Merge pull request 'feat: get additional data from catalogue:' (#9) from dev into main

Reviewed-on: #9

src/bibapi/catalogue.py

@@ -4,6 +4,8 @@ import regex
 import requests
 from bs4 import BeautifulSoup
 
+from .schemas.bookdata import BookData as Book
+
 URL = "https://rds.ibs-bw.de/phfreiburg/opac/RDSIndex/Search?type0%5B%5D=allfields&lookfor0%5B%5D={}&join=AND&bool0%5B%5D=AND&type0%5B%5D=au&lookfor0%5B%5D=&join=AND&bool0%5B%5D=AND&type0%5B%5D=ti&lookfor0%5B%5D=&join=AND&bool0%5B%5D=AND&type0%5B%5D=ct&lookfor0%5B%5D=&join=AND&bool0%5B%5D=AND&type0%5B%5D=isn&lookfor0%5B%5D=&join=AND&bool0%5B%5D=AND&type0%5B%5D=ta&lookfor0%5B%5D=&join=AND&bool0%5B%5D=AND&type0%5B%5D=co&lookfor0%5B%5D=&join=AND&bool0%5B%5D=AND&type0%5B%5D=py&lookfor0%5B%5D=&join=AND&bool0%5B%5D=AND&type0%5B%5D=pp&lookfor0%5B%5D=&join=AND&bool0%5B%5D=AND&type0%5B%5D=pu&lookfor0%5B%5D=&join=AND&bool0%5B%5D=AND&type0%5B%5D=si&lookfor0%5B%5D=&join=AND&bool0%5B%5D=AND&type0%5B%5D=zr&lookfor0%5B%5D=&join=AND&bool0%5B%5D=AND&type0%5B%5D=cc&lookfor0%5B%5D=&join=AND&bool0%5B%5D=AND"
 BASE = "https://rds.ibs-bw.de"
 
@@ -156,6 +158,46 @@ class Catalogue:
                             edition=edition,
                         )
 
+    def get_book_with_data(self, searchterm: str) -> Book | None:
+        book = self.get_book(searchterm)
+        if book:
+            # request data from book.link and parse for additional data
+            result = self.search(book.link)
+            soup = BeautifulSoup(result, "html.parser")
+
+            # from div col-xs-12 rds-dl RDS_SIGNATURE get signature (second div in this div)
+            signature = None
+            signature_el = soup.find("div", class_="RDS_SIGNATURE")
+            print(signature_el)
+            if signature_el:
+                signature = signature_el.find("div", class_="rds-dl-panel").get_text(
+                    strip=True
+                )
+                print(signature)
+            book.signature = signature
+            # from div col-xs-12 col-md-5 col-lg-4 rds-dl-head RDS_ISBN get isbn (second div in this div)
+            isbn = None
+            isbn_el = soup.find("div", class_="RDS_ISBN")
+            if isbn_el:
+                isbn = isbn_el.find_next_sibling(
+                    "div", class_="col-xs-12 col-md-7 col-lg-8 rds-dl-panel"
+                ).get_text(strip=True)
+            book.isbn = isbn
+            # from div col-xs-12 col-md-5 col-lg-4 rds-dl-head RDS_SCOPE get pages (second div in this div)
+            pages = None
+            pages_el = soup.find("div", class_="RDS_SCOPE")
+            if pages_el:
+                pages = pages_el.find_next_sibling(
+                    "div", class_="col-xs-12 col-md-7 col-lg-8 rds-dl-panel"
+                ).get_text(strip=True)
+                # regex match to get pages by grabbing the first number in the string
+                match = regex.search(r"(\d+)", pages)
+                if match:
+                    pages = match.group(1)
+            book.pages = pages
+            return book
+        return None
+
     def get(self, ppn: str) -> Book | None:
         # based on PPN, get title, people, edition, year, language, pages, isbn,
         link = f"https://rds.ibs-bw.de/phfreiburg/opac/RDSIndexrecord/{ppn}"