Fixing scrape/extract shenanigans wrt -I,--input-dir

minet/cli/extract/extract.py

@@ -89,6 +89,11 @@ def action(cli_args, enricher: IndexedEnricher, loading_bar):
     if not cli_args.glob:
         loading_bar.set_total(enricher.total)
 
+    if not cli_args.has_dummy_csv and cli_args.input_dir is None:
+        from minet.cli.constants import DEFAULT_CONTENT_FOLDER
+
+        cli_args.input_dir = DEFAULT_CONTENT_FOLDER
+
     items = create_fetch_like_report_iterator(cli_args, enricher)
 
     worked_on: Dict[int, FetchReportLikeItem] = {}

minet/cli/scrape/scrape.py

@@ -258,6 +258,11 @@ def writerow(row, item):
     with LoadingBar(
         "Scraping", unit="pages", total=reader.total if not cli_args.glob else None
     ) as loading_bar:
+        if not cli_args.has_dummy_csv and cli_args.input_dir is None:
+            from minet.cli.constants import DEFAULT_CONTENT_FOLDER
+
+            cli_args.input_dir = DEFAULT_CONTENT_FOLDER
+
         items = create_fetch_like_report_iterator(cli_args, reader)
 
         worked_on: Dict[int, FetchReportLikeItem] = {}

minet/cli/utils.py

@@ -26,7 +26,6 @@
 
 from minet.crawl import CrawlerState
 from minet.encodings import is_supported_encoding
-from minet.cli.constants import DEFAULT_CONTENT_FOLDER
 from minet.cli.console import console
 from minet.cli.loading_bar import LoadingBar, StatsItem
 from minet.cli.exceptions import FatalError
@@ -190,10 +189,7 @@ def create_fetch_like_report_iterator(
     cli_args: SimpleNamespace, reader: casanova.Reader
 ) -> Iterator[FetchReportLikeItem]:
     headers = reader.headers
-    input_dir = cli_args.input_dir
-
-    if input_dir is None:
-        input_dir = DEFAULT_CONTENT_FOLDER
+    input_dir = cli_args.input_dir or ""
 
     # TODO: deal with no_headers
     assert headers is not None