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

readabilite: comment the clean_html function

Browse Source
This commit is contained in:
pictuga
2017-03-24 21:50:01 -10:00
parent 67889a1d14
commit 91da0f36dc
1 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
morss/readabilite.py
View File

@@ -112,6 +112,7 @@ def clean_html(root):
# Step 1. Do we keep the node? # Step 1. Do we keep the node?
if item.tag in tags_junk: if item.tag in tags_junk:
# remove shitty tags
item.getparent().remove(item) item.getparent().remove(item)
continue continue
@@ -119,15 +120,18 @@ def clean_html(root):
and len(list(item.iterchildren())) <= 1 \ and len(list(item.iterchildren())) <= 1 \
and not (item.text or '').strip() \ and not (item.text or '').strip() \
and not (item.tail or '').strip(): and not (item.tail or '').strip():
# remove div with only one item inside
item.drop_tag() item.drop_tag()
continue continue
class_id = item.get('class', '') + item.get('id', '') class_id = item.get('class', '') + item.get('id', '')
if regex_bad.match(class_id) is not None: if regex_bad.match(class_id) is not None:
# remove shitty class/id
item.getparent().remove(item) item.getparent().remove(item)
continue continue
if isinstance(item, lxml.html.HtmlComment): if isinstance(item, lxml.html.HtmlComment):
# remove comments
item.getparent().remove(item) item.getparent().remove(item)
continue continue