hackpad_mail_processor.py 文件源码

def extract_url(self, text):
        """
        Extract Hackpad Archive URL from a text

        :param text:
        :return: the located URL as a string
        """
        archive_url = None
        regexes = [
            re.compile('https:\/\/[A-Za-z0-9\.-]*hackpad-export\.s3[^"]*(?=")'),
            re.compile('https:\/\/[A-Za-z0-9\.-]*hackpad-export\.s3[^>]*(?=>)')
        ]
        for r in regexes:
            matches = r.findall(text)

            if matches:
                archive_url = html.unescape(matches[0])
                self._logger.info("Located download URL: %s" % archive_url)
                break

        return archive_url