bsshare/bsupdate.py

import requests
from bs4 import BeautifulSoup
from urllib.parse import urlparse
import os
from dotenv import load_dotenv

if "BOOKSTACK_URL" not in os.environ:
   print("Environment variables not read. Try reading from file.")
   load_dotenv()

BOOKSTACK_URL = os.getenv("BOOKSTACK_URL","https://my-book-stack.com")
BOOKSTACK_TOKEN_ID = os.getenv("BOOKSTACK_TOKEN_ID", "TOKEN-ID")
BOOKSTACK_TOKEN_SECRET = os.getenv("BOOKSTACK_TOKEN_SECRET", "TOKEN-SECRET")
PAGE_SLUG = os.getenv("PAGE_SLUG","page-name-of-book")
BOOK_SLUG = os.getenv("BOOK_SLUG","book-name")
INSERT_MARKER_LINK = os.getenv("INSERT_MARKER_LINK", "## Unsortierte Links")
INSERT_MARKER_TEXT = os.getenv("INSERT_MARKER_TEXT", "## Textmerker")

HEADERS = {
    "Accept": "application/json",
    "Content-Type": "application/json",
    "Authorization": f"Token {BOOKSTACK_TOKEN_ID}:{BOOKSTACK_TOKEN_SECRET}"
}


def is_valid_url(url):
    parsed = urlparse(url)
    return all([parsed.scheme in ("http", "https"), parsed.netloc])


def get_page_id_by_slug(book_slug, page_slug):
   res = requests.get(f"{BOOKSTACK_URL}/api/pages", headers=HEADERS)
   print(HEADERS)
   print(res)
   pages = res.json().get("data", [])
   for p in pages:
      if p["book_slug"] == book_slug and p["slug"] == page_slug:
         return p["id"]
   
   raise("Book not found")
 

def get_page_title_from_url(url):
    try:
        response = requests.get(url, timeout=10)
        soup = BeautifulSoup(response.text, "html.parser")
        title_tag = soup.find("title")
        return title_tag.text.strip() if title_tag else url
    except Exception as e:
        print(f"Fehler beim Abrufen des Titels: {e}")
        return url
     
     
def get_clean_title_from_url(url, max_len=80):
    try:
        res = requests.get(url, timeout=10)
        res.raise_for_status()
        soup = BeautifulSoup(res.text, "html.parser")

        # 1. og:title
        og_title = soup.find("meta", property="og:title")
        if og_title and og_title.get("content"):
            title = og_title["content"]

        # 2. <meta name="title">
        elif soup.find("meta", attrs={"name": "title"}):
            title = soup.find("meta", attrs={"name": "title"}).get("content", "")

        # 3. <title>
        elif soup.title and soup.title.string:
            title = soup.title.string

        # 4. Fallback: Domain
        else:
            return urlparse(url).netloc

        title = title.strip()

        # Optional: Aufteilen an Trennzeichen wie " | " oder " – "
        for sep in ["|", "–", "-", "•"]:
            if sep in title:
                title = title.split(sep)[0].strip()
                break

        # Länge kürzen
        if len(title) > max_len:
            title = title[:max_len].rstrip() + "…"

        return title

    except Exception as e:
        print(f"Fehler beim Abrufen oder Parsen des Titels: {e}")
        return urlparse(url).netloc  # Fallback auf Domain


def append_link_to_bookstack_page(url): 
   strPageId = get_page_id_by_slug(BOOK_SLUG, PAGE_SLUG)

   # Hole aktuellen Seiteninhalt
   page = requests.get(f"{BOOKSTACK_URL}/api/pages/{strPageId}", headers=HEADERS).json()
   current_content = page["markdown"]

   if url in current_content:
      print("Text bereits vorhanden.")
      return

   title = get_page_title_from_url(url)
   new_entry = f"- [{title}]({url})<br>{url}"

   # Füge Link unterhalb von INSERT_MARKER_LINK ein
   if INSERT_MARKER_LINK in current_content:
     parts = current_content.split(INSERT_MARKER_LINK)
     updated_content = parts[0] + INSERT_MARKER_LINK + "\n" + new_entry + parts[1]
   else:
     # Falls Marker nicht vorhanden, füge ihn am Ende hinzu
     updated_content = current_content + "\n\n" + INSERT_MARKER_LINK + "\n\n" + new_entry

   # Seite aktualisieren
   update_data = {
     "name": page["name"],
     "markdown": updated_content
   }

   response = requests.put(
     f"{BOOKSTACK_URL}/api/pages/{strPageId}",
     headers=HEADERS,
     json=update_data
   )

   if response.status_code == 200:
     print("Link erfolgreich hinzugefügt.")
   else:
     print("Fehler beim Aktualisieren der Seite:", response.text)
        
def append_text_to_bockstack_page(strText):
   strPageId = get_page_id_by_slug(BOOK_SLUG, PAGE_SLUG)
    
   # Hole aktuellen Seiteninhalt
   page = requests.get(f"{BOOKSTACK_URL}/api/pages/{strPageId}", headers=HEADERS).json()
   current_content = page["markdown"]
   
   if strText in current_content:
      print("Text bereits vorhanden.")
      return

   new_entry = strText + "\n\n"

   # Füge Text unterhalb von INSERT_MARKER_TEXT ein
   if INSERT_MARKER_TEXT in current_content:
     parts = current_content.split(INSERT_MARKER_TEXT)
     updated_content = parts[0] + INSERT_MARKER_TEXT + "\n\n" + new_entry + "\n" + parts[1]
   else:
     # Falls Marker nicht vorhanden, füge ihn am Ende hinzu
     updated_content = current_content + "\n\n" + INSERT_MARKER_TEXT + "\n\n" + new_entry

   # Seite aktualisieren
   update_data = {
     "name": page["name"],
     "markdown": updated_content
   }

   response = requests.put(
     f"{BOOKSTACK_URL}/api/pages/{strPageId}",
     headers=HEADERS,
     json=update_data
   )

   if response.status_code == 200:
     print("Link erfolgreich hinzugefügt.")
   else:
     print("Fehler beim Aktualisieren der Seite:", response.text)


def add_link_or_text(strText):
   if (is_valid_url(strText)):
      append_link_to_bookstack_page(strText)
   else:
      append_text_to_bockstack_page(strText)
   pass