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

Unescape before removing html

main
Bob Mottram 2023-06-28 12:01:03 +01:00
parent ec3dda3ad1
commit 74533468ea
1 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
newswire.py
View File

@ -778,8 +778,8 @@ def _xml2str_to_dict(base_dir: str, domain: str, xml_str: str,
description = ''
if '<description>' in rss_item and '</description>' in rss_item:
description = rss_item.split('<description>')[1]
description = remove_html(description.split('</description>')[0])
description = unescaped_text(description)
description = unescaped_text(description.split('</description>')[0])
description = remove_html(description)
else:
if '<media:description>' in rss_item and \
'</media:description>' in rss_item:
@ -888,8 +888,8 @@ def _xml1str_to_dict(base_dir: str, domain: str, xml_str: str,
description = ''
if '<description>' in rss_item and '</description>' in rss_item:
description = rss_item.split('<description>')[1]
description = remove_html(description.split('</description>')[0])
description = unescaped_text(description)
description = unescaped_text(description.split('</description>')[0])
description = remove_html(description)
else:
if '<media:description>' in rss_item and \
'</media:description>' in rss_item:
@ -986,13 +986,13 @@ def _atom_feed_to_dict(base_dir: str, domain: str, xml_str: str,
description = ''
if '<summary>' in atom_item and '</summary>' in atom_item:
description = atom_item.split('<summary>')[1]
description = remove_html(description.split('</summary>')[0])
description = unescaped_text(description)
description = unescaped_text(description.split('</summary>')[0])
description = remove_html(description)
elif '<content' in atom_item and '</content>' in atom_item:
description = atom_item.split('<content', 1)[1]
description = description.split('>', 1)[1]
description = remove_html(description.split('</content>')[0])
description = unescaped_text(description)
description = unescaped_text(description.split('</content>')[0])
description = remove_html(description)
else:
if '<media:description>' in atom_item and \
'</media:description>' in atom_item: