chore: remove dead normalize_url definitions from utils

Two unreachable functions in utils.py:

- The first `normalize_url` (plain urljoin wrapper) was silently shadowed
  by the extended `normalize_url` defined ~20 lines later. Python last-write
  wins, so the first definition was never callable.

- `normalize_url_tmp` was a hand-rolled URL joiner (string split on "/")
  with no callers outside utils.py itself. `urllib.parse.urljoin` already
  covers this correctly.

Author: RajanChavada

crawl4ai/utils.py

@@ -2212,25 +2212,6 @@ def fast_format_html(html_string):
     return "\n".join(formatted)
 
 
-def normalize_url(href, base_url):
-    """Normalize URLs to ensure consistent format"""
-    from urllib.parse import urljoin, urlparse
-
-    # Parse base URL to get components
-    parsed_base = urlparse(base_url)
-    if not parsed_base.scheme or not parsed_base.netloc:
-        raise ValueError(f"Invalid base URL format: {base_url}")
-    
-    if  parsed_base.scheme.lower() not in ["http", "https"]:
-        # Handle special protocols
-        raise ValueError(f"Invalid base URL format: {base_url}")
-    cleaned_href = href.strip()
-
-    # Use urljoin to handle all cases
-    return urljoin(base_url, cleaned_href)
-
-
-
 
 def normalize_url(
     href: str,
@@ -2431,41 +2412,6 @@ def efficient_normalize_url_for_deep_crawl(href, base_url, preserve_https=False,
     return normalized
 
 
-def normalize_url_tmp(href, base_url):
-    """Normalize URLs to ensure consistent format"""
-    # Extract protocol and domain from base URL
-    try:
-        base_parts = base_url.split("/")
-        protocol = base_parts[0]
-        domain = base_parts[2]
-    except IndexError:
-        raise ValueError(f"Invalid base URL format: {base_url}")
-
-    # Handle special protocols
-    special_protocols = {"mailto:", "tel:", "ftp:", "file:", "data:", "javascript:"}
-    if any(href.lower().startswith(proto) for proto in special_protocols):
-        return href.strip()
-
-    # Handle anchor links
-    if href.startswith("#"):
-        return f"{base_url}{href}"
-
-    # Handle protocol-relative URLs
-    if href.startswith("//"):
-        return f"{protocol}{href}"
-
-    # Handle root-relative URLs
-    if href.startswith("/"):
-        return f"{protocol}//{domain}{href}"
-
-    # Handle relative URLs
-    if not href.startswith(("http://", "https://")):
-        # Remove leading './' if present
-        href = href.lstrip("./")
-        return f"{protocol}//{domain}/{href}"
-
-    return href.strip()
-
 
 def quick_extract_links(html: str, base_url: str) -> Dict[str, List[Dict[str, str]]]:
     """