abstarct parent class for parent books

travelogues_extraction/dataextractors/abstract.py

 from abc import ABC, abstractmethod
+import asyncio
 from dataclasses import dataclass
 import re as regex
 import typing
 
+import httpcore
 import httpx
 from pandas import DataFrame
 
@@ -126,6 +128,7 @@ class AbstractMultifield(AbstractDataExtractor):
 class AbstractParentAsSecondCast(AbstractDataExtractor):
 
     column: str
+    sleep: float
 
     @classmethod
     def get_columns_names_I_work_on(cls) -> list:
@@ -137,6 +140,7 @@ class AbstractParentAsSecondCast(AbstractDataExtractor):
         super().__init__(*args, **kwargs)
         self.parend_titles = {}
         self.log = []
+        self.sleep = 0.01
 
     @abstractmethod
     async def _write(self, record: 'RecordRetriever.Record') -> typing.Optional[str]:
@@ -167,6 +171,32 @@ class AbstractParentAsSecondCast(AbstractDataExtractor):
 
             # else: get the data
 
+            try:
+                await asyncio.sleep(self.sleep)
+                parent_response = await session.get(
+                    url='https://obv-at-oenb.alma.exlibrisgroup.com/view/sru/43ACC_ONB', params={
+                        'startRecord': 1,
+                        'maximumRecords': 1,
+                        'query': f'alma.local_control_field_009={ac_parent}',
+                        'version': '1.2',
+                        'operation': 'searchRetrieve',
+                        'recordSchema': 'marcxml',
+                    }, timeout=60
+                )
+
+            except httpx.ConnectTimeout as timeout:
+                self.log.append({
+                    'error': 'time_out',
+                    'message': str(timeout),
+                    'ac_child': record.ac_number,
+                    'ac_parent': ac_parent,
+                })
+                return
+
+            except Exception as error:
+                self.sleep *= 1.3
+                try:
+                    await asyncio.sleep(self.sleep)
                     parent_response = await session.get(
                         url='https://obv-at-oenb.alma.exlibrisgroup.com/view/sru/43ACC_ONB', params={
                             'startRecord': 1,
@@ -175,16 +205,37 @@ class AbstractParentAsSecondCast(AbstractDataExtractor):
                             'version': '1.2',
                             'operation': 'searchRetrieve',
                             'recordSchema': 'marcxml',
-                }, timeout=5
+                        }, timeout=60
                     )
-            if parent_response.status_code != '200':
+
+                except httpx.ConnectTimeout as timeout:
+                    self.log.append({
+                        'error': 'time_out',
+                        'message': str(timeout),
+                        'ac_child': record.ac_number,
+                        'ac_parent': ac_parent,
+                    })
+                    return
+
+                except Exception as error:
+                    self.sleep *= 1.3
+                    self.log.append({
+                        'error': 'time_out',
+                        'message': str(error),
+                        'ac_child': record.ac_number,
+                        'ac_parent': ac_parent,
+                    })
+                    return
+
+            if parent_response.status_code != 200:
                 self.log.append({
                     'status_code': parent_response.status_code,
-                    'url': parent_response.url,
+                    'url': parent_response.url.full_path,
                     'message': parent_response.text,
                     'ac_child': record.ac_number,
                     'ac_parent': ac_parent,
                 })
+                return
 
             try:
                 xml = lxmletree.fromstring(parent_response.content)

travelogues_extraction/dataextractors/dataextractors/übergeordnet.py

@@ -11,6 +11,9 @@ from travelogues_extraction.dataextractors.abstract import AbstractParentAsSecon
 
 class Werktitel(AbstractParentAsSecondCast):
 
+    def __init__(self, *args, **kwargs):
+        AbstractParentAsSecondCast.__init__(self, *args, **kwargs)
+
     column: str = 'Werktitel'
 
     log: List[Dict[str, Any]]
@@ -69,6 +72,9 @@ class Werktitel(AbstractParentAsSecondCast):
 
 class Schlagworte(AbstractParentAsSecondCast):
 
+    def __init__(self, *args, **kwargs):
+        AbstractParentAsSecondCast.__init__(self, *args, **kwargs)
+
     column: str = 'Schlagworte'
     join_string = AbstractXpathJoinDirectlyToColumn.join_string  # to lazy for multi inheritance
     parent_ac_xpath = lxmletree.XPath(