indymedia
/
epicyon
mirror of https://gitlab.com/bashrc2/epicyon
7
4
Fork 1
Code Issues 14 Releases Wiki Activity

Remove web link concatenations

main
bashrc 2026-02-13 22:04:40 +00:00
parent a9bbb6fb87
commit e6976bbccc
1 changed files with 20 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
content.py
View File

@ -798,6 +798,25 @@ def add_web_links(content: str) -> str:
return content return content
def _web_link_concatenations(html_text: str) -> str:
"""If any web links are concatenated with other words then undo them
"""
if 'https://' not in html_text:
return html_text
words = html_text.split(' ')
new_html_text = ''
for wrd in words:
if 'https://' not in wrd:
new_html_text += wrd + ' '
continue
if wrd.startswith('https://'):
new_html_text += wrd + ' '
continue
new_html_text += wrd.split('https://')[0] + ' '
new_html_text += 'https://' + wrd.split('https://')[1] + ' '
return new_html_text.strip()
def safe_web_text(arbitrary_html: str) -> str: def safe_web_text(arbitrary_html: str) -> str:
"""Turns arbitrary html into something safe. """Turns arbitrary html into something safe.
So if the arbitrary html contains attack scripts those will be removed So if the arbitrary html contains attack scripts those will be removed
@ -810,6 +829,7 @@ def safe_web_text(arbitrary_html: str) -> str:
remove_chars = ('Œ', 'â€', 'ğŸ', '<EFBFBD>', ']]', '__') remove_chars = ('Œ', 'â€', 'ğŸ', '<EFBFBD>', ']]', '__')
for remchar in remove_chars: for remchar in remove_chars:
safe_text = safe_text.replace(remchar, '') safe_text = safe_text.replace(remchar, '')
safe_text = _web_link_concatenations(safe_text)
# recreate any url links safely # recreate any url links safely
return add_web_links(safe_text) return add_web_links(safe_text)