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

readabilite: some technical improvements for score 

Linear, removed misplaced debugging code
master
pictuga 2018-10-24 23:47:37 +02:00
parent 040d2cb889
commit 787d90fac0
1 changed files with 15 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
morss/readabilite.py
View File

@ -130,6 +130,9 @@ def score_all(root):
def spread_score(node, score, grades): def spread_score(node, score, grades):
" Spread the node's score to its parents, on a linear way "
delta = score / 2
for ancestor in [node,] + list(node.iterancestors()): for ancestor in [node,] + list(node.iterancestors()):
if score >= 1 or ancestor is node: if score >= 1 or ancestor is node:
try: try:
@ -137,7 +140,7 @@ def spread_score(node, score, grades):
except KeyError: except KeyError:
grades[ancestor] = score grades[ancestor] = score
score /= 2 score -= delta
else: else:
break break
@ -145,7 +148,7 @@ def spread_score(node, score, grades):
def write_score_all(root, grades): def write_score_all(root, grades):
for node in root.iter(): for node in root.iter():
node.attrib['score'] = str(int(grades[node])) node.attrib['score'] = str(int(grades.get(node, 0)))
def clean_node(node): def clean_node(node):
@ -243,15 +246,15 @@ def rank_nodes(grades):
return sorted(grades.items(), key=lambda x: x[1], reverse=True) return sorted(grades.items(), key=lambda x: x[1], reverse=True)
def get_best_node(grades, highlight=False): def get_best_node(grades):
" To pick the best (raw) node. Another function will clean it "
if len(grades) == 1:
return grades[0]
top = rank_nodes(grades) top = rank_nodes(grades)
lowest = lowest_common_ancestor(top[0][0], top[1][0], 3) lowest = lowest_common_ancestor(top[0][0], top[1][0], 3)
if highlight:
top[0][0].attrib['style'] = 'border: 2px solid blue'
top[1][0].attrib['style'] = 'border: 2px solid green'
lowest.attrib['style'] = 'outline: 2px solid red'
return lowest return lowest
@ -259,8 +262,11 @@ def get_article(data, url=None, encoding=None):
html = parse(data, encoding) html = parse(data, encoding)
br2p(html) br2p(html)
scores = score_all(html) scores = score_all(html)
best = get_best_node(scores)
if not len(scores):
return None
best = get_best_node(scores)
wc = count_words(best.text_content()) wc = count_words(best.text_content())
wca = count_words(' '.join([x.text_content() for x in best.findall('.//a')])) wca = count_words(' '.join([x.text_content() for x in best.findall('.//a')]))