Python colors.run方法代码示例

# 需要导入模块: from core import colors [as 别名]
# 或者: from core.colors import run [as 别名]
def getQuark():
	if 'quark.html' not in os.listdir():
		cwd = os.getcwd()
		print ('%s Quark is neccessary to view graphs generated by Orbit.' % bad)
		print ('%s Downloading Quark [2.37 MB]' % run)
		os.system('git clone https://github.com/s0md3v/Quark %s/Quark -q' % cwd)
		os.system('mv ' + cwd + '/Quark/libs ' + cwd)
		os.system('mv ' + cwd + '/Quark/quark.html ' + cwd)
		os.remove(cwd + '/Quark/README.md')
		shutil.rmtree(cwd + '/Quark')
		print ('%s Quark was installed successfully' % info) 

# 需要导入模块: from core import colors [as 别名]
# 或者: from core.colors import run [as 别名]
def updater():
    """Update the current installation.

    git clones the latest version and merges it with the current directory.
    """
    print('%s Checking for updates' % run)
    # Changes must be separated by ;
    changes = '''major bug fixes;removed ninja mode;dropped python < 3.2 support;fixed unicode output;proxy support;more intels'''
    latest_commit = requester('https://raw.githubusercontent.com/s0md3v/Photon/master/core/updater.py', host='raw.githubusercontent.com')
    # Just a hack to see if a new version is available
    if changes not in latest_commit:
        changelog = re.search(r"changes = '''(.*?)'''", latest_commit)
        # Splitting the changes to form a list
        changelog = changelog.group(1).split(';')
        print('%s A new version of Photon is available.' % good)
        print('%s Changes:' % info)
        for change in changelog: # print changes
            print('%s>%s %s' % (green, end, change))

        current_path = os.getcwd().split('/') # if you know it, you know it
        folder = current_path[-1] # current directory name
        path = '/'.join(current_path) # current directory path
        choice = input('%s Would you like to update? [Y/n] ' % que).lower()

        if choice != 'n':
            print('%s Updating Photon' % run)
            os.system('git clone --quiet https://github.com/s0md3v/Photon %s'
                      % (folder))
            os.system('cp -r %s/%s/* %s && rm -r %s/%s/ 2>/dev/null'
                      % (path, folder, path, path, folder))
            print('%s Update successful!' % good)
    else:
        print('%s Photon is up to date!' % good) 

# 需要导入模块: from core import colors [as 别名]
# 或者: from core.colors import run [as 别名]
def photon(seedUrl, headers, depth, threadCount):
    forms = []  # web forms
    processed = set()  # urls that have been crawled
    storage = set()  # urls that belong to the target i.e. in-scope
    scheme = urlparse(seedUrl).scheme
    host = urlparse(seedUrl).netloc
    main_url = scheme + '://' + host
    storage.add(seedUrl)

    def rec(url):
        processed.add(url)
        urlPrint = (url + (' ' * 60))[:60]
        print ('%s Parsing %-40s' % (run, urlPrint), end='\r')
        url = getUrl(url, '', True)
        params = getParams(url, '', True)
        if '=' in url:
            inps = []
            for name, value in params.items():
                inps.append({'name': name, 'value': value})
            forms.append(
                {url: {0: {'action': url, 'method': 'get', 'inputs': inps}}})
        response = requester(url, params, headers, True, 0).text
        forms.append({url: zetanize(url, response)})
        matches = findall(
            r'<[aA][^>]*?(href|HREF)=["\']{0,1}(.*?)["\']', response)
        for link in matches:  # iterate over the matches
            # remove everything after a "#" to deal with in-page anchors
            link = link[1].split('#')[0].lstrip(' ')
            if link[:4] == 'http':
                if link.startswith(main_url):
                    storage.add(link)
            elif link[:2] == '//':
                if link.split('/')[2].startswith(host):
                    storage.add(scheme + '://' + link)
            elif link[:1] == '/':
                storage.add(remove_file(url) + link)
            else:
                usable_url = remove_file(url)
                if usable_url.endswith('/'):
                    storage.add(usable_url + link)
                elif link.startswith('/'):
                    storage.add(usable_url + link)
                else:
                    storage.add(usable_url + '/' + link)
    for x in range(depth):
        urls = storage - processed
        threadpool = concurrent.futures.ThreadPoolExecutor(max_workers=10)
        futures = (threadpool.submit(rec, url) for url in urls)
        for i in concurrent.futures.as_completed(futures):
            pass
    return [forms, len(processed)] 

# 需要导入模块: from core import colors [as 别名]
# 或者: from core.colors import run [as 别名]
def photon(seedUrl):
    forms = []  # web forms
    processed = set()  # urls that have been crawled
    storage = set()  # urls that belong to the target i.e. in-scope
    schema = urlparse(seedUrl).scheme  # extract the scheme e.g. http or https
    host = urlparse(seedUrl).netloc  # extract the host e.g. example.com
    main_url = schema + '://' + host  # join scheme and host to make the root url
    storage.add(seedUrl)  # add the url to storage
    checkedScripts = set()
    all_techs = []
    all_outdated_js = []

    def rec(target):
        processed.add(target)
        urlPrint = (target + (' ' * 60))[:60]
        print ('%s Parsing %-40s' % (run, urlPrint), end='\r')
        url = getUrl(target, True)
        params = getParams(target, '', True)
        if '=' in target:  # if there's a = in the url, there should be GET parameters
            inps = []
            for name, value in params.items():
                inps.append({'name': name, 'value': value})
            forms.append({0: {'action': url, 'method': 'get', 'inputs': inps}})
        raw_response = requester(url, params, True)
        response = raw_response.text
        js = js_extractor(response)
        scripts = script_extractor(response)
        for each in retirejs(url, response, checkedScripts):
            all_outdated_js.append(each)
        all_techs.extend(wappalyzer(raw_response, js, scripts))
        parsed_response = zetanize(response)
        forms.append(parsed_response)
        matches = re.finditer(r'<[aA][^>]*?(?:href|HREF)=[\'"`]?([^\s>]*?)[\'"`]?>', response)
        for link in matches:  # iterate over the matches
            # remove everything after a "#" to deal with in-page anchors
            this_url = handle_anchor(target, link.group(1))
            if is_link(this_url, processed):
                if urlparse(this_url).netloc == host:
                    storage.add(this_url.split('#')[0])
    for x in range(2):
        urls = storage - processed  # urls to crawl = all urls - urls that have been crawled
        threadpool = concurrent.futures.ThreadPoolExecutor(
            max_workers=10)
        futures = (threadpool.submit(rec, url) for url in urls)
        for i in concurrent.futures.as_completed(futures):
            pass
    return [forms, processed, set(all_techs), all_outdated_js] 

# 需要导入模块: from core import colors [as 别名]
# 或者: from core.colors import run [as 别名]
def zap(input_url, archive, domain, host, internal, robots, proxies):
    """Extract links from robots.txt and sitemap.xml."""
    if archive:
        print('%s Fetching URLs from archive.org' % run)
        if False:
            archived_urls = time_machine(domain, 'domain')
        else:
            archived_urls = time_machine(host, 'host')
        print('%s Retrieved %i URLs from archive.org' % (
            good, len(archived_urls) - 1))
        for url in archived_urls:
            verb('Internal page', url)
            internal.add(url)
    # Makes request to robots.txt
    response = requests.get(input_url + '/robots.txt',
                            proxies=random.choice(proxies)).text
    # Making sure robots.txt isn't some fancy 404 page
    if '<body' not in response:
        # If you know it, you know it
        matches = re.findall(r'Allow: (.*)|Disallow: (.*)', response)
        if matches:
            # Iterating over the matches, match is a tuple here
            for match in matches:
                # One item in match will always be empty so will combine both
                # items
                match = ''.join(match)
                # If the URL doesn't use a wildcard
                if '*' not in match:
                    url = input_url + match
                    # Add the URL to internal list for crawling
                    internal.add(url)
                    # Add the URL to robots list
                    robots.add(url)
            print('%s URLs retrieved from robots.txt: %s' % (good, len(robots)))
    # Makes request to sitemap.xml
    response = requests.get(input_url + '/sitemap.xml',
                            proxies=random.choice(proxies)).text
    # Making sure robots.txt isn't some fancy 404 page
    if '<body' not in response:
        matches = xml_parser(response)
        if matches: # if there are any matches
            print('%s URLs retrieved from sitemap.xml: %s' % (
                good, len(matches)))
            for match in matches:
                verb('Internal page', match)
                # Cleaning up the URL and adding it to the internal list for
                # crawling
                internal.add(match)