Author's book list:

# start xml

import os

import io

import ssl

import unicodedata

import requests

import xml.etree.ElementTree as ET

from urllib.parse import urlencode

from django.core.cache import cache

from django.core.paginator import Paginator, PageNotAnInteger, EmptyPage

from django.template.exceptions import TemplateDoesNotExist

from django.shortcuts import render

def _norm(s: str) -> str:

    """Normaliza texto: minúsculas, sin acentos, espacios compactados."""

    if not s:

        return ""

    s = unicodedata.normalize("NFKD", s)

    s = "".join(c for c in s if not unicodedata.combining(c))

    return " ".join(s.lower().strip().split())

def _fetch_books_catalog(file_id):

    """Descarga books.xml desde Drive y devuelve el catálogo completo normalizado.

    Es la parte cara (~12 MB de descarga + parseo de ~10.000 items), así que su

    resultado se cachea; los campos *_norm precomputados dejan el filtro por

    request en una pasada barata sobre la lista.

    """

    xml_bytes = download_gdrive_public_file(file_id)

    root = parse_xml_bytes(xml_bytes)

    catalog = []

    # Recorremos items; las etiquetas son <item>, <auth>, <book>, etc.

    for node in root.findall(".//item"):

        def tx(tag):

            el = node.find(tag)

            return (el.text if el is not None and el.text is not None else "").strip()

        author_raw = tx("auth")

        title_raw  = tx("book")

        img_raw = tx("img_url")

        if img_raw and not img_raw.startswith(("http://", "https://")):

            img_raw = "https://" + img_raw.lstrip("/")

        catalog.append({

            "id":           tx("isbn"),

            "title":        title_raw,

            "title_norm":   _norm(title_raw),

            "author_norm":  _norm(author_raw),

            "language":     tx("lang").capitalize(),

            "price":        tx("euro"),

            "publish_date": tx("year"),

            "description":  tx("about"),

            "publisher":    tx("publ").capitalize(),

            "tags":         tx("tags"),

            "img":          img_raw,

            "page":         tx("page"),

        })

    return catalog

def xml_books(request):

    search_line   = "# start xml"

    pattern       = "# finish_books_xml"

    # Desde el disco, nunca por HTTP a este mismo host: con el único dyno ocupado esa

    # auto-petición agotaba el timeout y la página devolvía 500 (auditoría 2026-08-20).

    content_json_url = "/static/json/data-science/content.json"

    project_key   = "books-store-xml"

    template_path = "portfolio/templates/data-science/books-store-xml/index.html"

    # --- Cargar snippets/metadata/plantilla ---------------------------------

    try:

        views_code        = get_views_code(search_line, pattern, module_dir)

        content_json_data = get_content_json_data(content_json_url, project_key)

        template_code     = get_template_code(template_path)

    except FileNotFoundError:

        ctx = {

            "description": "File not found. Please check the file path or create the file if it does not",

            "reference": "Read & Process Excel files with Data Frame",

        }

        print("❌ Error cargando content_json/plantilla/snippets (FileNotFoundError)")

        return render(request, "data-science/retrieve_error.html", ctx)

    except TemplateDoesNotExist:

        ctx = {

            "description": "Template not found. Please check the file path or create the file if it does not",

            "reference": "Books Store connection from XML File",

        }

        print("❌ Error: TemplateDoesNotExist")

        return render(request, "data-science/retrieve_error.html", ctx)

    # --- Descargar y parsear el XML desde Drive ------------------------------

    # Usa el ID definido en el entorno para evitar endurecerlo en código.

    file_id = '1Lk_-zqbRIT4nd-0oJWLxWnpLOwxnXGz5'

    if not file_id:

        ctx = {

            "description": "Falta la variable de entorno GDRIVE_BOOKS_FILE_ID con el ID del archivo XML.",

            "reference": "Books Store connection from XML File",

        }

        print("❌ Falta GDRIVE_BOOKS_FILE_ID")

        return render(request, "data-science/retrieve_error.html", ctx)

    try:

        # LocMemCache por proceso: cada worker de gunicorn guarda su copia y

        # se ahorra la descarga/parseo de Drive durante 15 minutos.

        catalog = cache.get_or_set(

            "xml_books_catalog", lambda: _fetch_books_catalog(file_id), 60 * 15

        )

    except Exception as e:

        # El detalle de la excepción va solo al log: renderizarlo exponía la

        # URL de la Drive API (con la key incluida) en la página pública.

        ctx = {"description": "No se pudo descargar books.xml desde Google Drive. Inténtalo más tarde.",

               "reference": "Books Store connection from XML File"}

        print("❌ Error descargando o parseando XML:", repr(e))

        return render(request, "data-science/retrieve_error.html", ctx)

    # --- Filtrado sobre el catálogo cacheado ---------------------------------

    books = []

    q_author = _norm(request.GET.get("author_name") or "")

    q_title  = _norm(request.GET.get("title") or "")

    for book in catalog:

        ok = True

        if q_author:

            ok = ok and (q_author in book["author_norm"])

        if q_title:

            ok = ok and (q_title in book["title_norm"])

        if ok:

            books.append(book)

    # Log de depuración

    print(f"xml_books: encontrados {len(books)} libros para author='{q_author}' title='{q_title}'")

    # (Opcional) ver 3 ejemplos sin filtrar

    # for i, sample in enumerate(root.findall('.//item')[:3], 1):

    #     print("SAMPLE", i, "AUTH=", (sample.findtext('auth') or '').strip(),

    #           "TITLE=", (sample.findtext('book') or '').strip())

    # --- Paginación ----------------------------------------------------------

    # Sin ella, los ~10.000 libros del XML generaban un HTML de ~31 MB.

    paginator = Paginator(books, 12)

    page = request.GET.get("page")

    try:

        books_page = paginator.page(page)

    except PageNotAnInteger:

        books_page = paginator.page(1)

    except EmptyPage:

        books_page = paginator.page(paginator.num_pages)

    # Query string extra para que PREV/NEXT conserven los filtros activos.

    filter_params = {k: request.GET[k] for k in ("author_name", "title") if request.GET.get(k)}

    extra_qs = "&" + urlencode(filter_params) if filter_params else ""

    context = {

        "books": books_page,

        "extra_qs": extra_qs,

        "author": q_author,

        "views": views_code,

        "content": content_json_data,

        "template": template_code,

    }

    return render(request, "data-science/books-store-xml/index.html", context)

{% extends 'base.html' %}

{% load i18n %}
{% load static %}
{% load cached_pygments %}
{% block title %}{% trans "XML Books Store (ElementTree)" %} | Marco A. Parra F.{% endblock %}
{% block meta_description %}{% trans "Parse an XML catalogue with ElementTree and filter it from a Django form." %}{% endblock %}
{% block content %}
<br>
<br>
<!-- ================= XML BOOKS: DOCUMENTACIÓN ================= -->
<!-- ===== XML BOOKS: Compact Doc Section with Show More ===== -->
<section id="xml-books-docs" class="container my-5">
  <!-- Header -->
  <div class="row align-items-center">
    <div class="col-auto">
      <img src="{% static 'img/worldwide.gif' %}" alt="" style="height:56px;">
    </div>
    <div class="col">
      <h2 class="mb-1">XML Books — Project Overview</h2>
      <div class="small text-muted">Django + XML + Google Drive API</div>
    </div>
  </div>

  <!-- Always-visible essentials -->
  <div class="card shadow-sm mt-3">
    <div class="card-body">
      <p class="mb-3">
        <strong>Summary:</strong> XML Books loads a book catalog from an XML file stored in Google Drive, validates and parses it
        at request time, and exposes simple filters by <em>author</em> and <em>title</em>. The goal is to keep the app lightweight
        (no large datasets in the repo) while demonstrating external storage integration and clean UI rendering in Django.
      </p>

      <div class="mb-3">
        <span class="badge bg-dark me-1">Django 4.1</span>
        <span class="badge bg-secondary me-1">Python 3.11</span>
        <span class="badge bg-info text-dark me-1">Requests</span>
        <span class="badge bg-warning text-dark me-1">Google Drive API</span>
        <span class="badge bg-primary">XML</span>
      </div>

      <div class="d-flex flex-wrap gap-2">
        <a class="btn btn-success btn-sm" target="_blank"
           href="https://portfolio-mparraf.herokuapp.com/data-science/books-filter/">
          Open Endpoint
        </a>

        <!-- Show more toggle -->
        <button class="btn btn-outline-primary btn-sm"
                type="button"
                data-bs-toggle="collapse"
                data-bs-target="#xmlBooksMore"
                aria-expanded="false"
                aria-controls="xmlBooksMore">
          Show more
        </button>
      </div>
    </div>

    <!-- Collapsible: more details -->
    <div id="xmlBooksMore" class="collapse">
      <hr class="my-0">
      <div class="card-body pt-4">
        <!-- Goals -->
        <h5 class="mb-2">Goals</h5>
        <ul class="mb-4">
          <li>Load and validate an XML dataset from Google Drive (folder-scoped query + file download).</li>
          <li>Defend against HTML previews/warnings from Drive before parsing.</li>
          <li>Filter results via query params (<code>?author=...</code>, <code>?title=...</code>).</li>
          <li>Keep the Heroku slug small (no heavy datasets in the repo).</li>
        </ul>

        <!-- Architecture -->
        <h5 class="mb-2">High-level Architecture</h5>
        <ol class="mb-4">
          <li>View <code>xml_books</code> reads query params and builds the Drive request.</li>
          <li>File listing by folder + exact filename; then direct file download.</li>
          <li>Guard: if payload looks like HTML, abort parsing (Drive preview pages).</li>
          <li>Parse with <code>xml.etree.ElementTree</code> and normalize CDATA/text.</li>
          <li>Filter and render results with Bootstrap.</li>
        </ol>

        <!-- Env Vars -->
        <h5 class="mb-2">Environment Variables</h5>
        <div class="table-responsive mb-3">
          <table class="table table-sm align-middle">
            <thead class="table-light">
              <tr><th scope="col">Variable</th><th scope="col">Description</th><th scope="col">Example</th></tr>
            </thead>
            <tbody>
              <tr>
                <td><code>GOOGLE_DRIVE_API_KEY</code></td>
                <td>API Key for Google Drive (Files: list/get).</td>
                <td><code>AIzaSy...xyz</code></td>
              </tr>
              <tr>
                <td><code>GOOGLE_DRIVE_FOLDER_ID</code></td>
                <td>Folder ID containing the XML file.</td>
                <td><code>1AbCdEfGhIJ...</code></td>
              </tr>
              <tr>
                <td><code>BOOKS_XML_FILENAME</code></td>
                <td>Exact XML filename to fetch.</td>
                <td><code>books.xml</code></td>
              </tr>
            </tbody>
          </table>
        </div>

        <!-- Endpoint usage -->
        <h5 class="mb-2">Endpoint & Usage</h5>
        <div class="table-responsive mb-3">
          <table class="table table-hover align-middle">
            <thead class="table-light">
              <tr><th scope="col">Endpoint</th><th scope="col">Description</th><th scope="col">Params</th><th scope="col">Examples</th></tr>
            </thead>
            <tbody>
              <tr>
                <td><code>/data-science/books-filter/</code></td>
                <td>Returns the book list from remote XML with optional filters.</td>
                <td><code>author</code> (optional), <code>title</code> (optional)</td>
                <td>
                  <code>?author=arturo</code><br>
                  <code>?title=sidi</code><br>
                  <code>?author=arturo&amp;title=sidi</code>
                </td>
              </tr>
            </tbody>
          </table>
        </div>

        <!-- Error handling -->
        <h5 class="mb-2">Error Handling</h5>
        <ul class="mb-0">
          <li><strong>404/403</strong> listing Drive: check <code>GOOGLE_DRIVE_FOLDER_ID</code> permissions.</li>
          <li><strong>HTML payload</strong> (preview/warning): abort parsing to avoid XML errors.</li>
          <li><strong>XML ParseError</strong>: malformed or truncated XML; verify the source file.</li>
          <li><strong>Timeouts</strong>: add caching and increase request timeout if needed.</li>
        </ul>
      </div>
    </div>
  </div>
</section>
<!-- ===== /XML BOOKS: Compact Doc Section with Show More ===== -->



<!-- ================= /XML BOOKS: DOCUMENTACIÓN ================= -->


<section class="container-section mb-4">
    <div class="container-fluid">
        <div class="row g-0">
            <div class="portfolio-box-caption">
                Books Store
            </div>
        </div>
        <hr>
        <div>

        </div>
        <div class="container">
            <div class="row border mt-3">
                <h2>{% trans "Search Form" %}</h2>
                <form method="get" action="{% url 'xml_books' %}">
                    {% csrf_token %}
                    <div class="row">
                        <div class="col-12 col-sm-6">
                            <div class="form-group mb-3">
                                <label for="author_name">Author Name:</label>
                                <input type="text" class="form-control" id="author_name" name="author_name" placeholder="Enter a value">
                            </div>
                        </div>
                        <div class="col-12 col-sm-6">
                            <div class="form-group mb-3">
                                <label for="title">Book Title:</label>
                                <input type="text" class="form-control" id="title" name="title" placeholder="Enter a value">
                            </div>
                        </div>
                    </div>
                    <button type="submit" class="btn btn-primary">{% trans "Search" %}</button>
                </form>
            </div>
            <hr>
            <div class="row mb-5 border">
                <h1>Author's book list: {{ author }}</h1>
            </div>

            <div class="row mt-3" id="books-list">
                {% for item in books %}
                <div class="col-12 col-sm-6">
                    <div class="card text-dark bg-light mb-3 align-items-center">
                        <img src="{{ item.img }}" class="card-img-top img-fluid" style="height: 15rem;"alt="{{ item.title }}">
                        <div class="card-header">
                            <h2 class="card-title">{{ item.title }}</h2>
                            <div class="row">
                                <div class="col-lg-6 col-sm-12 ">
                                    <h6 class="card-subtitle mb-2 text-muted">ISBN: <strong>{{ item.id }}</strong></h6>
                                </div>
                                <div class="col-lg-6 col-sm-12 ">
                                    <h6 class="card-subtitle mb-2 text-muted">Page: <strong>{{ item.page }}</strong></h6>
                                </div>
                            </div>
                            <div class="row">
                                <div class="col-lg-5 col-sm-12 ">
                                    <h6 class="card-subtitle mb-2 text-muted">Lang: <strong>{{ item.language }}</strong></h6>
                                </div>
                                <div class="col-lg-3 col-sm-12 ">
                                    <h6 class="card-subtitle mb-2 text-muted">Year: <strong>{{ item.publish_date }}</strong></h6>
                                </div>
                                <div class="col-lg-4 col-sm-12 ">
                                    <h6 class="card-subtitle mb-2 text-muted">Price: <strong>{{ item.price }}</strong></h6>
                                </div>
                            </div>
                            <div class="row">
                                <h6 class="card-subtitle mb-2 text-muted">Publisher By: <strong>{{ item.publisher }}</strong></h6>
                            </div>
                            <div class="row">
                                <h6 class="card-subtitle mb-2 text-muted">Tags: <strong>{{ item.tags }}</strong></h6>
                            </div>
                        </div>
                        <div class="card-body" style="height: 15rem; overflow:auto;">
                            <p class="cart-text d-sm-block show-read-more p-3 mt-2">{{ item.description }}</p>
                        </div>
                    </div>
                </div>
                {% endfor %}
            </div>

            <div class="row d-flex align-items-center mb-4">
                <div class="col-auto">
                    {% if books.has_previous %}
                    <a class="btn btn-outline-secondary" href="?page={{ books.previous_page_number }}{{ extra_qs }}#books-list">« PREV</a>
                    {% endif %}
                </div>
                <div class="col-auto text-muted">
                    Page {{ books.number }} of {{ books.paginator.num_pages }} ({{ books.paginator.count }} books)
                </div>
                <div class="col-auto">
                    {% if books.has_next %}
                    <a class="btn btn-outline-secondary" href="?page={{ books.next_page_number }}{{ extra_qs }}#books-list">NEXT »</a>
                    {% endif %}
                </div>
            </div>
        </div>
    </div>
</section>

<section class="container-section mb-4">
    <div class="container-fluid">
        <div class="row g-0">
            <div class="portfolio-box-caption">
                <div class="row">
                    <div class="col-12 col-sm-10">
                        <h3 class="portfolio-box-headers" style="text-align:center">
                            {% trans "Show Code" %}</h3>
                    </div>
                    <div class="col">
                        <button type="button" class="btn btn-light" onclick="$('#section-w').toggle();">
                            Show/Hide
                        </button>
                    </div>
                </div>
            </div>
            <hr>
            <div class="container" style="display:none;" id="section-w">
                <div class="row mb-4">
                    <div class="col">
                        <h4>views.py Code</h4>
                        <div class="sourcecode">
                            {% for item in views %}
                            {{ item|pygmentize:"python3" }}
                            {% endfor %}
                        </div>
                    </div>
                    <div class="col">
                        <h4>Template</h4>
                        <div class="sourcecode">
                            {{ template|pygmentize:"html" }}
                        </div>
                    </div>
                </div>
            </div>
        </div>
    </div>
</section>

{% endblock %}