custom class to request data from our webcatalogue and return dataclass books

src/logic/catalogue.py

@@ -0,0 +1,75 @@
+import requests
+from bs4 import BeautifulSoup
+from src import config
+from src.schemas import Book
+
+URL = "https://rds.ibs-bw.de/phfreiburg/opac/RDSIndex/Search?lookfor={}+&type=AllFields&limit=10&sort=py+desc%2C+title"
+BASE = "https://rds.ibs-bw.de"
+
+
+class Catalogue:
+    def __init__(self, timeout=5):
+        self.timeout = timeout
+
+    def search_book(self, searchterm: str):
+        response = requests.get(URL.format(searchterm), timeout=self.timeout)
+        return response.text
+
+    def search(self, link: str):
+        response = requests.get(link, timeout=self.timeout)
+        return response.text
+
+    def get_book_links(self, searchterm: str):
+        response = self.search_book(searchterm)
+        soup = BeautifulSoup(response, "html.parser")
+        links = soup.find_all("a", class_="title getFull")
+        res = []
+        for link in links:
+            res.append(BASE + link["href"])
+        return res
+
+    def get_book(self, searchterm: str):
+        links = self.get_book_links(searchterm)
+        for link in links:
+            result = self.search(link)
+            # in result search for class col-xs-12 rds-dl RDS_LOCATION
+            # if found, return text of href
+            soup = BeautifulSoup(result, "html.parser")
+            location = soup.find("div", class_="col-xs-12 rds-dl RDS_LOCATION")
+            if location:
+                if config.institution_name in location.text:
+                    location = config.institution_name
+                    title = (
+                        soup.find("div", class_="headline text")
+                        .text.replace("\n", "")
+                        .strip()
+                    )
+                    ppn = soup.find(
+                        "div", class_="col-xs-12 col-md-5 col-lg-4 rds-dl-head RDS_PPN"
+                    )
+                    signature = soup.find(
+                        "div", class_="col-xs-12 rds-dl RDS_SIGNATURE"
+                    )
+                    if signature:
+                        signature = (
+                            signature.find_next("div")
+                            .find_next("div")
+                            .text.replace("\n", "")
+                            .strip()
+                        )
+                    # use ppn to find the next div and extract the text
+                    if ppn:
+                        ppn = ppn.find_next("div").text.replace("\n", "").strip()
+                    else:
+                        ppn = None
+                    isbn = soup.find(
+                        "div", class_="col-xs-12 col-md-5 col-lg-4 rds-dl-head RDS_ISBN"
+                    )
+                    if isbn:
+                        isbn = isbn.find_next("div").find_next("div").text
+                    else:
+                        isbn = None
+                    return Book(
+                        title=title, ppn=ppn, signature=signature, isbn=isbn, link=link
+                    )
+        return False