信息收集-常用正则

邮箱

async def emails(self):
        await self.genericClean()
        # Local part is required, charset is flexible.
        # https://tools.ietf.org/html/rfc6531 (removed * and () as they provide FP mostly)
        reg_emails = re.compile(r'[a-zA-Z0-9.\-_+#~!$&\',;=:]+' + '@' + '[a-zA-Z0-9.-]*' + self.word.replace('www.', ''))
        self.temp = reg_emails.findall(self.results)
        emails = await self.unique()
        true_emails = {str(email)[1:].lower().strip() if len(str(email)) > 1 and str(email)[0] == '.'
                       else len(str(email)) > 1 and str(email).lower().strip() for email in emails}
        # if email starts with dot shift email string and make sure all emails are lowercase
        return true_emails

文件

 async def fileurls(self, file):
        urls = []
        reg_urls = re.compile('<a href="(.*?)"')
        self.temp = reg_urls.findall(self.results)
        allurls = await self.unique()
        for iteration in allurls:
            if iteration.count('webcache') or iteration.count('google.com') or iteration.count('search?hl'):
                pass
            else:
                urls.append(iteration)
        return urls

hostname

async def hostnames(self):
    await self.genericClean()
    reg_hosts = re.compile(r'[a-zA-Z0-9.-]*\.' + self.word)
    self.temp = reg_hosts.findall(self.results)
    hostnames = await self.unique()
    reg_hosts = re.compile(r'[a-zA-Z0-9.-]*\.' + self.word.replace('www.', ''))
    self.temp = reg_hosts.findall(self.results)
    hostnames.extend(await self.unique())
    return list(set(hostnames))

URL

 async def urls(self):
        found = re.finditer(r'(http|https)://(www\.)?trello.com/([a-zA-Z0-9\-_\.]+/?)*', self.results)
        urls = {match.group().strip() for match in found}
        return urls