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

readabilite: also use BS

master
pictuga 2020-04-05 20:46:42 +02:00
parent 568e7d7dd2
commit 6cf32af6c0
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
morss/readabilite.py
View File

@ -1,5 +1,6 @@
import lxml.etree import lxml.etree
import lxml.html import lxml.html
from bs4 import BeautifulSoup
import re import re
@ -9,7 +10,7 @@ def parse(data, encoding=None):
else: else:
parser = lxml.html.HTMLParser(remove_blank_text=True, remove_comments=True) parser = lxml.html.HTMLParser(remove_blank_text=True, remove_comments=True)
return lxml.html.fromstring(data, parser=parser) return lxml.html.fromstring(BeautifulSoup(data, 'lxml').prettify('utf-8'), parser=parser)
def count_words(string): def count_words(string):