[pre-commit.ci] pre-commit autoupdate

.pre-commit-config.yaml

@@ -7,18 +7,18 @@ repos:
       - id: end-of-file-fixer
       - id: trailing-whitespace
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.15.14
+    rev: v0.16.5
     hooks:
       - id: ruff
         args: [--fix, --show-fixes]
       - id: ruff-format
   - repo: https://github.com/python-jsonschema/check-jsonschema
-    rev: 0.37.2
+    rev: 0.38.0
     hooks:
       - id: check-github-workflows
       - id: check-github-actions
   - repo: https://github.com/rbubley/mirrors-prettier # Update mirror as official mirror is deprecated
-    rev: v3.8.3
+    rev: v3.9.6
     hooks:
       - id: prettier
         args: [--write] # edit files in-place

scripts/collate.py

@@ -3,8 +3,9 @@
 This script is placed here for future reference in case another collation is needed.
 """
 
+from dataclasses import asdict, dataclass, field
+
 import pandas as pd
-from dataclasses import dataclass, asdict, field
 import yaml
 
 # Obtaining the data

scripts/discord_integration.py

@@ -1,8 +1,9 @@
-from loguru import logger
 import argparse
-import requests
 from copy import deepcopy
 
+import requests
+from loguru import logger
+
 # Discord char limits https://www.pythondiscord.com/pages/guides/python-guides/discord-embed-limits/
 CHAR_LIMITS = {
     "embed_title": 256,

scripts/get_og_previews.py

@@ -3,11 +3,11 @@
 from pathlib import Path
 from urllib.request import Request, urlopen
 
+import httpx
+import validators
 import yaml
 from bs4 import BeautifulSoup
 from loguru import logger
-import validators
-import httpx
 from PIL import Image, UnidentifiedImageError
 
 RESOURCES_FILE = Path("data") / "resources.yml"

scripts/onboarding.py

@@ -9,16 +9,15 @@
 changes you need to before running.
 """
 
-import requests
-import yaml
-from loguru import logger
 import re
-from urllib.parse import urlparse
-from typing import List
 from datetime import datetime
-import pytz
 from pathlib import Path
+from urllib.parse import urlparse
 
+import pytz
+import requests
+import yaml
+from loguru import logger
 
 RESOURCE_ISSUE_PATTERN = r"""###\sResource\stitle\s*
 (?P<title>.+?)\s*
@@ -52,7 +51,7 @@ def __str__(self):
         return f"Issue {self.issue_number}: {self.issue_title} by {self.author} - {self.issue_url}"
 
     def __repr__(self):
-        return f"<GithubIssue issue_number={self.issue_number}, issue_title={repr(self.issue_title)}, author={repr(self.author)}, issue_url={repr(self.issue_url)}>"
+        return f"<GithubIssue issue_number={self.issue_number}, issue_title={self.issue_title!r}, author={self.author!r}, issue_url={self.issue_url!r}>"
 
 
 class InvalidResourceIssueBody(Exception):
@@ -70,7 +69,7 @@ def __init__(self, api_response):
             self.__class__ = GithubIssue
 
     def __repr__(self):
-        return f"<ResourceIssue issue_number={self.issue_number}, issue_title={repr(self.issue_title)}, author={repr(self.author)}, issue_url={repr(self.issue_url)}>"
+        return f"<ResourceIssue issue_number={self.issue_number}, issue_title={self.issue_title!r}, author={self.author!r}, issue_url={self.issue_url!r}>"
 
     def get_resource_dict(self):
         """Returns dict for resource according to data/resources.yml schema."""
@@ -98,10 +97,9 @@ def parse_body(self, issue_body):
                 raise InvalidResourceIssueBody("Resource description must be one line.")
         else:
             raise InvalidResourceIssueBody("Regex parsing of issue body failed.")
-        return
 
 
-def resource_is_duplicated(issues: List[ResourceIssue]):
+def resource_is_duplicated(issues: list[ResourceIssue]):
     """
     Checks if the resource already exists in the database.
 
@@ -158,7 +156,7 @@ def get_tl_domain(url):
     return tl_domain
 
 
-def get_pr_message(issues: List[ResourceIssue]):
+def get_pr_message(issues: list[ResourceIssue]):
     """
     Auto generates the message for the pull request.
     """
@@ -181,7 +179,7 @@ def get_pr_message(issues: List[ResourceIssue]):
     return message
 
 
-def get_all_contributors_message(issues: List[ResourceIssue]):
+def get_all_contributors_message(issues: list[ResourceIssue]):
     # Sorted list of unique authors
     message = "@all-contributors\n"
 

scripts/resource_converter.py

@@ -2,13 +2,14 @@
 A small utility CLI app to convert Climate Town Knowledge Hub resources between YAML and CSV.
 """
 
-import yaml
-import pandas as pd
-from pathlib import Path
+import argparse
 import json
-import jsonschema
 from copy import deepcopy
-import argparse
+from pathlib import Path
+
+import jsonschema
+import pandas as pd
+import yaml
 
 CURRENT_FOLDER = Path(__file__).parent.absolute()
 ENCODING = "utf-8"
@@ -66,7 +67,6 @@ def to_yaml(self, path):
             yaml.dump(
                 self._data, f, sort_keys=True, width=float("inf"), allow_unicode=True
             )
-        return
 
     def __dict__(self):
         return deepcopy(self._data)

scripts/youtube.py

@@ -3,21 +3,20 @@
 """
 
 import argparse
-import os
-import yaml
+import asyncio
+import dataclasses
+import datetime as dt
 import json
+import os
+from dataclasses import dataclass
 from pathlib import Path
-from typing import List
-import datetime as dt
-import aiohttp
-import asyncio
 
-from loguru import logger
-from tqdm import tqdm
+import aiohttp
+import yaml
 from dotenv import load_dotenv
 from googleapiclient.discovery import build
-from dataclasses import dataclass
-import dataclasses
+from loguru import logger
+from tqdm import tqdm
 
 YOUTUBE_CHANNEL_IDS = Path("data") / "youtube_channel_ids.yml"
 VIDEO_DATA = Path("data") / "video_data.json"
@@ -64,15 +63,14 @@ def default(self, o):
 
 async def is_youtube_short(video_id: str) -> bool:
     url = f"https://www.youtube.com/shorts/{video_id}"
-    async with aiohttp.ClientSession() as session:
-        async with session.head(url) as response:
-            is_short = True if response.status == 200 else False
-            logger.info(f"Checking if {video_id} is a short: {is_short}")
-            return is_short
+    async with aiohttp.ClientSession() as session, session.head(url) as response:
+        is_short = True if response.status == 200 else False
+        logger.info(f"Checking if {video_id} is a short: {is_short}")
+        return is_short
 
 
-async def get_videos_from_channels(channel_ids: List[str], youtube: build):
-    videos: List[YoutubeVideo] = []
+async def get_videos_from_channels(channel_ids: list[str], youtube: build):
+    videos: list[YoutubeVideo] = []
 
     pbar = tqdm(channel_ids, desc="Getting videos from channels")
     for channel_id in channel_ids:
@@ -123,11 +121,11 @@ def get_videos_from_channel(channel_id: str, service: build):
     return response
 
 
-def save_channel_data(channel_ids: List[str], youtube: build):
+def save_channel_data(channel_ids: list[str], youtube: build):
     """
     Uses YouTube API to find the channels, and record data in a JSON file.
     """
-    channels: List[YoutubeChannel] = []
+    channels: list[YoutubeChannel] = []
     pbar = tqdm(channel_ids, desc="Getting videos from channels")
     for channel_id in pbar:
         request = youtube.channels().list(part="snippet,statistics", id=channel_id)
@@ -156,10 +154,9 @@ def save_channel_data(channel_ids: List[str], youtube: build):
         json.dump(channels, f, indent=4, cls=EnhancedJSONEncoder)
 
     logger.success(f"Saved video data to {VIDEO_DATA}")
-    return
 
 
-async def save_video_data(channel_ids: List[str], youtube: build):
+async def save_video_data(channel_ids: list[str], youtube: build):
     """
     Uses the API to find the videos from the channels, and records the data in a JSON file.
     """
@@ -177,7 +174,6 @@ async def save_video_data(channel_ids: List[str], youtube: build):
         json.dump(videos, f, indent=4, cls=EnhancedJSONEncoder)
 
     logger.success(f"Saved video data to {VIDEO_DATA}")
-    return
 
 
 async def main():
@@ -214,8 +210,6 @@ async def main():
     await save_video_data(channel_ids, youtube)
     save_channel_data(channel_ids, youtube)
 
-    return
-
 
 if __name__ == "__main__":
     asyncio.run(main())