scrape anime list from https://nimegami.id/

animelist.py

import requests
from bs4 import BeautifulSoup
import time

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/127.0.0.0 Safari/537.36',
}

def fetch_page(url):
    while True:
        try:
            response = requests.get(url, headers=headers, timeout=30, verify=True)
            response.raise_for_status()
            return response
        except requests.RequestException as e:
            print(f"Error fetching {url}: {e}. Retrying in 3 seconds.")
            time.sleep(3)

def extract_anime_data(page_url):
    response = fetch_page(page_url)
    soup = BeautifulSoup(response.content, 'html.parser')
    daftar_anime = soup.find('div', class_='animelist')
    anime_list = []

    for anime in daftar_anime.find_all('li'):
        title_element = anime.find('a')
        status_element = anime.find('span', class_='color_anilist')
        
        if title_element and status_element:
            title = title_element.get_text(strip=True)
            status = status_element.get_text(strip=True)
            link = title_element['href']
            anime_list.append({'title': title, 'status': status, 'link': link})
    
    return anime_list

all_anime_data = []
for page_num in range(1, 8):
    page_url = f'https://nimegami.id/anime-list/page/{page_num}/'
    anime_data = extract_anime_data(page_url)
    all_anime_data.extend(anime_data)
    time.sleep(2)

for anime in all_anime_data:
    print(f"Title: {anime['title']}, Status: {anime['status']}, Link: {anime['link']}")

flaskmain.py

from flask import Flask, jsonify, request
from bs4 import BeautifulSoup
import requests, re, time

app = Flask(__name__)

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/127.0.0.0 Safari/537.36',
}

def fetch_page(url):
    while True:
        try:
            response = requests.get(url, headers=headers, timeout=10)
            response.raise_for_status()
            return response
        except requests.RequestException as e:
            print(f"Error fetching {url}: {e}. Retrying in 3 seconds.")
            time.sleep(3)

def extract_anime_data(page_url, status_filter=None):
    response = fetch_page(page_url)
    soup = BeautifulSoup(response.content, 'html.parser')
    daftar_anime = soup.find('div', class_='animelist')
    anime_list = []

    if daftar_anime:
        for anime in daftar_anime.find_all('li'):
            title_element = anime.find('a')
            status_element = anime.find('span', class_='color_anilist')
            
            if title_element and status_element:
                title = title_element.get_text(strip=True)
                status = status_element.get_text(strip=True)
                link = title_element['href']
                
                # Apply status filter if provided
                if status_filter is None or status_filter.lower() in status.lower():
                    anime_list.append({'title': title, 'status': status, 'link': link})
    
    return anime_list

@app.route('/listanime', methods=['GET'])
@app.route('/listanime/', methods=['GET'])
def list_anime():
    all_anime_data = []
    
    for page_num in range(1, 8):
        page_url = f'https://nimegami.id/anime-list/page/{page_num}/'
        anime_data = extract_anime_data(page_url)
        all_anime_data.extend(anime_data)
        time.sleep(2)
    
    return jsonify(all_anime_data)

@app.route('/listanime/complete', methods=['GET'])
@app.route('/listanime/complete/', methods=['GET'])
def list_anime_complete():
    all_anime_data = []
    
    for page_num in range(1, 8):
        page_url = f'https://nimegami.id/anime-list/page/{page_num}/'
        anime_data = extract_anime_data(page_url, status_filter='Complete')
        all_anime_data.extend(anime_data)
        time.sleep(2)
    
    return jsonify(all_anime_data)

@app.route('/listanime/ongoing', methods=['GET'])
@app.route('/listanime/ongoing/', methods=['GET'])
def list_anime_ongoing():
    all_anime_data = []
    
    for page_num in range(1, 8):
        page_url = f'https://nimegami.id/anime-list/page/{page_num}/'
        anime_data = extract_anime_data(page_url, status_filter='On-Going')
        all_anime_data.extend(anime_data)
        time.sleep(2)
    
    return jsonify(all_anime_data)

@app.route('/listanime/<int:page_num>', methods=['GET'])
def list_anime_page(page_num):
    if page_num < 1 or page_num > 7:
        return jsonify({
            'message': 'Page number out of range. Please use a page number between 1 and 7.',
            'status': 'error',
            'tips': 'Try using a number between 1 and 7.',
            'allanime': request.host_url + 'listanime',
            'animewithpage': request.host_url + 'listanime/1'
        }), 400
    
    page_url = f'https://nimegami.id/anime-list/page/{page_num}/'
    anime_data = extract_anime_data(page_url)
    
    return jsonify(anime_data)

@app.errorhandler(404)
def not_found_error(error):
    requested_url = request.path
    
    if re.match(r'^/listanime(/)?$', requested_url):
        return jsonify({
            'message': 'The requested page does not exist. Please use a valid page number.',
            'status': str(error),
            'tips': 'Visit the main page to see the list of available pages.',
            'allanime': request.host_url + 'listanime',
            'animewithpage': request.host_url + 'listanime/1'
        }), 404

    if re.match(r'^/listanime/complete(/)?$', requested_url):
        return jsonify({
            'message': 'The requested page does not exist. Please use a valid page number.',
            'status': str(error),
            'tips': 'Visit the complete anime page to see the list of available pages.',
            'allanime': request.host_url + 'listanime/complete',
            'animewithpage': request.host_url + 'listanime/complete/1'
        }), 404

    if re.match(r'^/listanime/ongoing(/)?$', requested_url):
        return jsonify({
            'message': 'The requested page does not exist. Please use a valid page number.',
            'status': str(error),
            'tips': 'Visit the ongoing anime page to see the list of available pages.',
            'allanime': request.host_url + 'listanime/ongoing',
            'animewithpage': request.host_url + 'listanime/ongoing/1'
        }), 404
    
    return jsonify({
        'message': 'The requested resource was not found.',
        'status': str(error),
        'allanime': request.host_url + 'listanime',
        'animewithpage': request.host_url + 'listanime/1',
        'tips': 'Check the URL and try again.'
    }), 404

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