pictuga/morss
1
1
Fork 0
Code Issues Pull Requests Actions Packages Releases Activity

Use etree.tostring 'method' arg

Browse Source 
Gives appropriately formatted html code.
Some pages might otherwise be rendered as blank.
This commit is contained in:
pictuga
2020-05-13 11:44:34 +02:00
parent 7d0d416610
commit 22005065e8
3 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
morss/morss.py
View File

@@ -294,7 +294,7 @@ def ItemAfter(item, options):
for link in content.xpath('//a'):
log(link.text_content())
link.drop_tag()
item.content = lxml.etree.tostring(content)
item.content = lxml.etree.tostring(content, method='html')
if options.noref:
item.link = ''
@@ -612,7 +612,7 @@ def cgi_get(environ, start_response):
for elem in html.xpath('//'+tag):
elem.getparent().remove(elem)
output = lxml.etree.tostring(html.getroottree(), encoding='utf-8')
output = lxml.etree.tostring(html.getroottree(), encoding='utf-8', method='html')
elif options.get == 'article':
output = readabilite.get_article(req['data'], url=req['url'], encoding_in=req['encoding'], encoding_out='utf-8', debug=options.debug)