Extract methods for getting and generating xml

sru/almasru.py

@@ -18,7 +18,7 @@ information:
 Possible formats are documented here:
 https://developers.exlibrisgroup.com/alma/integrations/SRU/
 
-The Library of Congrass has general information on SRU:
+The Library of Congress has general information on SRU:
 http://www.loc.gov/standards/sru/
 """
 
@@ -108,14 +108,7 @@ class RecordRetriever:
         first_page = self._get_first_page(alma_query)
         num_recs = self._get_num_records(first_page)
 
-        xml_list = []
-
-        for startrecord in range(1, int(num_recs), 10):
-            sru_url = self._create_url(alma_query, startrecord)
-            sru_xml = self._response_to_xml(sru_url)
-            self._raise_error_sru(sru_xml)
-            xml_list.extend(self._extract_marc_xml(sru_xml))
-
+        xml_list = self._get_xml_list(alma_query, num_recs)
         return xml_list
 
     def _get_first_page(self, alma_query):
@@ -131,45 +124,52 @@ class RecordRetriever:
         num_recs = int(num_recs_element.text)
         return num_recs
 
-    def _create_url(self, alma_query: str, startrecord: int) -> str:
+    def _get_xml_list(self, alma_query: str, num_recs: int):
+        xml_list = []
+        for xml in self._gen_xml(alma_query, num_recs):
+            xml_list.extend(self._extract_marc_xml(xml))
+        return xml_list
 
+    def _gen_xml(self, alma_query: str, num_recs: int):
+        print(num_recs)
+        for startrecord in range(1, num_recs+1, 10):
+            print(startrecord)
+            sru_url = self._create_url(alma_query, startrecord)
+            sru_xml = self._response_to_xml(sru_url)
+            self._raise_error_sru(sru_xml)
+            yield sru_xml
+
+    def _create_url(self, alma_query: str, startrecord: int) -> str:
         self.url_query['startRecord'] = str(startrecord)
         self.url_query['maximumRecords'] = '10'
         self.url_query['query'] = alma_query
         url_query_string = parse.urlencode(self.url_query)
         sru_url = self.url_base + url_query_string
-
         return sru_url
 
     @staticmethod
     def _response_to_xml(url: str) -> Element:
-
         response = request.urlopen(url).read()
         xml = fromstring(response)
-
         return xml
 
     @staticmethod
     def _raise_error_unique(num_recs: int):
-
         if num_recs > 1:
             raise NotUnique('More than one record found while exactly one was expected.')
 
     @staticmethod
     def _raise_error_no_match(num_recs_element: Element):
-
         if (num_recs_element is not None and
                 num_recs_element.text == '0'):
             raise NoRecord('No matching records found.')
 
     @staticmethod
     def _raise_error_too_many_recs(num_recs_element: Element):
-
         if int(num_recs_element.text) > 10000:
             raise TooManyRecords('SRU searches are limited to 10.000 records.')
 
     def _raise_error_sru(self, sru_xml: Element):
-
         if sru_xml.find("srw:diagnostics", self.namespaces):
             xpath = "srw:diagnostics/diag:diagnostic/diag:message"
             sru_message = sru_xml.find(xpath, self.namespaces).text