static.py 文件源码

def run(self):
        ret = []
        source = open(self.filepath, "rb").read()

        # Get rid of superfluous comments.
        source = re.sub("/\\*.*?\\*/", "", source, flags=re.S)

        for script in re.findall(self.script_re, source, re.I | re.S):
            try:
                x = bs4.BeautifulSoup(script, "html.parser")
                language = x.script.attrs.get("language", "").lower()
            except:
                language = None

            # We can't rely on bs4 or any other HTML/XML parser to provide us
            # with the raw content of the xml tag as they decode html entities
            # and all that, leaving us with a corrupted string.
            source = re.match("<.*>(.*)</.*>$", script, re.S).group(0)

            # Decode JScript.Encode encoding.
            if language in ("jscript.encode", "vbscript.encode"):
                source = self.decode(source)

            ret.append(to_unicode(source))

        return ret