lordwelch/comictagger
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Make cleanup_html produce text that is more compliant with markdown

Browse Source
This commit is contained in:
Timmy Welch 2024-03-12 18:20:12 -07:00
parent e46656323c
commit c0db1e52ae
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
comictalker/talker_utils.py
View File

@ -47,9 +47,10 @@ def cleanup_html(string: str | None, remove_html_tables: bool = False) -> str:
# put in our own
string = re.sub(r"<br>|</li>", "\n", string, flags=re.IGNORECASE)
string = re.sub(r"<li>", "* ", string, flags=re.IGNORECASE)
string = re.sub(r"</p>", "\n\n", string, flags=re.IGNORECASE)
string = re.sub(r"<h([1-6])>", "*", string, flags=re.IGNORECASE)
string = re.sub(r"</h[1-6]>", "*\n", string, flags=re.IGNORECASE)
string = re.sub(r"<h([1-6])>", lambda m: '#'*int(m.group(1))+' ', string, flags=re.IGNORECASE)
string = re.sub(r"</h[1-6]>", "\n", string, flags=re.IGNORECASE)
# remove the tables
p = re.compile(r"<table[^<]*?>.*?</table>")