Implementing ruff suggestions.

src/auto_archiver/modules/cli_feeder/__manifest__.py

@@ -3,7 +3,6 @@
     "type": ["feeder"],
     "entry_point": "cli_feeder::CLIFeeder",
     "requires_setup": False,
-    "description": "Feeds URLs to orchestrator from the command line",
     "configs": {
         "urls": {
             "default": None,

src/auto_archiver/modules/csv_feeder/__manifest__.py

@@ -1,7 +1,6 @@
 {
     "name": "CSV Feeder",
     "type": ["feeder"],
-    "requires_setup": False,
     "dependencies": {"python": ["loguru"], "bin": [""]},
     "requires_setup": True,
     "entry_point": "csv_feeder::CSVFeeder",

src/auto_archiver/modules/gsheet_feeder_db/__manifest__.py

@@ -12,7 +12,9 @@
             "default": None,
             "help": "the id of the sheet to archive (alternative to 'sheet' config)",
         },
-        "header": {"default": 1, "type": "int", "help": "index of the header row (starts at 1)", "type": "int"},
+        "header": {"default": 1,
+                   "help": "index of the header row (starts at 1)",
+                   "type": "int"},
         "service_account": {
             "default": "secrets/service_account.json",
             "help": "service account JSON file path. Learn how to create one: https://gspread.readthedocs.io/en/latest/oauth2.html",
@@ -51,19 +53,6 @@
             "help": "if True the stored files path will include 'workbook_name/worksheet_name/...'",
             "type": "bool",
         },
-        "allow_worksheets": {
-            "default": set(),
-            "help": "(CSV) only worksheets whose name is included in allow are included (overrides worksheet_block), leave empty so all are allowed",
-        },
-        "block_worksheets": {
-            "default": set(),
-            "help": "(CSV) explicitly block some worksheets from being processed",
-        },
-        "use_sheet_names_in_stored_paths": {
-            "default": True,
-            "type": "bool",
-            "help": "if True the stored files path will include 'workbook_name/worksheet_name/...'",
-        },
     },
     "description": """
     GsheetsFeederDatabase

src/auto_archiver/modules/gsheet_feeder_db/gworksheet.py

@@ -68,7 +68,7 @@ class GWorksheet:
 
         if fresh:
             return self.wks.cell(row, col_index + 1).value
-        if type(row) == int:
+        if isinstance(row, int):
             row = self.get_row(row)
 
         if col_index >= len(row):
@@ -84,7 +84,7 @@ class GWorksheet:
             if when_empty_use_default and val.strip() == "":
                 return default
             return val
-        except:
+        except Exception:
             return default
 
     def set_cell(self, row: int, col: str, val):

src/auto_archiver/modules/instagram_api_extractor/instagram_api_extractor.py

@@ -74,9 +74,9 @@ class InstagramAPIExtractor(Extractor):
         # repeats 3 times to remove nested empty values
         if not self.minimize_json_output:
             return d
-        if type(d) == list:
+        if isinstance(d, list):
             return [self.cleanup_dict(v) for v in d]
-        if type(d) != dict:
+        if not isinstance(d, dict):
             return d
         return {
             k: clean_v
@@ -220,7 +220,7 @@ class InstagramAPIExtractor(Extractor):
         post_count = 0
         while end_cursor != "":
             posts = self.call_api("v1/user/medias/chunk", {"user_id": user_id, "end_cursor": end_cursor})
-            if not len(posts) or not type(posts) == list or len(posts) != 2:
+            if not posts or not isinstance(posts, list) or len(posts) != 2:
                 break
             posts, end_cursor = posts[0], posts[1]
             logger.info(f"parsing {len(posts)} posts, next {end_cursor=}")
@@ -243,7 +243,7 @@ class InstagramAPIExtractor(Extractor):
         pbar = tqdm(desc="downloading tagged posts")
 
         tagged_count = 0
-        while next_page_id != None:
+        while next_page_id is not None:
             resp = self.call_api("v2/user/tag/medias", {"user_id": user_id, "page_id": next_page_id})
             posts = resp.get("response", {}).get("items", [])
             if not len(posts):

src/auto_archiver/modules/telegram_extractor/telegram_extractor.py

@@ -61,7 +61,7 @@ class TelegramExtractor(Extractor):
                 else:
                     duration = float(duration)
                 m_video.set("duration", duration)
-            except:
+            except Exception:
                 pass
             result.add_media(m_video)
 

src/auto_archiver/modules/twitter_api_extractor/twitter_api_extractor.py

@@ -46,7 +46,7 @@ class TwitterApiExtractor(Extractor):
                 r = requests.get(url, timeout=30)
                 logger.debug(f"Expanded url {url} to {r.url}")
                 url = r.url
-            except:
+            except Exception:
                 logger.error(f"Failed to expand url {url}")
         return url
 

src/auto_archiver/modules/wacz_extractor_enricher/__manifest__.py

@@ -14,7 +14,9 @@
             "help": "browsertrix-profile (for profile generation see https://github.com/webrecorder/browsertrix-crawler#creating-and-using-browser-profiles).",
         },
         "docker_commands": {"default": None, "help": "if a custom docker invocation is needed"},
-        "timeout": {"default": 120, "type": "int", "help": "timeout for WACZ generation in seconds", "type": "int"},
+        "timeout": {"default": 120,
+                    "help": "timeout for WACZ generation in seconds",
+                    "type": "int"},
         "extract_media": {
             "default": False,
             "type": "bool",

src/auto_archiver/modules/whisper_enricher/whisper_enricher.py

@@ -88,7 +88,7 @@ class WhisperEnricher(Enricher):
         while not all_completed and (time.time() - start_time) <= self.timeout:
             all_completed = True
             for job_id in job_results:
-                if job_results[job_id] != False:
+                if job_results[job_id] is not False:
                     continue
                 all_completed = False  # at least one not ready
                 try: