parser_functions.py 文件源码

def parseUrls(rtext):
    def findUrls(s):
        # yes, this is faster than regex and less complex to read
        urls = []
        prefixes = ("http://", "https://")
        for prefix in prefixes:
            start = 0
            while start >= 0:
                start = s.find(prefix, start)
                if start >= 0:
                    stop = s.find(" ", start)
                    if stop < 0:
                        stop = len(s)
                    urls.append(s[start:stop])
                    start += 1
        return urls

    def formatUrl(text, url):
        newText = u"""<a style="color:#28a5ed;font-weight:bold" href="link/{0}">{0}</a>"""
        text = text.replace(url, newText.format(url))
        return text

    texts = [t for t in rtext.contents if isinstance(t, NavigableString)]
    for text in texts:
        urls = findUrls(text)
        for url in urls:
            textReplace(text, formatUrl(text, url))
            return True