Mikaela/Limnoria
1
0
Fork 0
mirror of https://github.com/Mikaela/Limnoria.git synced 2024-11-26 20:59:27 +01:00
Code Issues Projects Releases Wiki Activity

utils/web: Add <br/> to the list of block elements

Browse Source 
It should always be replaced with a space.
This commit is contained in:
Valentin Lorentz 2022-09-20 07:51:46 +02:00
parent 169824a9d2
commit 35bf599856
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/utils/web.py
View File

@ -226,6 +226,8 @@ def getEncoding(s):
# From beautifulsoup (version 4.10.0, bs4/builder/__init__.py, line 391) # From beautifulsoup (version 4.10.0, bs4/builder/__init__.py, line 391)
_block_elements = set(["address", "article", "aside", "blockquote", "canvas", "dd", "div", "dl", "dt", "fieldset", "figcaption", "figure", "footer", "form", "h1", "h2", "h3", "h4", "h5", "h6", "header", "hr", "li", "main", "nav", "noscript", "ol", "output", "p", "pre", "section", "table", "tfoot", "ul", "video"]) _block_elements = set(["address", "article", "aside", "blockquote", "canvas", "dd", "div", "dl", "dt", "fieldset", "figcaption", "figure", "footer", "form", "h1", "h2", "h3", "h4", "h5", "h6", "header", "hr", "li", "main", "nav", "noscript", "ol", "output", "p", "pre", "section", "table", "tfoot", "ul", "video"])
_block_elements.update({"br"})
class HtmlToText(HTMLParser, object): class HtmlToText(HTMLParser, object):
"""Taken from some eff-bot code on c.l.p.""" """Taken from some eff-bot code on c.l.p."""
entitydefs = entitydefs.copy() entitydefs = entitydefs.copy()