Compare commits
3 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| b238b52fbf | |||
| 545dd7783c | |||
| f4ce1cf3b4 |
+109
@@ -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 +9540,113 @@ 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 (Web Scraping für deutsche Schulbücher)
|
||||
Robuste Version mit Fallbacks für Meta-Tags und Tabellendaten.
|
||||
"""
|
||||
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 prüfen
|
||||
title_elem = soup.find('h1')
|
||||
if not title_elem or "nicht gefunden" in title_elem.text.lower() or "Suche" in title_elem.text:
|
||||
return None
|
||||
title = title_elem.text.strip()
|
||||
|
||||
# --- Hilfsfunktion für unstrukturierte HTML-Tabellen ---
|
||||
def get_detail_by_keyword(keywords):
|
||||
"""Sucht nach Schlagwörtern (z.B. 'Verlag') und gibt den angrenzenden Wert zurück."""
|
||||
for tag in soup.find_all(['th', 'td', 'strong', 'b', 'span']):
|
||||
text = tag.text.strip().lower()
|
||||
if any(kw in text for kw in keywords):
|
||||
# Wenn es eine Tabellenzelle (th/td) ist, nimm das nächste Geschwister-Element
|
||||
if tag.name in ['th', 'td']:
|
||||
sibling = tag.find_next_sibling('td')
|
||||
if sibling:
|
||||
return sibling.text.strip()
|
||||
# Wenn es ein Label in einem Listen- oder Absatz-Element ist
|
||||
parent = tag.parent
|
||||
if parent and parent.name in ['li', 'p', 'div']:
|
||||
return parent.text.replace(tag.text, '').strip()
|
||||
return None
|
||||
|
||||
# --- Hilfsfunktion für Schema.org (itemprop) ---
|
||||
def get_itemprop(prop_name):
|
||||
elem = soup.find(attrs={"itemprop": prop_name})
|
||||
if elem:
|
||||
return elem.get('content') or elem.text.strip()
|
||||
return None
|
||||
|
||||
authors = get_itemprop("author")
|
||||
if not authors:
|
||||
authors = get_detail_by_keyword(['autor', 'herausgeber', 'von:'])
|
||||
authors = authors if authors else "Unknown Author"
|
||||
|
||||
publisher = get_itemprop("publisher")
|
||||
if not publisher:
|
||||
publisher = get_detail_by_keyword(['verlag'])
|
||||
publisher = publisher if publisher else "Unknown Publisher"
|
||||
|
||||
pub_date = get_itemprop("datePublished")
|
||||
if not pub_date:
|
||||
pub_date = get_detail_by_keyword(['erscheinungsjahr', 'erschienen', 'datum'])
|
||||
pub_date = pub_date if pub_date else "Unknown Date"
|
||||
|
||||
page_count = get_itemprop("numberOfPages")
|
||||
if not page_count:
|
||||
page_count = get_detail_by_keyword(['seiten', 'umfang'])
|
||||
|
||||
if page_count:
|
||||
match = re.search(r'\d+', page_count)
|
||||
page_count = match.group(0) if match else "Unknown"
|
||||
else:
|
||||
page_count = "Unknown"
|
||||
|
||||
description = get_itemprop("description")
|
||||
if not description:
|
||||
for class_name in ['description', 'zusammenfassung', 'klappentext', 'buch-beschreibung']:
|
||||
fallback_desc = soup.find('div', class_=re.compile(class_name, re.IGNORECASE))
|
||||
if fallback_desc:
|
||||
description = fallback_desc.text.strip()
|
||||
break
|
||||
description = description if description else "Keine Beschreibung verfügbar"
|
||||
|
||||
thumbnail = ""
|
||||
img_elem = soup.find('img', itemprop="image")
|
||||
if not img_elem:
|
||||
img_elem = soup.find('img', class_=lambda c: c and 'cover' in str(c).lower())
|
||||
|
||||
if img_elem and 'src' in img_elem.attrs:
|
||||
thumbnail = img_elem['src']
|
||||
if thumbnail.startswith('/'):
|
||||
thumbnail = "https://www.isbn.de" + thumbnail
|
||||
|
||||
return {
|
||||
"title": title,
|
||||
"authors": authors,
|
||||
"publisher": publisher,
|
||||
"publishedDate": pub_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 +9670,7 @@ def fetch_book_info(isbn):
|
||||
providers = [
|
||||
_fetch_from_google_books,
|
||||
_fetch_from_lobid_germany,
|
||||
_fetch_from_isbn_de,
|
||||
_fetch_from_open_library
|
||||
]
|
||||
|
||||
|
||||
@@ -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>
|
||||
|
||||
|
||||
@@ -15,3 +15,4 @@ openpyxl
|
||||
cryptography>=42.0.0
|
||||
pywebpush
|
||||
py-vapid>=1.9.0
|
||||
beautifulsoup4
|
||||
Reference in New Issue
Block a user