data_sources.py

# Import necessary libraries
import requests
from typing import Dict, Any, List, Optional

# URL
GOOGLE_URL = "https://www.googleapis.com/books/v1/volumes"
OPEN_LIB_SEARCH = "https://openlibrary.org/search.json"

def google_books(query: str, max_results: int = 15) -> List[Dict]:
    """ Fetch raw book information from Google Books and convert it into a small dictionary per book. """
    r = requests.get(GOOGLE_URL, params={"q": query, "maxResults": max_results}, timeout=30)
    r.raise_for_status()
    out = []
    for item in r.json().get("items", []) or []:
        vi = item.get("volumeInfo", {}) or {}
        out.append({
            "id": item.get("id"),
            "title": vi.get("title"),
            "authors": "; ".join(vi.get("authors", []) or []),
            "description": vi.get("description", "") or "",
            "categories": "; ".join(vi.get("categories", []) or []),
            "year": (vi.get("publishedDate", "") or "")[:4], # to get only the year
            "cover_url": (vi.get("imageLinks", {}) or {}).get("thumbnail"),
            "preview_url": vi.get("previewLink"),
            "source": "google",
            "subjects": "",   
            "raw": item,
        })
    return out
    

def openlibrary_enrich(title:str) -> Dict[str, Optional[str]]:
    """ Get subjects/tags and better covers if possible by using Open Library.
    If any errors occurs during the process, ir returns "not found" results.
    """
    try:
        # Make a http request
        r = requests.get(OPEN_LIB_SEARCH, params={"title": title, "limit": 1}, timeout=30)
        # check the request status
        r.raise_for_status()
        # parses the response as json and then retrieves the key associate with "docs"
        docs = r.json().get("docs", [])
        # if not titles found return a dictionary saying None
        if not docs:
            return {"subjects": None, "ol_cover_url": None}
        d = docs[0]
        subjects = "; ".join((d.get("subject") or [])[:20]) if d.get("subject") else None
        # construcst the cover url
        cover = f"https://covers.openlibrary.org/b/id/{d['cover_i']}-M.jpg" if d.get("cover_i") else None
        # returns a dictionary contaning subjects and cover url
        return {"subjects": subjects, "ol_cover_url": cover}
    except Exception:
        return {"subjects": None, "ol_cover_url": None}
    

def normalize(book: Dict[str, Any], enrich: Dict[str, Any]) -> Dict[str, Any]:
    """ Merges the infomation from Google books and the information from Open Library
    Inputs:
        book: dictionary from the function google_books()
        enrich: dictionary from the function openlibrary_enrich()
    Ouputs:
        a dictionary with tags/subjects and covers
    
    """
    out = dict(book)
    if enrich.get("subjects"):
        out["subjects"] = enrich["subjects"]
    if enrich.get("ol_cover_url"):
        out["cover_url"] = enrich["ol_cover_url"]
    return out