add flake8

.flake8

@@ -0,0 +1,6 @@
+[flake8]
+ignore = D100,D101,D102,D103,D104,D105,D202,D203,D205,D400,E131,E241,E252,E266,E272,E701,E731,W293,W503,W291,W391
+select = F,E9,W
+max-line-length = 130
+max-complexity = 10
+exclude = migrations,tests,node_modules,vendor,venv,.venv,.venv2,.docker-venv

archivebox/.flake8

@@ -1,4 +1,6 @@
 [flake8]
-ignore = D100,D101,D102,D103,D104,D105,D202,D203,D205,D400,E127,E131,E241,E252,E266,E272,E701,E731,W293,W503
+ignore = D100,D101,D102,D103,D104,D105,D202,D203,D205,D400,E131,E241,E252,E266,E272,E701,E731,W293,W503,W291,W391
-select = F,E9
+select = F,E9,W
-exclude = migrations,util_scripts,node_modules,venv
+max-line-length = 130
+max-complexity = 10
+exclude = migrations,tests,node_modules,vendor,static,venv,.venv,.venv2,.docker-venv

archivebox/__main__.py

@@ -6,5 +6,6 @@ import sys
 
 from .cli import main
 
+
 if __name__ == '__main__':
     main(args=sys.argv[1:], stdin=sys.stdin)

archivebox/config/__init__.py

@@ -279,6 +279,8 @@ def load_config_val(key: str,
                     config: Optional[ConfigDict]=None,
                     env_vars: Optional[os._Environ]=None,
                     config_file_vars: Optional[Dict[str, str]]=None) -> ConfigValue:
+    """parse bool, int, and str key=value pairs from env"""
+
 
     config_keys_to_check = (key, *(aliases or ()))
     for key in config_keys_to_check:
@@ -777,7 +779,7 @@ def check_dependencies(config: ConfigDict=CONFIG, show_help: bool=True) -> None:
         stderr()
         stderr(f'[!] Warning: TIMEOUT is set too low! (currently set to TIMEOUT={config["TIMEOUT"]} seconds)', color='red')
         stderr('    You must allow *at least* 5 seconds for indexing and archive methods to run succesfully.')
-        stderr('    (Setting it to somewhere between 30 and 300 seconds is recommended)')
+        stderr('    (Setting it to somewhere between 30 and 3000 seconds is recommended)')
         stderr()
         stderr('    If you want to make ArchiveBox run faster, disable specific archive methods instead:')
         stderr('        https://github.com/pirate/ArchiveBox/wiki/Configuration#archive-method-toggles')

archivebox/core/models.py

@@ -24,7 +24,6 @@ class Snapshot(models.Model):
 
     keys = ('url', 'timestamp', 'title', 'tags', 'updated')
 
-
     def __repr__(self) -> str:
         title = self.title or '-'
         return f'[{self.timestamp}] {self.url[:64]} ({title[:64]})'

archivebox/index/schema.py

@@ -98,6 +98,7 @@ class Link:
     updated: Optional[datetime] = None
     schema: str = 'Link'
 
+
     def __str__(self) -> str:
         return f'[{self.timestamp}] {self.base_url} "{self.title}"'
 

archivebox/main.py

@@ -641,8 +641,8 @@ def update(resume: Optional[float]=None,
            out_dir: str=OUTPUT_DIR) -> List[Link]:
     """Import any new links from subscriptions and retry any previously failed/skipped links"""
 
-    check_dependencies()
     check_data_folder(out_dir=out_dir)
+    check_dependencies()
 
     # Step 1: Load list of links from the existing index
     #         merge in and dedupe new links from import_path
@@ -990,7 +990,7 @@ def schedule(add: bool=False,
         if total_runs > 60 and not quiet:
             stderr()
             stderr('{lightyellow}[!] With the current cron config, ArchiveBox is estimated to run >{} times per year.{reset}'.format(total_runs, **ANSI))
-            stderr(f'    Congrats on being an enthusiastic internet archiver! 👌')
+            stderr('    Congrats on being an enthusiastic internet archiver! 👌')
             stderr()
             stderr('    Make sure you have enough storage space available to hold all the data.')
             stderr('    Using a compressed/deduped filesystem like ZFS is recommended if you plan on archiving a lot.')