RomanNum3ral
/
scrapy
mirror of https://github.com/scrapy/scrapy.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

rolled back public ent_re to private and added a function has_entities instead 

--HG--
extra : convert_revision : svn%3Ab85faa78-f9eb-468e-a121-7cced6da292c%40282
This commit is contained in:
Damian Canabal 2008-09-29 13:21:35 +00:00
parent ad00d5e632
commit f8f2f3a542
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
scrapy/trunk/scrapy/utils/markup.py
View File

@ -5,7 +5,7 @@ Functions for dealing with markup text
import re
import htmlentitydefs
ent_re = re.compile(r'&(#?)([^&;]+);')
_ent_re = re.compile(r'&(#?)([^&;]+);')
_tag_re = re.compile(r'<[a-zA-Z\/!].*?>', re.DOTALL)
def remove_entities(text, keep=(), remove_illegal=True):
@ -45,8 +45,10 @@ def remove_entities(text, keep=(), remove_illegal=True):
else:
return u'&%s;' % m.group(2)
return ent_re.sub(convert_entity, text.decode('utf-8'))
return _ent_re.sub(convert_entity, text.decode('utf-8'))
def has_entities(text):
return bool(_ent_re.search(text))
def replace_tags(text, token=''):
"""Replace all markup tags found in the given text by the given token. By