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

readabilite: improve score for <p>

Browse Source 
Helps a lot with bbc, le monde. Might backfire on other websites tho...
This commit is contained in:
pictuga
2017-03-01 18:02:45 -10:00
parent a8ac2ed1ca
commit 3fc89d5359
1 changed files with 3 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
morss/readabilite.py
View File

@@ -63,6 +63,9 @@ def score_node(node):
if node.tag in ['h1', 'h2', 'article']: if node.tag in ['h1', 'h2', 'article']:
score += 8 score += 8
if node.tag in ['p']:
score += 3
class_id = node.get('class', '') + node.get('id', '') class_id = node.get('class', '') + node.get('id', '')
score += len(regex_good.findall(class_id) * 4) score += len(regex_good.findall(class_id) * 4)