Article Processing

class Article:
    def __init__(self, url: str, title: str = '', source_url: str = '', config=None, **kwargs):
        """
        Initialize an article object.
        
        Parameters:
        - url: Article URL to process
        - title: Optional article title
        - source_url: Optional source website URL 
        - config: Configuration object for processing options
        - **kwargs: Additional configuration parameters
        """

    def build(self):
        """
        Complete article processing pipeline: download, parse, and NLP.
        Equivalent to calling download(), parse(), and nlp() in sequence.
        """

def build_article(url: str = '', config=None, **kwargs) -> Article:
    """
    Factory function to create an Article object.
    
    Parameters:
    - url: Article URL
    - config: Configuration object
    - **kwargs: Additional configuration parameters
    
    Returns:
    Article object ready for processing
    """

def download(self, input_html: str = None, title: str = None, recursion_counter: int = 0):
    """
    Download article HTML content.
    
    Parameters:
    - input_html: Optional pre-downloaded HTML content
    - title: Optional title override
    - recursion_counter: Internal parameter for handling redirects
    
    Raises:
    ArticleException: If download fails due to network or HTTP errors
    """

def parse(self):
    """
    Parse downloaded HTML content to extract article data.
    Extracts title, authors, text content, images, metadata, and publication date.
    
    Raises:
    ArticleException: If article has not been downloaded first
    """

def nlp(self):
    """
    Perform natural language processing on parsed article text.
    Extracts keywords from title and body text, generates article summary.
    
    Raises:
    ArticleException: If article has not been downloaded and parsed first
    """

def is_valid_url(self) -> bool:
    """
    Check if the article URL is valid for processing.
    
    Returns:
    bool: True if URL is valid, False otherwise
    """

def is_valid_body(self) -> bool:
    """
    Check if article content meets quality requirements.
    Validates word count, sentence count, title quality, and HTML content.
    
    Returns:
    bool: True if article body is valid, False otherwise
    
    Raises:
    ArticleException: If article has not been parsed first
    """

def is_media_news(self) -> bool:
    """
    Check if article is media-heavy (gallery, video, slideshow, etc.).
    
    Returns:
    bool: True if article is media-focused, False otherwise
    """

# Content Properties
url: str                    # Article URL
title: str                  # Article title  
text: str                   # Main article body text
html: str                   # Raw HTML content
article_html: str           # Cleaned article HTML content
summary: str                # Auto-generated summary

# Author and Date Information  
authors: list               # List of article authors
publish_date: str           # Publication date

# Media Content
top_img: str               # Primary article image URL (alias: top_image)
imgs: list                 # List of all image URLs (alias: images)  
movies: list               # List of video URLs

# Metadata from HTML
meta_img: str              # Image URL from metadata
meta_keywords: list        # Keywords from HTML meta tags
meta_description: str      # Description from HTML meta
meta_lang: str             # Language from HTML meta
meta_favicon: str          # Favicon URL from meta
meta_data: dict            # Dictionary of all metadata
canonical_link: str        # Canonical URL from meta
tags: set                  # Set of article tags

# Processing State
is_parsed: bool            # Whether article has been parsed
download_state: int        # Download status (ArticleDownloadState values)
download_exception_msg: str # Error message if download failed

# Source Information
source_url: str            # URL of the parent news source

# Advanced Properties
top_node: object           # Main DOM node of article content
clean_top_node: object     # Clean copy of main DOM node  
doc: object                # Full lxml DOM object
clean_doc: object          # Clean copy of DOM object
additional_data: dict      # Custom user data storage

# Extracted Content
keywords: list             # Keywords from NLP processing

class ArticleDownloadState:
    NOT_STARTED: int = 0      # Download not yet attempted
    FAILED_RESPONSE: int = 1  # Download failed due to network/HTTP error
    SUCCESS: int = 2          # Download completed successfully

from newspaper import Article

# Create and process article
article = Article('https://example.com/news/article')
article.download()
article.parse()

# Access extracted content  
print(f"Title: {article.title}")
print(f"Authors: {article.authors}")
print(f"Text length: {len(article.text)} characters")
print(f"Publication date: {article.publish_date}")
print(f"Top image: {article.top_img}")

from newspaper import build_article

# Build article with full processing
article = build_article('https://example.com/news/article')
article.build()  # download + parse + nlp

# Access NLP results
print(f"Keywords: {article.keywords}")
print(f"Summary: {article.summary}")

from newspaper import Article, ArticleException

try:
    article = Article('https://example.com/news/article')
    article.download()
    
    if article.download_state == ArticleDownloadState.FAILED_RESPONSE:
        print(f"Download failed: {article.download_exception_msg}")
    else:
        article.parse()
        
        if article.is_valid_body():
            article.nlp()
            print(f"Article processed successfully: {article.title}")
        else:
            print("Article content does not meet quality requirements")
            
except ArticleException as e:
    print(f"Article processing error: {e}")

from newspaper import Article, Configuration

# Create custom configuration
config = Configuration()
config.language = 'es'
config.MIN_WORD_COUNT = 500
config.fetch_images = False

# Process article with custom settings
article = Article('https://example.com/news/article', config=config)
article.build()