Merge branch 'main' into pr/40

.devcontainer/devcontainer.json

@@ -17,5 +17,5 @@
             ]
         }
     },
-    "postCreateCommand": "poetry install"
+    "postCreateCommand": "poetry install && poetry run pre-commit install"
 }

.pre-commit-config.yaml

@@ -0,0 +1,14 @@
+repos:
+  - repo: local
+    hooks:
+      - id: black
+        name: black
+        entry: poetry run black
+        language: system
+        types: [python]
+
+      - id: isort
+        name: isort
+        entry: poetry run isort
+        language: system
+        types: [python]

README.md

@@ -226,13 +226,16 @@ pip install poetry
 
 # Install dependencies
 poetry install
+
+# Set up pre-commit hooks to keep your code formatted
+poetry run pre-commit install
 ```
 
 Check out [Important commands](#important-commands) below for next steps.
 
 ### Developing using a GitHub Codespace
 
-This project uses a custom Development Container supported by GitHub Codespaces. Creating a new Codespace automatically takes care of installing all supported Python interpreters, the Poetry package manager, and Python dependencies for you.
+This project uses a custom Development Container supported by GitHub Codespaces. Creating a new Codespace automatically takes care of installing all supported Python interpreters, the Poetry package manager, Python dependencies, and pre-commit hooks for you.
 
 To create a new Codespace:
 1. Click on the `<> Code` dropdown on the GitHub UI.

edgar_tool/__main__.py

@@ -1,6 +1,7 @@
-from edgar_tool.cli import SecEdgarScraperCli
 import fire
 
+from edgar_tool.cli import SecEdgarScraperCli
+
 
 def main():
     fire.Fire(SecEdgarScraperCli)

edgar_tool/cli.py

@@ -1,17 +1,18 @@
 import sys
 import time
-from datetime import date, timedelta, datetime
+from datetime import date, datetime, timedelta
 from typing import List, Optional
 from warnings import warn
+
 from edgar_tool.constants import (
     SUPPORTED_OUTPUT_EXTENSIONS,
     TEXT_SEARCH_CATEGORY_FORM_GROUPINGS,
     TEXT_SEARCH_FILING_VS_MAPPING_CATEGORIES_MAPPING,
 )
+from edgar_tool.page_fetcher import NoResultsFoundError
 from edgar_tool.rss import fetch_rss_feed
 from edgar_tool.text_search import EdgarTextSearcher
 from edgar_tool.utils import parse_location_input
-from edgar_tool.page_fetcher import NoResultsFoundError
 
 
 def _validate_text_search_args(

edgar_tool/io.py

@@ -1,12 +1,10 @@
 import csv
 import json
-from typing import List, Dict, Any, Iterator
+from typing import Any, Dict, Iterator, List
 
 import jsonlines
 
-from edgar_tool.constants import (
-    SUPPORTED_OUTPUT_EXTENSIONS,
-)
+from edgar_tool.constants import SUPPORTED_OUTPUT_EXTENSIONS
 
 
 def write_results_to_file(

edgar_tool/page_fetcher.py

@@ -1,10 +1,10 @@
 import time
 import uuid
 from random import uniform
-from typing import Callable, Any, Optional
+from typing import Any, Callable, Optional
 
-from tenacity import retry, wait_fixed, stop_after_attempt
 import requests
+from tenacity import retry, stop_after_attempt, wait_fixed
 
 
 def fetch_page(

edgar_tool/rss.py

@@ -1,7 +1,7 @@
 import json
 import uuid
 from pathlib import Path
-from typing import List, Any, Dict, Iterator, Tuple
+from typing import Any, Dict, Iterator, List, Tuple
 
 import requests
 import xmltodict

edgar_tool/text_search.py

@@ -4,24 +4,23 @@
 import urllib.parse
 from datetime import date, timedelta
 from math import ceil
-from typing import List, Optional, Dict, Any, Iterator
+from typing import Any, Dict, Iterator, List, Optional
 
-
-from edgar_tool.page_fetcher import (
-    fetch_page,
-    PageCheckFailedError,
-    ResultsTableNotFoundError,
-    NoResultsFoundError,
-)
 from edgar_tool.constants import (
     TEXT_SEARCH_BASE_URL,
     TEXT_SEARCH_CATEGORY_FORM_GROUPINGS,
-    TEXT_SEARCH_SPLIT_BATCHES_NUMBER,
     TEXT_SEARCH_CSV_FIELDS_NAMES,
     TEXT_SEARCH_FORM_MAPPING,
     TEXT_SEARCH_LOCATIONS_MAPPING,
+    TEXT_SEARCH_SPLIT_BATCHES_NUMBER,
 )
 from edgar_tool.io import write_results_to_file
+from edgar_tool.page_fetcher import (
+    fetch_page,
+    PageCheckFailedError,
+    ResultsTableNotFoundError,
+    NoResultsFoundError,
+)
 from edgar_tool.utils import split_date_range_in_n, unpack_singleton_list
 
 

edgar_tool/utils.py

@@ -2,7 +2,8 @@
 
 import re
 from datetime import date
-from typing import Any, Iterator, Dict, List, Union, Optional
+from typing import Any, Dict, Iterator, List, Optional, Union
+
 from edgar_tool.constants import TEXT_SEARCH_LOCATIONS_MAPPING
 
 

pyproject.toml

@@ -27,19 +27,28 @@ keywords=["scraper", "edgar", "finance", "sec"]
 edgar-tool = "edgar_tool.__main__:main"
 
 [tool.poetry.dependencies]
-python = "^3.9"
-tenacity = "^8.2"
 fire = "^0.5"
 jsonlines = "^4.0"
+python = "^3.9"
 requests = "^2.31"
+tenacity = "^8.2"
 xmltodict = "^0.13"
 pytest = "^8.2.2"
 
 [tool.poetry.group.dev.dependencies]
-black = "^24.2.0"
-tox = "^4.16.0"
+black = "24.3.0"
+isort = "5.13.2"
+pre-commit = "^3.8.0"
 pytest = "^8.2.2"
+tox = "^4.16.0"
 
 [build-system]
 requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"
+
+[tool.isort]
+profile = "black"
+line_length = 88 # Should always match tool.black
+
+[tool.black]
+line-length = 88  # black's default