MarkdownGenerationStrategy (markdown_generation_strategy.py)

Generates Markdown from HTML using formatting rules and URL-joining strategies.

# Source: https://github.com/nerdy-tech-com-gitub/crawl4ai | License: Apache-2.0
# Provided via justclaw.it.com; keep this notice with the code.
from abc import ABC, abstractmethod
from typing import Optional, Dict, Any, Tuple
from .models import MarkdownGenerationResult
from .utils import CustomHTML2Text
from .content_filter_strategy import RelevantContentFilter, BM25ContentFilter
import re
from urllib.parse import urljoin

# Pre-compile the regex pattern
LINK_PATTERN = re.compile(r'!?\[([^\]]+)\]\(([^)]+?)(?:\s+"([^"]*)")?\)')

class MarkdownGenerationStrategy(ABC):
    """Abstract base class for markdown generation strategies."""
    def __init__(self, content_filter: Optional[RelevantContentFilter] = None):
        self.content_filter = content_filter
    
    @abstractmethod
    def g

... (truncated -- full source via MCP)