fix lint errors

archivebox/api/v1_auth.py

@@ -2,7 +2,6 @@ __package__ = 'archivebox.api'
 
 from typing import Optional
 
-from django.contrib.auth import authenticate
 from ninja import Router, Schema
 
 from api.models import APIToken

archivebox/api/v1_cli.py

@@ -157,7 +157,7 @@ def cli_update(request, args: UpdateCommandSchema):
 
 
 @router.post("/schedule", response=CLICommandResponseSchema, summary='archivebox schedule [args] [import_path]')
-def cli_add(request, args: ScheduleCommandSchema):
+def cli_schedule(request, args: ScheduleCommandSchema):
     result = schedule(
         import_path=args.import_path,
         add=args.add,

archivebox/api/v1_core.py

@@ -1,7 +1,7 @@
 __package__ = 'archivebox.api'
 
 from uuid import UUID
-from typing import List, Optional, Union
+from typing import List, Optional
 from datetime import datetime
 
 from django.shortcuts import get_object_or_404

archivebox/core/auth.py

@@ -1,7 +1,5 @@
 __package__ = 'archivebox.core'
 
-import os
-from django.conf import settings
 
 from ..config import (
     LDAP

archivebox/core/auth_ldap.py

@@ -1,10 +1,8 @@
-from django.conf import settings
 from ..config import (
     LDAP_CREATE_SUPERUSER
 )
 
 def create_user(sender, user=None, ldap_user=None, **kwargs):
-
     if not user.id and LDAP_CREATE_SUPERUSER:
         user.is_superuser = True
 

archivebox/logging_util.py

@@ -494,12 +494,12 @@ def log_removal_started(links: List["Link"], yes: bool, delete: bool):
     if delete:
         file_counts = [link.num_outputs for link in links if Path(link.link_dir).exists()]
         print(
-            f'    {len(links)} Links will be de-listed from the main index, and their archived content folders will be deleted from disk.\n' +
+            f'    {len(links)} Links will be de-listed from the main index, and their archived content folders will be deleted from disk.\n'
             f'    ({len(file_counts)} data folders with {sum(file_counts)} archived files will be deleted!)'
         )
     else:
         print(
-            '    Matching links will be de-listed from the main index, but their archived content folders will remain in place on disk.\n' +
+            '    Matching links will be de-listed from the main index, but their archived content folders will remain in place on disk.\n'
             '    (Pass --delete if you also want to permanently delete the data folders)'
         )
 

archivebox/parsers/__init__.py

@@ -7,7 +7,6 @@ For examples of supported import formats see tests/.
 
 __package__ = 'archivebox.parsers'
 
-import re
 from io import StringIO
 
 from typing import IO, Tuple, List, Optional
@@ -28,7 +27,6 @@ from ..util import (
     htmldecode,
     download_url,
     enforce_types,
-    find_all_urls,
 )
 from ..index.schema import Link
 from ..logging_util import TimedProgress, log_source_saved

archivebox/parsers/generic_json.py

@@ -72,21 +72,13 @@ def parse_generic_json_export(json_file: IO[str], **_kwargs) -> Iterable[Link]:
 
     json_file.seek(0)
 
-    try:
-        links = json.load(json_file)
-        if type(links) != list:
-            raise Exception('JSON parser expects list of objects, maybe this is JSONL?')
-    except json.decoder.JSONDecodeError:
-        # sometimes the first line is a comment or other junk, so try without
-        json_file.seek(0)
-        first_line = json_file.readline()
-        #print('      > Trying JSON parser without first line: "', first_line.strip(), '"', sep= '')
-        links = json.load(json_file)
-        # we may fail again, which means we really don't know what to do
-
+    links = json.load(json_file)
+    if type(links) != list:
+        raise Exception('JSON parser expects list of objects, maybe this is JSONL?')
+    
     for link in links:
         if link:
-            yield jsonObjectToLink(link,json_file.name)
+            yield jsonObjectToLink(link, json_file.name)
 
 KEY = 'json'
 NAME = 'Generic JSON'

archivebox/parsers/generic_jsonl.py

@@ -3,11 +3,9 @@ __package__ = 'archivebox.parsers'
 import json
 
 from typing import IO, Iterable
-from datetime import datetime, timezone
 
 from ..index.schema import Link
 from ..util import (
-    htmldecode,
     enforce_types,
 )
 

archivebox/parsers/generic_txt.py

@@ -1,8 +1,6 @@
 __package__ = 'archivebox.parsers'
 __description__ = 'Plain Text'
 
-import re
-
 from typing import IO, Iterable
 from datetime import datetime, timezone
 from pathlib import Path

archivebox/util.py

@@ -62,12 +62,12 @@ COLOR_REGEX = re.compile(r'\[(?P<arg_1>\d+)(;(?P<arg_2>\d+)(;(?P<arg_3>\d+))?)?m
 
 # https://mathiasbynens.be/demo/url-regex
 URL_REGEX = re.compile(
-    r'(?=('                           +
-    r'http[s]?://'                    +  # start matching from allowed schemes
-    r'(?:[a-zA-Z]|[0-9]'              +  # followed by allowed alphanum characters
-    r'|[-_$@.&+!*\(\),]'              +  #   or allowed symbols (keep hyphen first to match literal hyphen)
-    r'|[^\u0000-\u007F])+'            +  #   or allowed unicode bytes
-    r'[^\]\[<>"\'\s]+'                +  # stop parsing at these symbols
+    r'(?=('                          
+    r'http[s]?://'                     # start matching from allowed schemes
+    r'(?:[a-zA-Z]|[0-9]'               # followed by allowed alphanum characters
+    r'|[-_$@.&+!*\(\),]'               #   or allowed symbols (keep hyphen first to match literal hyphen)
+    r'|[^\u0000-\u007F])+'             #   or allowed unicode bytes
+    r'[^\]\[<>"\'\s]+'                 # stop parsing at these symbols
     r'))',
     re.IGNORECASE | re.UNICODE,
 )

bin/lint.sh

@@ -15,7 +15,7 @@ DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && cd .. && pwd )"
 source "$DIR/.venv/bin/activate"
 
 echo "[*] Running flake8..."
-cd archivebox
+cd "$DIR/archivebox"
 flake8 . && echo "√ No errors found."
 
 echo