src/logic/swb.py

@@ -1,11 +1,27 @@
+import sys
 import xml.etree.ElementTree as ET
 from dataclasses import dataclass, field
+from datetime import datetime
 from typing import Dict, Iterable, List, Optional, Tuple
 
+import loguru
 import requests
 
+from src import LOG_DIR
 from src.logic.dataclass import BookData
 
+log = loguru.logger
+log.remove()
+log.add(sys.stdout, level="INFO")
+log.add(f"{LOG_DIR}/application.log", rotation="1 MB", retention="10 days")
+
+log.add(
+    f"{LOG_DIR}/{datetime.now().strftime('%Y-%m-%d')}.log",
+    rotation="1 day",
+    retention="1 month",
+)
+
+
 # -----------------------
 # Dataclasses
 # -----------------------
@@ -393,15 +409,19 @@ def book_from_marc(rec: MarcRecord) -> BookData:
     )
     isbn = subfield_values(rec, "020", "a")
 
+    lang = subfield_values(rec, "041", "a")
+
     return BookData(
         ppn=ppn,
         title=title,
         signature=signature,
-        edition=first_subfield_value(rec, "250", "a"),
+        edition=first_subfield_value(rec, "250", "a") or "",
         year=year,
-        pages=first_subfield_value(rec, "300", "a"),
+        pages=first_subfield_value(rec, "300", "a") or "",
-        publisher=first_subfield_value(rec, "264", "b"),
+        publisher=first_subfield_value(rec, "264", "b") or "",
         isbn=isbn,
+        language=lang,
+        link="",
     )
 
 
@@ -418,7 +438,7 @@ class SWB:
 
         url = self.url.format(query)
 
-        print("Fetching from SWB:", url)
+        log.debug(url)
         headers = {
             "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3",
             "Accept": "application/xml",
@@ -427,7 +447,7 @@ class SWB:
         response = requests.get(url, headers=headers)
         if response.status_code != 200:
             raise Exception(f"Error fetching data from SWB: {response.status_code}")
-        # print(response.text)
+        # #print(response.text)
         data = response.content
 
         # extract top-level response
@@ -437,12 +457,22 @@ class SWB:
     def getBooks(self, query_args: Iterable[str]) -> List[BookData]:
         records: List[Record] = self.get(query_args)
         books: List[BookData] = []
-        title = query_args[1].split("=")[1]
+        # extract title from query_args if present
-        # print(len(records), "records found")
+        title = None
+        for arg in query_args:
+            if arg.startswith("pica.tit="):
+                title = arg.split("=")[1]
+                break
         for rec in records:
             book = book_from_marc(rec.recordData)
             books.append(book)
-        books = [
+        if title:
-            b for b in books if b.title and b.title.lower().startswith(title.lower())
+            books = [
-        ]
+                b
+                for b in books
+                if b.title and b.title.lower().startswith(title.lower())
+            ]
         return books
+
+    def getLinkForBook(self, book: BookData) -> str:
+        results = self.getBooks()