python - 如何用<em>标签替换html中的所有链接标签?

Question

我有一个程序，它可以把一篇长文章的内容缩短成一个简短的摘要，使用的是PHP。不过，我不想在页面加载时就生成这个摘要，而是想把它存储到数据库里。

我已经把其他的都搞定了，唯一的问题是如何把链接标签替换成一个<em>文本</em>。我不想用beautiful soup来处理这个，尽量想用简单的正则表达式替换，如果可以的话，或者用HTMLParser的其他功能（我在网上搜索了一段时间也没找到合适的）。

这是我现在的代码：

import HTMLParser, string, re

tag_end_re = re.compile(r'(\w+)[^>]*>')
entity_end_re = re.compile(r'(\w+;)')

class StrippingParser(HTMLParser.HTMLParser):

    # These are the HTML tags that we will leave intact
    valid_tags = ('a')

    from htmlentitydefs import entitydefs # replace entitydefs from sgmllib

    def __init__(self):
        HTMLParser.HTMLParser.__init__(self)
        self.result = ""
        self.endTagList = []

    def handle_data(self, data):
        if data:
            self.result = self.result + data

    def handle_charref(self, name):
        self.result = "%s&#%s;" % (self.result, name)

    def handle_entityref(self, name):
        if self.entitydefs.has_key(name): 
            x = ';'
        else:
            # this breaks unstandard entities that end with ';'
            x = ''
        self.result = "%s&%s%s" % (self.result, name, x)

    def handle_starttag(self, tag, attrs):
        """ Delete all tags except for legal ones """
        if tag in self.valid_tags:       
            self.result = self.result + '<' + tag
            for k, v in attrs:
                if string.lower(k[0:2]) != 'on' and string.lower(v[0:10]) != 'javascript':
                    self.result = '%s %s="%s"' % (self.result, k, v)
            endTag = '</%s>' % tag
            self.endTagList.insert(0,endTag)    
            self.result = self.result + '>'

    def handle_endtag(self, tag):
        if tag in self.valid_tags:
            self.result = "%s</%s>" % (self.result, tag)
            remTag = '</%s>' % tag
            self.endTagList.remove(remTag)

    def cleanup(self):
        """ Append missing closing tags """
        for j in range(len(self.endTagList)):
                self.result = self.result + self.endTagList[j]    


def strip(s):
    """ Strip illegal HTML tags from string s """
    parser = StrippingParser()
    parser.feed(s)
    parser.close()
    parser.cleanup()
    return parser.result


def truncate_html(string, length, ellipsis='...'):
    """Truncate HTML string, preserving tag structure and character entities."""
    length = int(length)
    output_length = 0
    i = 0
    pending_close_tags = {}

    while output_length < length and i < len(string):
        c = string[i]

        if c == '<':
            # probably some kind of tag
            if i in pending_close_tags:
                # just pop and skip if it's closing tag we already knew about
                i += len(pending_close_tags.pop(i))
            else:
                # else maybe add tag
                i += 1
                match = tag_end_re.match(string[i:])
                if match:
                    tag = match.groups()[0]
                    i += match.end()

                    # save the end tag for possible later use if there is one
                    match = re.search(r'(</' + tag + '[^>]*>)', string[i:], re.IGNORECASE)
                    if match:
                        pending_close_tags[i + match.start()] = match.groups()[0]
                else:
                    output_length += 1 # some kind of garbage, but count it in

        elif c == '&':
            # possible character entity, we need to skip it
            i += 1
            match = entity_end_re.match(string[i:])
            if match:
                i += match.end()

            # this is either a weird character or just '&', both count as 1
            output_length += 1
        else:
            # plain old characters

            skip_to = string.find('<', i, i + length)
            if skip_to == -1:
                skip_to = string.find('&', i, i + length)
            if skip_to == -1:
                skip_to = i + length

            # clamp
            delta = min(skip_to - i,
                        length - output_length,
                        len(string) - i)

            output_length += delta
            i += delta

    output = [string[:i]]
    if output_length == length:
        output.append(ellipsis)

    for k in sorted(pending_close_tags.keys()):
        output.append(pending_close_tags[k])

    return "".join(output)


def summarize(contents,length):
    summary = strip(contents)
    summary = truncate_html(summary,length)
    return summary

现在调用summarize('我的长文本，里面有<a href="" target="_blank">链接</a>',400)会返回一个400个字符的摘要（不包括HTML标签），里面还包含链接。我需要帮助把这些链接替换成标签。

Answer 1

你可以用一个简单的正则表达式来解决这个问题：

import re
'<em>' + re.search(r'<a.+>(.+)</a>',r'my long text with <a href="" target="_blank">links</a>').group(1) + '</em>'