exiftool from scraping website

flask_main.py

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

app = Flask(__name__)

# Regular expression to validate URLs
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 remove_spaces_from_keys(data):
    if isinstance(data, dict):
        new_data = {}
        for key, value in data.items():
            new_key = key.replace(" ", "")
            new_data[new_key] = remove_spaces_from_keys(value)
        return new_data
    elif isinstance(data, list):
        return [remove_spaces_from_keys(item) for item in data]
    else:
        return data

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

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

@app.route('/exiftool', methods=['GET'])
def exiftool():
    image_url = request.args.get('url')

    if not image_url:
        return jsonify({"error": "Missing 'url' parameter",
                        "example": request.host_url + "exiftool?url=https://example.com/image.jpg"}), 400
    
    image_url = prepend_scheme(image_url)

    # Validate URL format
    if not is_valid_url(image_url):
        return jsonify({"error": "Invalid URL format. Please provide a valid URL.",
                        "example": request.host_url + "exiftool?url=https://example.com/image.jpg"}), 400

    parsed_url = urlparse(image_url)
    
    if parsed_url.query:
        query_params = parse_qs(parsed_url.query)
        image_url = query_params.get('imgurl', [None])[0]

    if not image_url or not (image_url.endswith('.jpg') or image_url.endswith('.png') or image_url.endswith('.webp')):
        return jsonify({"error": "Invalid image URL. Please provide a link to a .jpg, .png, or .webp image.",
                        "Exjpg": request.host_url + "exiftool?url=https://example.com/image.jpg",
                        "Expng": request.host_url + "exiftool?url=https://example.com/image.png",
                        "Exwebp": request.host_url + "exiftool?url=https://example.com/image.webp",
                        }), 400

    headers = {
        'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8',
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36',
    }

    params = {
        'url': image_url,
    }

    try:
        response = requests.get('https://exifinfo.org/url', params=params, headers=headers, timeout=30)
        response.raise_for_status()
    except requests.exceptions.RequestException as e:
        return jsonify({"error": str(e)}), 500

    soup = BeautifulSoup(response.text, 'html.parser')
    sections = soup.find_all('div', class_='section')

    exif_data = {}

    for section in sections:
        section_image = section.find('img')
        if section_image:
            exif_data["Image"] = f"https://exifinfo.org{section_image['src']}"

        section_title = section.find('h2')
        if section_title:
            title = section_title.get_text()
            details = section.find_all(['dt', 'dd'])
            section_data = {}

            for i in range(0, len(details), 2):
                dt = details[i].get_text().strip().replace(" ", "")
                dd = details[i + 1].get_text().strip()
                section_data[dt] = dd

            exif_data[title.replace(" ", "")] = section_data

    exif_data = remove_spaces_from_keys(exif_data)

    return jsonify(exif_data), 200

if __name__ == '__main__':
    app.run(debug=False, host='0.0.0.0', port=5000)

main.py

import requests
from bs4 import BeautifulSoup

masukanlink = input("Link Images (.jpg/.png/.webp/) etc : ")

headers = {
    'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8',
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36',
}

params = {
    # 'url': 'https://ppcexpo.com/blog/wp-content/uploads/2020/11/what-is-a-meta-search-engine-.jpg',
    'url': f'{masukanlink}',
}

response = requests.get('https://exifinfo.org/url', params=params, headers=headers)

soup = BeautifulSoup(response.text, 'html.parser')

sections = soup.find_all('div', class_='section')

for section in sections:
    section_image = section.find('img')
    if section_image:
        print(f"Image: https://exifinfo.org{section_image['src']}")

    section_title = section.find('h2')
    if section_title:
        print(f"{section_title.get_text()}:")

    details = section.find_all(['dt', 'dd'])
    for i in range(0, len(details), 2):
        dt = details[i].get_text().strip()
        dd = details[i+1].get_text().strip()
        print(f"  {dt}: {dd}")

    print()