Compare commits
7 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 3f90e2d4f1 | |||
| b238b52fbf | |||
| 545dd7783c | |||
| f4ce1cf3b4 | |||
| 7bd12bddaa | |||
| b8e23b94d2 | |||
| 06b32b4a3d |
+111
@@ -25,6 +25,7 @@ from werkzeug.routing import BuildError
|
||||
from jinja2 import TemplateNotFound
|
||||
import os
|
||||
import sys
|
||||
from bs4 import BeautifulSoup
|
||||
|
||||
# Ensure imports work regardless of whether gunicorn starts in /app or /app/Web.
|
||||
_CURRENT_DIR = os.path.dirname(os.path.abspath(__file__))
|
||||
@@ -9539,6 +9540,115 @@ def _fetch_from_open_library(clean_isbn):
|
||||
print(f"OpenLibrary Search error: {e}")
|
||||
return None
|
||||
|
||||
def _fetch_from_isbn_de(clean_isbn):
|
||||
"""
|
||||
Source 4: isbn.de (Maßgeschneidertes Scraping basierend auf realer HTML-Struktur)
|
||||
Nutzt Open-Graph Meta-Tags und durchsucht die .infotab-Struktur der Sidebar.
|
||||
"""
|
||||
try:
|
||||
url = f"https://www.isbn.de/buch/{clean_isbn}"
|
||||
headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
|
||||
}
|
||||
|
||||
response = requests.get(url, headers=headers, timeout=5)
|
||||
if response.status_code != 200:
|
||||
return None
|
||||
|
||||
soup = BeautifulSoup(response.text, 'html.parser')
|
||||
|
||||
# 1. Titel aus den Meta-Tags extrahieren (extrem zuverlässig)
|
||||
title_meta = soup.find('meta', property='og:title')
|
||||
title = title_meta.get('content', '').strip() if title_meta else None
|
||||
if not title:
|
||||
h1_elem = soup.find('h1')
|
||||
title = h1_elem.text.strip() if h1_elem else "Unknown Title"
|
||||
|
||||
# Falls wir auf einer Fehler-/Suchseite landen
|
||||
if "nicht gefunden" in title.lower() or "suche" in title.lower():
|
||||
return None
|
||||
|
||||
# --- Hilfsfunktion zum Parsen der .infotab-Sidebar-Struktur ---
|
||||
# Jede Zeile dort ist aufgebaut als: <div><div>Label</div>Wert</div>
|
||||
def get_sidebar_value(keyword):
|
||||
infotab = soup.find(class_='infotab')
|
||||
if infotab:
|
||||
for d in infotab.find_all('div'):
|
||||
# Prüfe, ob der Text im inneren Label-Div mit dem Keyword übereinstimmt
|
||||
if d.text.strip().lower() == keyword.lower():
|
||||
parent = d.parent
|
||||
# Ziehe das Label vom Gesamttext ab, um nur den Wert zu erhalten
|
||||
return parent.text.replace(d.text, '', 1).strip()
|
||||
return None
|
||||
|
||||
# 2. Verlag holen
|
||||
publisher = get_sidebar_value('verlag')
|
||||
if not publisher:
|
||||
publisher = "Unknown Publisher"
|
||||
|
||||
# 3. Erscheinungsdatum (Aus Meta-Tag oder Sidebar)
|
||||
date_meta = soup.find('meta', property='og:book:release_date')
|
||||
if date_meta and date_meta.get('content'):
|
||||
published_date = date_meta.get('content', '').strip()
|
||||
else:
|
||||
published_date = get_sidebar_value('erschienen am')
|
||||
|
||||
if not published_date:
|
||||
published_date = "Unknown Date"
|
||||
|
||||
# 4. Autor (Schulbücher haben oft keinen Einzelautor, daher kluger Fallback)
|
||||
author_meta = soup.find('meta', property='og:book:author')
|
||||
author = author_meta.get('content', '').strip() if author_meta else ""
|
||||
if not author:
|
||||
author = get_sidebar_value('autor') or get_sidebar_value('herausgeber')
|
||||
|
||||
if not author:
|
||||
# Wenn kein Autor existiert, ist es eine Verlagsredaktion (z.B. "Klett Redaktion")
|
||||
author = f"{publisher} Redaktion" if publisher != "Unknown Publisher" else "Unknown Author"
|
||||
|
||||
# 5. Seitenanzahl
|
||||
page_count = get_sidebar_value('seiten') or get_sidebar_value('umfang')
|
||||
if page_count:
|
||||
match = re.search(r'\d+', page_count)
|
||||
page_count = match.group(0) if match else "Unknown"
|
||||
else:
|
||||
page_count = "Unknown"
|
||||
|
||||
# 6. Beschreibung aus dem zentralen Textfeld holen und Whitespace bereinigen
|
||||
description = "Keine Beschreibung verfügbar"
|
||||
desc_div = soup.find(id='bookdesc')
|
||||
if desc_div:
|
||||
# Kombiniert <p> und <ul>-Inhalte zu sauberem Fließtext ohne Zeilenumbruch-Chaos
|
||||
description = " ".join(desc_div.text.split())
|
||||
|
||||
# 7. Cover-Bild (Nutzt den direkten Link zum hochauflösenden Bild aus den Metas)
|
||||
thumbnail = ""
|
||||
img_meta = soup.find('meta', property='og:image')
|
||||
if img_meta:
|
||||
thumbnail = img_meta.get('content', '').strip()
|
||||
else:
|
||||
img_tag = soup.find('img', id='ISBNcover')
|
||||
if img_tag:
|
||||
thumbnail = img_tag.get('data-big') or img_tag.get('src')
|
||||
|
||||
if thumbnail and thumbnail.startswith('/'):
|
||||
thumbnail = "https://www.isbn.de" + thumbnail
|
||||
|
||||
return {
|
||||
"title": title,
|
||||
"authors": author,
|
||||
"publisher": publisher,
|
||||
"publishedDate": published_date,
|
||||
"description": description,
|
||||
"pageCount": page_count,
|
||||
"price": None,
|
||||
"thumbnail": thumbnail,
|
||||
"source": "isbn-de"
|
||||
}
|
||||
except Exception as e:
|
||||
print(f"isbn.de Scraping error: {e}")
|
||||
return None
|
||||
|
||||
@app.route('/fetch_book_info/<isbn>')
|
||||
def fetch_book_info(isbn):
|
||||
"""
|
||||
@@ -9562,6 +9672,7 @@ def fetch_book_info(isbn):
|
||||
providers = [
|
||||
_fetch_from_google_books,
|
||||
_fetch_from_lobid_germany,
|
||||
_fetch_from_isbn_de,
|
||||
_fetch_from_open_library
|
||||
]
|
||||
|
||||
|
||||
@@ -38,7 +38,7 @@ def _active_record_query(extra_query=None):
|
||||
return base_query
|
||||
|
||||
|
||||
def add(date_start: str, date_end: str, time_span: list, slots: int, slot_lenght: int, user: str, mail: list=[], note:str="", calendar_enabled: bool=False):
|
||||
def add(date_start: str, date_end: str, time_span: list, slots: int, slot_lenght: int, user: str, mail: list=[], note:str="", calendar_enabled: bool=False, title: str=""):
|
||||
try:
|
||||
client = MongoClient(cfg.MONGODB_HOST, cfg.MONGODB_PORT)
|
||||
db = _get_tenant_db(client)
|
||||
@@ -53,6 +53,7 @@ def add(date_start: str, date_end: str, time_span: list, slots: int, slot_lenght
|
||||
'user': user,
|
||||
'mail': mail,
|
||||
'note': note,
|
||||
'title': title,
|
||||
'calendar_enabled': bool(calendar_enabled),
|
||||
'slots_booked': [], # -> [(start_time, name), ...]the list gets there indexes as the slot 1-defined so is can be counted without an extra variable
|
||||
'Created': datetime.datetime.now(),
|
||||
|
||||
@@ -15,3 +15,4 @@ openpyxl
|
||||
cryptography>=42.0.0
|
||||
pywebpush
|
||||
py-vapid>=1.9.0
|
||||
beautifulsoup4
|
||||
@@ -28,11 +28,10 @@
|
||||
<li class="nav-item" role="presentation">
|
||||
<button class="nav-link" id="tab-legal" data-bs-toggle="tab" data-bs-target="#pane-legal"
|
||||
type="button" role="tab">Rechtsgrundlage</button>
|
||||
</li>
|
||||
</ul>
|
||||
|
||||
<!-- ── NOTICE ────────────────────────────────────────────────────── -->
|
||||
<div class="tab-pane fade" id="pane-notice" role="tabpanel">
|
||||
<div class="tab-pane" id="pane-notice" role="tabpanel">
|
||||
<div class="license-content">
|
||||
<h2>NOTICE – Urheberrechtliche Hinweise</h2>
|
||||
<p><strong>Invario Modul Suite</strong><br>Copyright © 2026 Invario UG</p>
|
||||
@@ -59,14 +58,14 @@
|
||||
|
||||
<h4>Frontend / Laufzeit-Assets</h4>
|
||||
<ul>
|
||||
<li>html5-qrcode (MIT) © 2020-2025 Manoj Brahmbhatt (mebjas)</li>
|
||||
<li>quagga2 (MIT) © 2014 Christoph Oberhofer, © 2019 Eric Blade and contributors</li>
|
||||
</ul>
|
||||
<hr>
|
||||
</div>
|
||||
</div><!-- /#pane-notice -->
|
||||
|
||||
<!-- ── DATENSCHUTZ ───────────────────────────────────────────────── -->
|
||||
<div class="tab-pane fade" id="pane-privacy" role="tabpanel">
|
||||
<div class="tab-pane" id="pane-privacy" role="tabpanel">
|
||||
<div class="license-content">
|
||||
<h2>Datenschutzerklärung (Privacy Policy)</h2>
|
||||
|
||||
@@ -108,7 +107,7 @@
|
||||
</div><!-- /#pane-privacy -->
|
||||
|
||||
<!-- ── SICHERHEIT ────────────────────────────────────────────────── -->
|
||||
<div class="tab-pane fade" id="pane-security" role="tabpanel">
|
||||
<div class="tab-pane" id="pane-security" role="tabpanel">
|
||||
<div class="license-content">
|
||||
<h2>Sicherheitsrichtlinie (Security Policy)</h2>
|
||||
|
||||
@@ -129,7 +128,7 @@
|
||||
</div><!-- /#pane-security -->
|
||||
|
||||
<!-- ── DATENVERARBEITUNG ─────────────────────────────────────────── -->
|
||||
<div class="tab-pane fade" id="pane-data" role="tabpanel">
|
||||
<div class="tab-pane" id="pane-data" role="tabpanel">
|
||||
<div class="license-content">
|
||||
<h2>Dokumentation der Datenverarbeitung (VVT)</h2>
|
||||
|
||||
@@ -157,7 +156,7 @@
|
||||
</div><!-- /#pane-data -->
|
||||
|
||||
<!-- ── RECHTSGRUNDLAGE ───────────────────────────────────────────── -->
|
||||
<div class="tab-pane fade" id="pane-legal" role="tabpanel">
|
||||
<div class="tab-pane" id="pane-legal" role="tabpanel">
|
||||
<div class="license-content">
|
||||
<h2>Rechtsgrundlage der Nutzung</h2>
|
||||
<p>Um das Inventarsystem DSGVO-konform zu betreiben, muss der Betreiber eine der folgenden Grundlagen festlegen:</p>
|
||||
@@ -170,9 +169,6 @@
|
||||
Einwilligung vorliegen (Art. 6 Abs. 1 lit. a DSGVO).</li>
|
||||
</ol>
|
||||
</div>
|
||||
</div><!-- /#pane-legal -->
|
||||
|
||||
</div><!-- /.tab-content -->
|
||||
</div>
|
||||
</div>
|
||||
|
||||
|
||||
@@ -43,7 +43,7 @@
|
||||
<div class="card border-0 shadow-lg rounded-4 h-100">
|
||||
<div class="card-body p-4 p-md-5">
|
||||
<p class="text-uppercase text-muted fw-semibold mb-2">Terminplaner</p>
|
||||
<h1 class="h3 fw-bold mb-3">Termin buchen</h1>
|
||||
<h1 class="h3 fw-bold mb-3">Termin buchen - {{ available.title }}</h1>
|
||||
<p class="text-muted mb-4">Wählen Sie im Kalender einen freien Slot aus. Den gewählten Termin können Sie danach direkt wie in einem Kalender-Block verschieben.</p>
|
||||
|
||||
<div class="p-3 rounded-3 bg-light mb-3">
|
||||
|
||||
@@ -15,3 +15,4 @@ openpyxl
|
||||
cryptography>=42.0.0
|
||||
pywebpush
|
||||
py-vapid>=1.9.0
|
||||
beautifulsoup4
|
||||
Reference in New Issue
Block a user