simple downloader class for bloom library

bloom.py

import requests
import json
from urllib.parse import urlparse, urlunparse
import os

# Just a simple downloader 
class BloomDownloader(object):
    def __init__(self):
        self._api_url = "https://server.bloomlibrary.org/parse/classes/books"
        self._headers = {
            "accept": "application/json, text/plain, */*",
            "content-type": "text/json",
            "origin": "https://bloomlibrary.org",
            "referer": "https://bloomlibrary.org/",
            "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/145.0.0.0 Safari/537.36",
            "x-parse-application-id": "R6qNTeumQXjJCMutAJYAwPtip1qBulkFyLefkCE5"
        }
        self._books = []
        self._level = 1
        self._lang = ""
    
    def get_books(self, lang, level=1):
        self._lang = lang
        self._books = []
        self._level = level
    
        in_levels = [f"computedLevel:{level}", f"level:{level}"]
        nin_levels = ["level:1", "level:2", "level:3", "level:4"]
        
        if f'level:{level}' in nin_levels:
            nin_levels.remove(f'level:{level}')
    
        limit = 100
        skip = 0
    
        while True:
            payload = {
                "_method": "GET",
                "keys": "title,baseUrl,objectId,tags",
                "include": "langPointers",
                "limit": limit,
                "skip": skip,
                "where": {
                    "langPointers": {
                        "$inQuery": {
                            "where": {"isoCode": lang},
                            "className": "language"
                        }
                    },
                    "$and": [
                        {"tags": {"$in": in_levels}},
                        {"tags": {"$nin": nin_levels}},
                    ],
                    "inCirculation": True,
                    "draft": False,
                    "rebrand": False,
                    "baseUrl": {"$exists": True}
                },
                "order": "-createdAt"
            }
        
            response = requests.post(self._api_url, headers=self._headers, json=payload)
        
            if response.status_code == 200:
                data = response.json()
                results = data.get("results", [])
            
                if not results:
                    break
                
                self._books.extend(results)
                skip += limit
            else:
                break
        
    
    def get_book_urls(self):
        book_epubs = []
        for book in self._books:
            title = book.get("title")
            objectId = book.get("objectId")
            tags = book.get("tags", [])
            topic_tag = next((t for t in tags if t.startswith("topic:")), "")
            topic = topic_tag.replace("topic:", "")
            base_url = (book.get("baseUrl") or "").replace('%2f', '/')
            parsed = urlparse(base_url)
            parts = parsed.path.split('/')
            parts.insert(-2, 'epub')
            parts[-2] = parts[-2] + '.epub'
            parts.pop()
            new_path = '/'.join(parts)
            new_path = new_path.replace('BloomLibraryBooks', 'bloomharvest')
            new_url_obj = parsed._replace(path=new_path)
            book_epubs.append(
                {
                    "id": objectId,
                    "topic": topic,
                    "title": title, 
                    "epub": urlunparse(new_url_obj),
                    "bloom_url": f"https://bloomlibrary.org/language:{self._lang}/book/{objectId}?lang={self._lang}"
                }
            )
        return book_epubs
    
    def dump_json(self):
        return json.dumps(self._books, indent=4)
    
    def download_books(self, save_dir=f"bloom"):
        save_dir = save_dir + f'/{self._lang}/{self._level}'
        if not os.path.exists(save_dir):
            os.makedirs(save_dir)
        
        books_to_download = self.get_book_urls()
    

        for i, book in enumerate(books_to_download, 1):
            url = book['epub']
            filename = f'{book["id"]}.epub'
        
            filepath = os.path.join(save_dir, filename)
        
            try:
                with requests.get(url, stream=True, timeout=20) as r:
                    if r.status_code == 200:
                        with open(filepath, 'wb') as f:
                            for chunk in r.iter_content(chunk_size=8192):
                                f.write(chunk)
                    else:
                        print(f"  FAILED: Status {r.status_code} for {url}")
            except Exception as e:
                print(f"  ERROR downloading {book['title']}: {e}")

        
        
        
bloom = BloomDownloader()
bloom.get_books('ceb', 1)
bloom.download_books()