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

Added override for auto-detected character encoding of parsed pages.

Browse Source
This commit is contained in:
Florian Muenchbach
2016-01-31 13:52:23 +01:00
committed by pictuga
parent 627163abff
commit 993ac638a3
3 changed files with 18 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
morss/readabilite.py
View File

@@ -3,8 +3,12 @@ import lxml.html
import re
def parse(data):
parser = lxml.html.HTMLParser(remove_blank_text=True, remove_comments=True)
def parse(data, encoding=None):
if encoding:
parser = lxml.html.HTMLParser(remove_blank_text=True, remove_comments=True, encoding=encoding)
else:
parser = lxml.html.HTMLParser(remove_blank_text=True, remove_comments=True)
return lxml.html.fromstring(data, parser=parser)
@@ -149,5 +153,5 @@ def br2p(root):
gdparent.insert(gdparent.index(parent)+1, new_item)
def get_article(data):
return lxml.etree.tostring(get_best_node(parse(data)))
def get_article(data, encoding=None):
return lxml.etree.tostring(get_best_node(parse(data, encoding)))