TheLovinator/wutheringwaves
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Keep newlines in Atom feed

Browse Source
This commit is contained in:
Joakim Hellsén
2025-05-10 16:55:53 +02:00
parent f6f47bb9a2
commit 7035f3e72e
3 changed files with 7826 additions and 306 deletions

7340
articles_all.xml

File diff suppressed because one or more lines are too long

782
articles_latest.xml

File diff suppressed because one or more lines are too long

10
scrape.py

@ -294,8 +294,12 @@ def strip_unsafe_tags(content: str) -> str:
str: The cleaned HTML content.
"""
sanitizer = Sanitizer()
return sanitizer.sanitize(content) # pyright: ignore[reportUnknownVariableType, reportUnknownMemberType]
sanitizer = Sanitizer({
"tags": {"a", "br", "b", "strong", "i", "em", "code", "s", "strike", "del", "u"},
"empty": {"a", "br"},
"separate": {"br"},
})
return sanitizer.sanitize(content.replace("\n", "<br>")).replace("<br>", "\n") # pyright: ignore[reportUnknownVariableType, reportUnknownMemberType]
def generate_atom_feed(articles: list[dict[Any, Any]], file_name: str) -> str:
@ -355,7 +359,7 @@ def generate_atom_feed(articles: list[dict[Any, Any]], file_name: str) -> str:
<id>{entry_id}</id>
<title>{escape(article_title)}</title>
<link href="{article_url}" rel="alternate" type="text/html"/>
<content type="html">{escape(article_content)}</content>
<content type="html">{escape(article_content.strip())}</content>
{published}
<updated>{updated}</updated>
{category}