)
-    # name: None = None
 
 
 @dataclass
@@ -74,11 +75,11 @@ class AnyparserUrl:
     politeness_delay: int = field(default=0)
     total_characters: int = field(default=0)
     markdown: str = field(default="")
-
     directive: AnyparserCrawlDirective = field(default_factory=AnyparserCrawlDirective)
     title: Optional[str] = field(default=None)
     crawled_at: Optional[str] = field(default=None)
-
+    images: List[AnyparserImageReference] = field(default_factory=list)
+    text: Optional[str] = field(default=None)
 
 @dataclass
 class AnyparserPdfPage:
@@ -111,11 +112,11 @@ class AnyparserCrawlResult:
     robots_directive: AnyparserRobotsTxtDirective
 
 
-AnyparserResult = Union[AnyparserPdfResult, AnyparserCrawlResult]
+AnyparserResult = Union[AnyparserPdfResult, AnyparserCrawlResult, AnyparserResultBase]
 
 
 class Anyparser:
-    """Main class for parsing itemss using the AnyParser API."""
+    """Main class for parsing itemss using the Anyparser API."""
 
     def __init__(self, options: Optional[AnyparserOption] = None) -> None:
         """Initialize the parser with optional configuration.
@@ -128,7 +129,7 @@ def __init__(self, options: Optional[AnyparserOption] = None) -> None:
     async def parse(
         self, file_paths_or_url: Union[str, List[str]]
     ) -> Union[List[AnyparserResult], str]:
-        """Parse files using the AnyParser API.
+        """Parse files using the Anyparser API.
 
         Args:
             file_paths_or_url: A single file path or list of file paths to parse, or a start URL for crawling

anyparser_core/validator/path.py

@@ -16,6 +16,12 @@ async def validate_path(file_paths: Union[str, List[str]]) -> PathValidationResu
     """
     Validates file paths exist and are accessible
     """
+    if not file_paths or (isinstance(file_paths, str) and not file_paths.strip()):
+        return InvalidPathValidationResult(
+            error=FileNotFoundError("No files provided")
+        )
+    
+
     if isinstance(file_paths, (str, Path)):
         files = [file_paths]
     else: