我一直在尝试为我的django网站添加语法突出显示。问题是我的格式也是
和<br />
字符。有没有办法保存这些角色?这是我正在使用的代码:
from BeautifulSoup import BeautifulSoup
from django import template
from django.template.defaultfilters import stringfilter
import pygments
import pygments.formatters
import pygments.lexers
register = template.Library()
@register.filter
@stringfilter
def pygmentized(html):
soup = BeautifulSoup(html)
codeblocks = soup.findAll('code')
for block in codeblocks:
if block.has_key('class'):
try:
code = ''.join([unicode(item) for item in block.contents])
lexer = pygments.lexers.get_lexer_by_name(block['class'], stripall=True)
formatter = pygments.formatters.HtmlFormatter()
code_hl = pygments.highlight(code, lexer, formatter)
block.contents = [BeautifulSoup(code_hl)]
block.name = 'code'
except:
raise
return unicode(soup)
答案 0 :(得分:1)
嗯,Petri是对的,pre是代码块。在他指出我刚刚编写了一个函数来清理第一个输出之前,它很乱,但也许只需要从最终输出中删除某些东西的人可能会发现它没问题:
from BeautifulSoup import BeautifulSoup
from django import template
from django.template.defaultfilters import stringfilter
import pygments
import pygments.formatters
import pygments.lexers
register = template.Library()
wanted = {'br': '<br />', 'BR': '<BR />', 'nbsp': ' ', 'NBSP': '&NBSP;', '/>': ''}
def uglyfilter(html):
content = BeautifulSoup(html)
for node in content.findAll('span'):
data = ''.join(node.findAll(text=True))
if wanted.has_key(data):
node.replaceWith(wanted.get(data))
return unicode(content)
@register.filter
@stringfilter
def pygmentized(html):
soup = BeautifulSoup(html)
codeblocks = soup.findAll('pre')
for block in codeblocks:
if block.has_key('class'):
try:
code = ''.join([unicode(item) for item in block.contents])
lexer = pygments.lexers.get_lexer_by_name(block['class'], stripall=True)
formatter = pygments.formatters.HtmlFormatter()
code_hl = pygments.highlight(code, lexer, formatter)
clean = uglyfilter(code_hl)
block.contents = [BeautifulSoup(clean)]
block.name = 'pre'
except:
raise
return unicode(soup)