implement rate limit and retry to prevent ratelimits

src/logic/webrequest.py

@@ -27,19 +27,25 @@ HEADERS = {
             (KHTML, like Gecko) Chrome/44.0.2403.157 Safari/537.36",
     "Accept-Language": "en-US, en;q=0.5",
 }
-
+RATE_LIMIT = 20
+RATE_PERIOD = 30
 
 class WebRequest:
-    def __init__(self, appnr) -> None:
+    def __init__(self) -> None:
         """Request data from the web, and format it depending on the mode."""
-        self.apparat = appnr
-        if int(self.apparat) < 10:
-            self.apparat = f"0{self.apparat}"
+        self.apparat = None
+        
         self.signature = None
         self.ppn = None
         self.data = None
         self.timeout = 5
         logger.log_info("Initialized WebRequest")
+    
+    def set_apparat(self, apparat):
+        self.apparat = apparat
+        if int(self.apparat) < 10:
+            self.apparat = f"0{self.apparat}"
+        return self
 
     def get_ppn(self, signature):
         self.signature = signature
@@ -49,7 +55,8 @@ class WebRequest:
             signature = signature.split("/")[-1]
         self.ppn = signature
         return self
-
+    @sleep_and_retry
+    @limits(calls=RATE_LIMIT, period=RATE_PERIOD)
     def search_book(self, searchterm: str):
         response = requests.get(PPN_URL.format(searchterm), timeout=self.timeout)
         return response.text
@@ -62,16 +69,17 @@ class WebRequest:
         for link in links:
             res.append(BASE + link["href"])
         return res
-
+    @sleep_and_retry
+    @limits(calls=RATE_LIMIT, period=RATE_PERIOD)
     def search(self, link: str):
-        response = requests.get(link, timeout=self.timeout)
-        return response.text
-
-    def get_data(
-        self
-    ):
+        try:
+            response = requests.get(link, timeout=self.timeout)
+            return response.text
+        except requests.exceptions.RequestException as e:
+            logger.log_error(f"Request failed: {e}")
+            return None
+    def get_data(self):
         links = self.get_book_links(self.ppn)
-        print(links)
         for link in links:
             result = self.search(link)
             # in result search for class col-xs-12 rds-dl RDS_LOCATION
@@ -95,6 +103,27 @@ class WebRequest:
                             logger.log_error("No <pre> tag found")
                             return return_data
 
+    def get_data_elsa(self):
+        links = self.get_book_links(self.ppn)
+        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")
+            locations = soup.find_all("div", class_="col-xs-12 rds-dl RDS_LOCATION")
+            if locations:
+                for location in locations:
+                    pre_tag = soup.find_all("pre")
+                    return_data = []
+                    if pre_tag:
+                        for tag in pre_tag:
+                            data = tag.text.strip()
+                            return_data.append(data)
+                        return return_data
+                    else:
+                        logger.log_error("No <pre> tag found")
+                        return return_data
+
 
 class BibTextTransformer:
     """Transforms data from the web into a BibText format.
@@ -114,7 +143,6 @@ class BibTextTransformer:
         if mode not in self.valid_modes:
             logger.log_error(f"Mode {mode} not valid")
             raise ValueError(f"Mode {mode} not valid")
-        # # print(self.field)
         self.data = None
         # self.bookdata = BookData(**self.data)