How to Extract URLs from Text — The Complete Guide

https://www.example.com/path/to/page?query=value&id=42#section├── Protocol:  https://
                  ├── Subdomain: www.
                  ├── Domain:    example.com
                  ├── Path:      /path/to/page
                  ├── Query:     ?query=value&id=42
                  └── Fragment:  #section

import re

                  text = """
                  Visit https://quicktexttools.in for tools.
                  Documentation: https://docs.example.com/api/v2
                  Legacy: http://old.example.com/endpoint?id=42
                  """

                  pattern = r'https?://[^\s]+'
                  urls = re.findall(pattern, text)

                  print(urls)
                  ['https://quicktexttools.in', 'https://docs.example.com/api/v2', 'http://old.example.com/endpoint?id=42']

import re
                def extract_urls(text, unique=True, sort=False):
                pattern = r'https?://[^s<>"')]]+'
                urls = re.findall(pattern, text)if unique:
                    # Preserve order while removing duplicates
                    urls = list(dict.fromkeys(urls))if sort:
                    urls = sorted(urls)return urlsUsage
                with open('input.txt', 'r') as f:
                content = f.read()results = extract_urls(content, unique=True, sort=True)with open('urls.txt', 'w') as f:
                f.write('
'.join(results))print(f"Extracted {len(results)} unique URLs")

from bs4 import BeautifulSoup
                  import requests
                  url = 'https://example.com'
                  response = requests.get(url)
                  soup = BeautifulSoup(response.text, 'html.parser')Extract all href links
                  links = []
                  for tag in soup.find_all('a', href=True):
                  href = tag['href']
                  if href.startswith('http'):
                  links.append(href)Also extract src attributes (images, scripts)
                  for tag in soup.find_all(src=True):
                  src = tag['src']
                  if src.startswith('http'):
                  links.append(src)unique_links = list(dict.fromkeys(links))
                  print(f"Found {len(unique_links)} unique links")

import re
                  from collections import Counter
                  pattern = r'https?://[^s"')]+'with open('access.log', 'r') as f:
                  log_content = f.read()urls = re.findall(pattern, log_content)
                  url_counts = Counter(urls)Most frequently accessed URLs
                  for url, count in url_counts.most_common(10):
                  print(f"{count:>6} {url}")

const text = `
                  Visit https://quicktexttools.in for tools.
                  API docs: https://docs.example.com/api/v2
                  Legacy: http://old.example.com/endpoint?id=42
                  `;

                  const pattern = /https?:\/\/(www\.)?[-a-zA-Z0-9@:%.+~#=]{1,256}\.[a-zA-Z0-9()]{1,6}\b([-a-zA-Z0-9()@:%+.~#?&/=]*)/gi;

                  const urls = text.match(pattern) || [];

                  console.log(urls);

                  // ['https://quicktexttools.in', 'https://docs.example.com/api/v2', 'http://old.example.com/endpoint?id=42']

function extractUrls(
                  text,
                  { unique = true, sort = false, httpsOnly = false } = {}
                  ) {
                    const pattern =
                      /https?:\/\/(www\.)?[-a-zA-Z0-9@:%.+~#=]{1,256}\.[a-zA-Z0-9()]{1,6}\b([-a-zA-Z0-9()@:%+.~#?&/=]*)/gi;

                    let urls = text.match(pattern) || [];

                    if (httpsOnly) {
                      urls = urls.filter(url => url.startsWith('https://'));
                    }

                    if (unique) {
                      urls = [...new Set(urls)];
                    }

                    if (sort) {
                      urls = urls.sort((a, b) => a.localeCompare(b));
                    }

                    return urls;
                  }

                  // Usage
                  const result = extractUrls(text, {
                    unique: true,
                    sort: true,
                    httpsOnly: false,
                  });

                console.log(`Found ${result.length} URLs`);
                  

// Extract all links from the current page DOM
                  function extractPageLinks() {
                  const anchors = document.querySelectorAll('a[href]');
                  const imgSrcs = document.querySelectorAll('img[src], script[src], link[href]');const links = new Set();anchors.forEach(a => {
                  if (a.href && a.href.startsWith('http')) {
                  links.add(a.href);
                  }
                  });imgSrcs.forEach(el => {
                  const src = el.src || el.href;
                  if (src && src.startsWith('http')) {
                  links.add(src);
                  }
                  });return [...links];
                  }// Run in browser console on any page
                  console.log(extractPageLinks());

192.168.1.1 - - [01/Jun/2025:12:34:01 +0000] "GET /api/users HTTP/1.1" 200 1423 "https://app.example.com/dashboard" "Mozilla/5.0" 192.168.1.2 - - [01/Jun/2025:12:34:02 +0000] "POST /api/orders HTTP/1.1" 201 892 "https://app.example.com/checkout" "Mozilla/5.0"