instagram photo downloader

flask_main.py

from flask import Flask, request, jsonify
import requests
from bs4 import BeautifulSoup
import re
from urllib.parse import urlparse

class InstagramScraperAPI:
    URL_REGEX = re.compile(
        r'^(?:http|ftp)s?://'  # http:// or https://
        r'(?:(?:[A-Z0-9](?:[A-Z0-9-]{0,61}[A-Z0-9])?\.)+(?:[A-Z]{2,6}|[A-Z0-9-]{2,})|'  # domain...
        r'localhost|'  # localhost
        r'\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}|'  # ...or ipv4
        r'\[?[A-F0-9]*:[A-F0-9:]+\]?)'  # ...or ipv6
        r'(?::\d+)?'  # optional port
        r'(?:/?|[/?]\S+)$', re.IGNORECASE)

    def __init__(self, app=None):
        self.app = app
        if app is not None:
            self.init_app(app)

    def init_app(self, app):
        self.app = app
        self.register_routes()

    def prepend_scheme(self, url):
        parsed_url = urlparse(url)
        if not parsed_url.scheme:
            return 'https://' + url
        return url

    def is_valid_instagram_url(self, url):
        url = self.prepend_scheme(url)  # Ensure the URL has the scheme
        return url.startswith('https://www.instagram.com/p/') and self.is_valid_url(url)

    def is_valid_url(self, url):
        return re.match(self.URL_REGEX, url) is not None

    def register_routes(self):
        @self.app.route('/igp', methods=['GET'])
        def igp():
            user_input = request.args.get('u')

            if not user_input:
                return jsonify({"error": "Missing 'u' parameter",
                                "example": request.host_url + "igp?u=https://www.instagram.com/p/C7gz-Q3tW3J/"}), 400

            user_input = self.prepend_scheme(user_input)

            if not self.is_valid_instagram_url(user_input):
                return jsonify({"error": "Invalid Instagram URL format. Please provide a valid Instagram post URL.",
                                "example": request.host_url + "igp?u=https://www.instagram.com/p/C7gz-Q3tW3J/"}), 400

            headers = {
                'accept': 'application/json, text/javascript, */*; q=0.01',
                'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36',
                'x-requested-with': 'XMLHttpRequest',
            }
            data = {
                'q': user_input,
                'downloader': 'image',
            }

            try:
                response = requests.post('https://inoffline.net/search/', headers=headers, data=data, timeout=30)
                response.raise_for_status()
            except requests.exceptions.RequestException as e:
                return jsonify({"error": str(e)}), 500

            soup = BeautifulSoup(response.text, 'html.parser')
            links = soup.find_all('a', href=True)

            cleaned_urls = []
            for link in links:
                img_url = link.get('href')
                clean_url = re.sub(r'\\+', '', img_url)
                clean_url = clean_url.replace('"', '') + '\n'
                cleaned_urls.append(clean_url.strip())

            return jsonify({"image_urls": cleaned_urls}), 200


app = Flask(__name__)
InstagramScraperAPI(app)

if __name__ == '__main__':
    app.run(debug=True)

main.py

import requests
from bs4 import BeautifulSoup
import re

url = 'https://inoffline.net/search/'
cookies = {
    'PHPSESSID': 'gg0skvdsjo022p6eo2vbuibers',
}
headers = {
    'accept': 'application/json, text/javascript, */*; q=0.01',
    'content-type': 'application/x-www-form-urlencoded; charset=UTF-8',
    'sec-ch-ua': 'Not)A;Brand";v="99", "Brave";v="127", "Chromium";v="127"',
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36',
    'x-requested-with': 'XMLHttpRequest',
}
data = {
    'q': 'https://www.instagram.com/p/C7gz-Q3tW3J/?igsh=MTM5Z3d5Y202dThzZw==',
    'downloader': 'image',
}

response = requests.post(url, cookies=cookies, headers=headers, data=data)

if response.status_code == 200:
    soup = BeautifulSoup(response.text, 'html.parser')

    links = soup.find_all('a', href=True)

    for link in links:
        img_url = link.get('href')
        clean_url = re.sub(r'\\+', '', img_url)
        clean_url = clean_url.replace('\"', '') + '\n'
        print(clean_url)
else:
    print(f"Gagal mengambil halaman. Kode status: {response.status_code}")