TheLovinator/wutheringwaves
1
Fork 0
mirror of https://github.com/TheLovinator1/wutheringwaves.git synced 2025-11-27 20:49:48 +01:00
Code Issues Packages Projects Releases Wiki Activity

Optimize MarkdownConverter by creating single instance at module level

Browse Source 
Co-authored-by: TheLovinator1 <4153203+TheLovinator1@users.noreply.github.com>
This commit is contained in:
copilot-swe-agent[bot]
2025-11-03 05:56:06 +00:00
parent f1924f38ad
commit 0ddb59e727
1 changed files with 7 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
scrape.py
View File

@@ -50,6 +50,12 @@ CIRCLED_NUMBERS = {
"⑩": ("10", re.compile(r"^\s*⑩\s*(.*?)\s*$", re.MULTILINE)), "⑩": ("10", re.compile(r"^\s*⑩\s*(.*?)\s*$", re.MULTILINE)),
} }
# Markdown converter instance - reuse instead of creating for each article
MARKDOWN_CONVERTER = MarkdownConverter(
heading_style="ATX",
strip=["pre", "code"],
)
async def fetch_json(url: str, client: httpx.AsyncClient) -> dict[Any, Any] | None: async def fetch_json(url: str, client: httpx.AsyncClient) -> dict[Any, Any] | None:
@@ -428,11 +434,7 @@ def generate_atom_feed(articles: list[dict[Any, Any]], file_name: str) -> str:
if not article_content: if not article_content:
article_content = article_title article_content = article_title
converter: MarkdownConverter = MarkdownConverter( article_content_converted = str(MARKDOWN_CONVERTER.convert(article_content).strip()) # type: ignore # noqa: PGH003
heading_style="ATX",
strip=["pre", "code"],
)
article_content_converted = str(converter.convert(article_content).strip()) # type: ignore # noqa: PGH003
if not article_content_converted: if not article_content_converted:
msg: str = f"Article content is empty for article ID: {article_id}" msg: str = f"Article content is empty for article ID: {article_id}"