add type checking, error handling, fix search issue. Closes #3 Closes #4 Fixes #3 Fixes #4

src/logic/webrequest.py

@@ -4,7 +4,7 @@ from bs4 import BeautifulSoup
 
 # import sleep_and_retry decorator to retry requests
 from ratelimit import limits, sleep_and_retry
-
+from typing import Union, Any
 from src.logic.dataclass import BookData
 
 from src.transformers import ARRAYData, BibTeXData, COinSData, RDSData, RISData
@@ -61,14 +61,14 @@ class WebRequest:
         logger.info("Using any book")
         return self
 
-    def set_apparat(self, apparat):
+    def set_apparat(self, apparat: int):
         self.apparat = apparat
         if int(self.apparat) < 10:
             self.apparat = f"0{self.apparat}"
         logger.info(f"Set apparat to {self.apparat}")
         return self
 
-    def get_ppn(self, signature):
+    def get_ppn(self, signature: str):
         self.signature = signature
         if "+" in signature:
             signature = signature.replace("+", "%2B")
@@ -79,15 +79,15 @@ class WebRequest:
 
     @sleep_and_retry
     @limits(calls=RATE_LIMIT, period=RATE_PERIOD)
-    def search_book(self, searchterm: str):
+    def search_book(self, searchterm: str) -> str:
         response = requests.get(PPN_URL.format(searchterm), timeout=self.timeout)
         return response.text
 
-    def get_book_links(self, searchterm: str):
-        response = self.search_book(searchterm)
+    def get_book_links(self, searchterm: str) -> list[str]:
+        response: str = self.search_book(searchterm)  # type:ignore
         soup = BeautifulSoup(response, "html.parser")
         links = soup.find_all("a", class_="title getFull")
-        res = []
+        res: list[str] = []
         for link in links:
             res.append(BASE + link["href"])
         return res
@@ -102,10 +102,11 @@ class WebRequest:
             logger.error(f"Request failed: {e}")
             return None
 
-    def get_data(self):
+    def get_data(self) -> Union[list[str], None]:
         links = self.get_book_links(self.ppn)
+        logger.debug(f"Links: {links}")
         for link in links:
-            result = self.search(link)
+            result: str = self.search(link)  # type:ignore
             # in result search for class col-xs-12 rds-dl RDS_LOCATION
             # if found, return text of href
             soup = BeautifulSoup(result, "html.parser")
@@ -117,7 +118,7 @@ class WebRequest:
                     ).text.strip()
                     if self.use_any:
                         pre_tag = soup.find_all("pre")
-                        return_data = []
+                        return_data: list[str] = []
                         if pre_tag:
                             for tag in pre_tag:
                                 data = tag.text.strip()
@@ -126,7 +127,7 @@ class WebRequest:
                         else:
                             logger.error("No <pre> tag found")
                             raise ValueError("No <pre> tag found")
-                    if f"Semesterapparat-{self.apparat}" in item_location:
+                    elif f"Semesterapparat-{self.apparat}" in item_location:
                         pre_tag = soup.find_all("pre")
                         return_data = []
                         if pre_tag:
@@ -137,6 +138,13 @@ class WebRequest:
                         else:
                             logger.error("No <pre> tag found")
                             return return_data
+                    else:
+                        logger.error(
+                            f"Signature {self.signature} not found in {item_location}"
+                        )
+                        return_data = []
+
+                        return return_data
 
     def get_data_elsa(self):
         links = self.get_book_links(self.ppn)
@@ -184,7 +192,7 @@ class BibTextTransformer:
         self.signature = signature
         return self
 
-    def get_data(self, data: list):
+    def get_data(self, data: Union[list[str]] = None) -> "BibTextTransformer":
         RIS_IDENT = "TY  -"
         ARRAY_IDENT = "[kid]"
         COinS_IDENT = "ctx_ver"
@@ -217,7 +225,7 @@ class BibTextTransformer:
                     self.data = line
         return self
 
-    def return_data(self, option=None) -> BookData:
+    def return_data(self, option: Any = None) -> Union[BookData, None]:
         """Return Data to caller.
 
         Args:
@@ -239,7 +247,7 @@ class BibTextTransformer:
                 return RISData().transform(self.data)
             case "RDS":
                 return RDSData().transform(self.data).return_data(option)
-            case None:
+            case _:
                 return None
 
         # if self.mode == "ARRAY":
@@ -256,7 +264,7 @@ class BibTextTransformer:
 
 def cover(isbn):
     test_url = f"https://www.buchhandel.de/cover/{isbn}/{isbn}-cover-m.jpg"
-    # print(test_url)
+    # logger.debug(test_url)
     data = requests.get(test_url, stream=True)
     return data.content
 
@@ -266,8 +274,8 @@ def get_content(soup, css_class):
 
 
 if __name__ == "__main__":
-    # print("main")
+    # logger.debug("main")
     link = "CU 8500 K64"
     data = WebRequest(71).get_ppn(link).get_data()
     bib = BibTextTransformer("ARRAY").get_data().return_data()
-    print(bib)
+    logger.debug(bib)

src/logic/wordparser.py

@@ -67,7 +67,7 @@ class Book:
                 self.location = value.split(",")[0] if "," in value else value
                 self.publisher = value.split(",")[1] if "," in value else ""
             elif key == "Standnummer":
-                self.signature = value
+                self.signature = value.strip()
             elif key == "Interne Vermerke":
                 self.internal_notes = value
 
@@ -212,7 +212,7 @@ def elsa_word_to_csv(path):
     data = [
         row for row in df.itertuples(index=False, name=None) if row != tuples[doctype]
     ]
-    # print(data)
+    # logger.debug(data)
     return tuple_to_dict(data, doctype), doctype