Browse Source

[utils] Fix inconsistent output of clean_html

`\s` in Python 2.x doesn't match unicode whitespace characters by
default
master-ytdl-org
Tithen-Firion 8 years ago
parent
commit
edd9221cd2
1 changed files with 2 additions and 2 deletions
  1. +2
    -2
      youtube_dl/utils.py

+ 2
- 2
youtube_dl/utils.py View File

@ -421,8 +421,8 @@ def clean_html(html):
# Newline vs <br />
html = html.replace('\n', ' ')
html = re.sub(r'\s*<\s*br\s*/?\s*>\s*', '\n', html)
html = re.sub(r'<\s*/\s*p\s*>\s*<\s*p[^>]*>', '\n', html)
html = re.sub(r'(?u)\s*<\s*br\s*/?\s*>\s*', '\n', html)
html = re.sub(r'(?u)<\s*/\s*p\s*>\s*<\s*p[^>]*>', '\n', html)
# Strip html tags
html = re.sub('<.*?>', '', html)
# Replace html entities


Loading…
Cancel
Save