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

readabilite: loosen the slayer 

Previous impl. lead to too many empty results
master
pictuga 2020-04-05 20:47:30 +02:00
parent 6cf32af6c0
commit e136b0feb2
1 changed files with 12 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
morss/readabilite.py
View File

@ -63,7 +63,7 @@ regex_good = re.compile('|'.join(class_good), re.I)
tags_junk = ['script', 'head', 'iframe', 'object', 'noscript', tags_junk = ['script', 'head', 'iframe', 'object', 'noscript',
'param', 'embed', 'layer', 'applet', 'style', 'form', 'input', 'textarea', 'param', 'embed', 'layer', 'applet', 'style', 'form', 'input', 'textarea',
'button', 'footer'] 'button', 'footer', 'link', 'meta']
tags_bad = tags_junk + ['a', 'aside'] tags_bad = tags_junk + ['a', 'aside']
@ -94,11 +94,18 @@ def score_node(node):
class_id = node.get('class', '') + node.get('id', '') class_id = node.get('class', '') + node.get('id', '')
if (isinstance(node, lxml.html.HtmlComment) if (isinstance(node, lxml.html.HtmlComment)
or isinstance(node, lxml.html.HtmlProcessingInstruction) or isinstance(node, lxml.html.HtmlProcessingInstruction)):
or node.tag in tags_bad
or regex_bad.search(class_id)):
return 0 return 0
if node.tag in tags_junk:
score += -1 # actuall -2 as tags_junk is included tags_bad
if node.tag in tags_bad:
score += -1
if regex_bad.search(class_id):
score += -1
if node.tag in tags_good: if node.tag in tags_good:
score += 4 score += 4
@ -126,7 +133,7 @@ def score_all(node, grades=None):
score = score_node(child) score = score_node(child)
child.attrib['seen'] = 'yes, ' + str(int(score)) child.attrib['seen'] = 'yes, ' + str(int(score))
if score > 0: if score > 0 or not len(grades):
spread_score(child, score, grades) spread_score(child, score, grades)
score_all(child, grades) score_all(child, grades)