Print mtime before updating file metadata

CONFIG.md

@@ -92,9 +92,6 @@ common to all crawlers:
   load for the crawl target. (Default: `0.0`)
 - `windows_paths`: Whether PFERD should find alternative names for paths that
   are invalid on Windows. (Default: `yes` on Windows, `no` otherwise)
-- `aliases`: List of strings that are considered as an alias when invoking with
-  the `--crawler` or `-C` flag. If there is more than one crawl section with
-  the same aliases all are selected. Thereby, you can group different crawlers.
 
 Some crawlers may also require credentials for authentication. To configure how
 the crawler obtains its credentials, the `auth` option is used. It is set to the
@@ -109,7 +106,6 @@ username = foo
 password = bar
 
 [crawl:something]
-aliases = [sth, some]
 type = some-complex-crawler
 auth = auth:example
 on_conflict = no-delete

PFERD/crawl/ilias/kit_ilias_html.py

@@ -514,8 +514,11 @@ class IliasPage:
                 f"td.std:nth-child({index})"
             ).getText().strip()
             if re.search(r"\d+\.\d+.\d+ - \d+:\d+", modification_string):
+                log.explain(f"Converting {modification_string!r}")
                 modification_time = datetime.strptime(modification_string, "%d.%m.%Y - %H:%M")
                 break
+            else:
+                log.explain(f"Date has wrong format: {modification_string!r}")
 
         if modification_time is None:
             log.warn(f"Could not determine upload time for {link}")

PFERD/output_dir.py

@@ -415,6 +415,7 @@ class OutputDirectory:
 
     def _update_metadata(self, info: DownloadInfo) -> None:
         if mtime := info.heuristics.mtime:
+            log.explain(f"Setting mtime to {mtime}")
             mtimestamp = mtime.timestamp()
             os.utime(info.local_path, times=(mtimestamp, mtimestamp))
 

PFERD/pferd.py

@@ -1,5 +1,5 @@
 from pathlib import Path
-from typing import Dict, List, Optional, Set
+from typing import Dict, List, Optional
 
 from rich.markup import escape
 
@@ -43,24 +43,16 @@ class Pferd:
 
         crawl_sections = [name for name, _ in config.crawl_sections()]
 
-        crawlers_to_run = set()  # With crawl: prefix
+        crawlers_to_run = []  # With crawl: prefix
         unknown_names = []  # Without crawl: prefix
 
         for name in cli_crawlers:
             section_name = f"crawl:{name}"
             if section_name in crawl_sections:
                 log.explain(f"Crawler section named {section_name!r} exists")
-                crawlers_to_run.add(section_name)
+                crawlers_to_run.append(section_name)
-            # interprete name as alias of a crawler
+            else:
-            alias_names = self._find_crawlers_by_alias(name, config)
+                log.explain(f"There's no crawler section named {section_name!r}")
-            if alias_names:
-                crawlers_to_run.update(alias_names)
-                log.explain_topic(f"Crawler alias {name!r} found corresponding crawler sections:")
-                for alias_name in alias_names:
-                    log.explain(f"Crawler section named {alias_name!r} with alias {name!r} exists")
-
-            if not section_name in crawl_sections and not alias_names:
-                log.explain(f"There's neither a crawler section named {section_name!r} nor does a crawler with alias {name!r} exist.")
                 unknown_names.append(name)
 
         if unknown_names:
@@ -73,14 +65,6 @@ class Pferd:
 
         return crawlers_to_run
 
-    def _find_crawlers_by_alias(self, alias: str, config: Config) -> Set[str]:
-        alias_names = set()
-        for (section_name, section) in config.crawl_sections():
-            section_aliases = section.get("aliases", [])
-            if alias in section_aliases:
-                alias_names.add(section_name)
-        return alias_names
-
     def _find_crawlers_to_run(
             self,
             config: Config,