extract web links url bootstrap local

import os
import re

# ---------- CONFIG ----------
ROOT_DIR = r"C:\Users\Mayank\Documents\GitHub\ERP"
OUTPUT_FILE = "web_links.txt"

# Regex to extract http/https URLs
url_pattern = re.compile(
    r'https?://[^\s\'"<>()]+',
    re.IGNORECASE
)

urls = set()

# ---------- SCAN ----------
for root, _, files in os.walk(ROOT_DIR):
    for file in files:

        if not file.lower().endswith(".php"):
            continue

        full_path = os.path.join(root, file)

        try:
            with open(full_path, "r", encoding="utf-8", errors="ignore") as f:
                content = f.read()

            matches = url_pattern.findall(content)

            for url in matches:

                # Remove trailing punctuation
                url = url.rstrip(''''",);]}''')

                # Ignore localhost / local IPs
                if (
                    "localhost" in url.lower()
                    or "127.0.0.1" in url
                    or "0.0.0.0" in url
                    or url.startswith("http://192.168.")
                    or url.startswith("https://192.168.")
                    or url.startswith("http://10.")
                    or url.startswith("https://10.")
                    or url.startswith("http://172.")
                    or url.startswith("https://172.")
                ):
                    continue

                urls.add(url)

        except Exception as e:
            print(f"Error reading {full_path}: {e}")

# ---------- EXPORT ----------
with open(OUTPUT_FILE, "w", encoding="utf-8") as f:

    f.write(f"Total unique URLs: {len(urls)}\n\n")

    for url in sorted(urls):
        f.write(url + "\n")

print(f"Found {len(urls)} unique web URLs.")
print(f"Saved to {OUTPUT_FILE}")