使用Pygments过滤空格和换行符

Question

我一直在尝试给我的Django网站添加语法高亮。问题是我发现像 和<br />这些字符也被格式化了。有没有办法保留这些字符呢？这是我使用的代码：

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)

Answer 1

嗯，Petri说得对，pre是用来表示代码块的。在他指出这一点之前，我写了一个函数来清理第一次的输出，虽然有点乱，但也许有些人只是想从最终输出中去掉某些东西，可能会觉得这个方法还不错：

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': '&NBSP;', '/&gt;': ''}

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)