def vul_scan(domain):
"""
常见漏洞扫描
"""
urls = Crawler(target=domain, dynamic=False).run()
Xss(targets=urls).scan()
Sqli(targets=urls).scan()
Struts2(urls).scan()
def crawl():
crawler = Crawler()
param_did = input("预先输入本用户cookie中的did值：")
crawler.set_did(param_did)
uid = input("输入此次要爬取的用户id：")
crawler.add_to_list(uid)
crawler.crawl()
input("请按回车键退出......")
def post(self, collection):
"""Crawl collection"""
try:
Crawler.crawl_and_save_articles_and_keywords(collection)
return (
json.dumps({"success": True}),
200,
{
"ContentType": "application/json"
},
)
except:
return (
json.dumps({"success": False}),
500,
{
"ContentType": "application/json"
},
)
def site_scan(domain):
if domain.startswith('http://www.'):
domain = domain[11:]
elif domain.startswith('https://www.'):
domain = domain[12:]
elif domain.startswith('http://'):
domain = domain[7:]
elif domain.startswith('https://'):
domain = domain[8:]
id = Database().insert_task(domain)
domains, ips = Domain(domain, id).run()
for domain in domains:
url = Crawler(domain).scan()
Vul(url, id).run()
Sendir(domains, id).run()
Port(id).run(ips)
def main():
# .envか実行引数からアクセストークンを取得
if dotenv.load_dotenv():
consumer_key = os.getenv("CLIENT_ID")
consumer_secret = os.getenv("CLIENT_SECRET")
access_token = os.getenv("ACCESS_TOKEN")
access_token_secret = os.getenv("ACCESS_TOKEN_SECRET")
elif len(sys.argv) >= 5:
consumer_key = sys.argv[1]
consumer_secret = sys.argv[2]
access_token = sys.argv[3]
access_token_secret = sys.argv[4]
else:
print("\033[31mERROR\033[0m: No credentials has been passed.")
return
# アクセストークンを渡してtweepy.apiのインスタンスを生成
auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_token, access_token_secret)
api = tweepy.API(auth, wait_on_rate_limit=True, wait_on_rate_limit_notify=True)
# ログインユーザの情報を吐き出す(auth.status的なものが見つからなかったのでこれで妥協)
try:
target_user_object = api.me()
print(f"Fetch target: {target_user_object.name}(@{target_user_object.screen_name})")
except tweepy.TweepError:
print("\033[31mERROR\033[0m: Couldn't get user object.Make sure whether you have passed a valid token.")
return
# ツイート収集・削除を行うスレッドをそれぞれ起動し、キューを直結
tweetqueue = StatusQueue()
crawlthread = CrawlThread(Crawler(api), tweetqueue, endreq_event)
eliminatethread = EliminateThread(Eliminator(api), tweetqueue, endreq_event)
crawlthread.start()
eliminatethread.start()
print("Process started.")
try:
crawlthread.join()
eliminatethread.join()
except KeyboardInterrupt:
print("Ctrl+C")
endreq_event.set()
crawlthread.join()
eliminatethread.join()
def enumerate_twit(args):
twit = Crawler(args.config_path, args.enum_search)
from lib.config import Config
from lib.zip import Zip
def init_driver(config_instance: Config):
drv = webdriver.PhantomJS(executable_path=config_instance.phantomjs_bin_path)
drv.wait = WebDriverWait(drv, 1)
return drv
if __name__ == "__main__":
# init config object and driver
config = Config('conf/config.yml')
driver = init_driver(config)
crawler = Crawler(driver, config)
print("====Driver logging in====")
crawler.login()
print("====Driver logged in====")
print("====Starting backup process====")
# head driver to pages section
crawler.goto_pages()
time.sleep(2)
# create folder for backups if it doesnt exist
current_datetime = time.strftime('%d%m%Y%H%M%S')
backup_dir_for_now = config.dir_backup + os.path.sep + current_datetime
if not os.path.exists(config.dir_backup):
os.makedirs(config.dir_backup)
def main():
opts, args = parse_options()
url = args[0]
if opts.links:
getLinks(url)
raise SystemExit, 0
depth_limit = opts.depth_limit
confine_prefix = opts.confine
exclude = opts.exclude
sTime = time.time()
print >> sys.stderr, "Crawling %s (Max Depth: %d)" % (url, depth_limit)
crawler = Crawler(url, depth_limit, confine_prefix, exclude)
crawler.crawl()
# create log directory
if not os.path.exists(LOG_DIRECTORY):
os.makedirs(LOG_DIRECTORY)
num_links = 0
if opts.out_urls:
for url_crawl in crawler.urls_seen:
parsed_uri = urlparse.urlparse(url_crawl)
# only base url
if not re.match(".*%s" % parsed_uri.netloc.replace('www.', ''),
url): # and not opts.skip_host:
continue
if not opts.out_path:
print url_crawl
else:
domain = '{uri.netloc}'.format(uri=parsed_uri)
log_file = "%s/%s.log" % (LOG_DIRECTORY, domain)
logging.basicConfig(
filename=log_file,
filemode='w+',
level=logging.DEBUG,
format=
'%(asctime)-15s [%(levelname)s] (%(threadName)-10s) %(message)s',
datefmt='%m/%d/%Y %I:%M:%S %p')
try:
directory = opts.out_path + domain + '/'
path = directory + toSeoFriendly(url_crawl, 50) + '.html'
if not os.path.exists(directory):
os.makedirs(directory)
r = requests.get(url_crawl,
allow_redirects=True,
timeout=30)
if not os.path.exists(path):
target = open(path, 'w')
target.write(r.text.encode('utf-8'))
target.close()
num_links = num_links + 1
logging.debug("Saving: {0}".format(url_crawl))
except IOError as e:
logging.error("IOError: {0} {1}".format(url, e.message))
pass
except Exception as e:
logging.error("Error({0}): {1}".format(
url, e.__doc__, e.message),
exc_info=True)
pass
if opts.out_links:
print "\n".join([str(l) for l in crawler.links_remembered])
if opts.out_dot:
d = DotWriter()
d.asDot(crawler.links_remembered)
eTime = time.time()
tTime = eTime - sTime
print >> sys.stderr, "Found: %d" % num_links
print >> sys.stderr, "Stats: (%d/s after %0.2fs)" % (int(
math.ceil(float(num_links) / tTime)), tTime)
class Taobaoke(MongoClient):
"""
Taobaoke
"""
start_urls = (
'http://pub.alimama.com/promo/item/channel/index.htm?channel=qqhd&toPage={}&catIds={}&level=1&perPageSize=100'
)
crawler = Crawler()
def start_requests(self):
# item list range
for cat in range(1, 18):
for page in range(10, 31):
print "crawl:%s,%s" % (cat, page)
self.requests_url(self.start_urls.format(page, cat),
callback=self.callback)
def requests_url(self, url, callback=None):
"""
:param url:
:param callback:
:return:
"""
crawler = self.crawler.crawl(url)
callback(crawler)
def safe_febx_text(self, crawler, xpath, count=1, max_count=10):
"""
:param crawler:
:param xpath:
:param count:
:param max_count:
:return:
"""
if count > max_count:
return ""
try:
return crawler.febx(xpath).text.strip()
except Exception:
print "try:%s" % count
return self.safe_febx_text(crawler,
xpath,
count=count + 1,
max_count=max_count)
def callback(self, crawler):
"""
回调处理
:param crawler:
:return:
"""
time.sleep(10)
for index in range(1, 101):
item = {
"title":
self.safe_febx_text(
crawler, u".//*[@id='J_search_results']/div/div[{}]"
u"/div[@class='box-content']/div[1]/p/a/node()".format(
index)),
"category":
self.safe_febx_text(crawler,
u".//*[@class='top-nav-tag']/span")
}
if not item["title"] or not item[
"category"] or self.db.tbk_test.find({
"title": item["title"]
}).count():
print "continue", item["category"], item["title"]
continue
print item["category"], item["title"]
self.db.tbk_test.insert(item)
browser.quit()
def content_func(res):
words = []
soup = BeautifulSoup(res.text, 'lxml')
content = ''
divs = soup.select('div.comp_detail')
del divs[-1]
for div in divs:
content += div.text.replace('\n', '').replace('\xa0', '')
words += list(
set(
re.findall('java script|objective c|visual basic|[A-Za-z.+#]+',
content, re.IGNORECASE)))
return words
# Create an instance of Crawler class
crawler = Crawler(open_thread=True)
# Call grab_content_th_auto to get content page by page
crawler.grab_content_th_auto(alinks, content_func, sleep_time=1)
# Call get_counter to get word count result
print(crawler.get_counter().most_common())
with open('yes123_1_new.csv', 'w') as f:
for lang, counts in crawler.get_counter().most_common():
f.write('{},{}\n'.format(lang, counts))
from lib.signature import Signature
from lib.crawler import Crawler
import coloredlogs
coloredlogs.install(fmt="%(asctime)s %(name)s [%(levelname)s] %(message)s")
signature = Signature(status_code=200)
signature.add(lambda x: "an error" not in x.text)
c = Crawler("https://www.youtube.com", "./test_dic.txt", signature=signature)
c.start()
# lock = threading.Lock() # 全局资源锁
# 提取数据、多线程、存储、异常处理、日志
initDir = "f:/thz/"
headers = {
"user-agent":
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36",
"Referer": "http://thzbbt.net",
}
initUrls = [
"http://thzbbt.net/forum-181-{num}.html".format(num=num)
for num in range(1, 10)
]
print "initUrls", initUrls
crawler = Crawler(initUrls, initDir, headers, "crawler-thz")
def fn1(url):
arr = []
r = requests.get(url, headers=headers, timeout=100).text
for father in BeautifulSoup(r, 'lxml').find_all('th', class_="common"):
link = father.find_all("a")[3]["href"]
arr.append("http://thzbbt.net/" + link)
return arr
def fn2(url):
arr = []
# print "url",url
r = requests.get(url, headers=headers, timeout=100).text
def vul_scan(domain):
url = Crawler(domain).scan()
Vul(url).run()
def crawl(collection):
Crawler.crawl_and_save_articles_and_keywords(collection)
def crawl_scan(domain):
Crawler(domain).scan()
def crawl():
c = Crawler()
c.set_did(param_did)
c.crawl_like("3xzixigzwy4kj5c")
links = soup.select('div.jbInfo > div > h3 > a')
if res.status_code == 200 and len(links) != 0:
for link in links:
page_links.append('https:' + str(link['href']))
return page_links
# Get total page from the website you want to crawl
HOST = 'https://www.1111.com.tw'
url = HOST + '/job-bank/job-index.asp?si=1&d0=140400,140200,140300&fs=1&ps=100&page=1'
res = requests.get(url)
soup = BeautifulSoup(res.text, 'lxml')
page = int(soup.select_one('div.pagedata').text.split('/')[1].split('жаЂ')[0])
# Create an instance of Crawler class
crawler = Crawler(open_thread=True)
# Call grab_pagelinks_th_auto to get all links
page_url = HOST + '/job-bank/job-index.asp?si=1&d0=140400,140200,140300&fs=1&ps=100&page={}'
crawler.grab_pagelinks_th_auto(page_url, page_func, page, sleep_time=1)
# Call get_alinks to get all links crawled from previous pages
links = crawler.get_alinks()
# Call grab_content_th_auto to get content page by page
crawler.grab_content_th_auto(links, content_func, sleep_time=1)
# Call get_counter to get word count result
print(crawler.get_counter().most_common())
with open('1111_1_new.csv', 'w') as f:
"user-agent":
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36",
"Referer": "http://www.mmjpg.com",
}
initUrls = [
"http://www.mmjpg.com/mm/{num}".format(num=num) for num in range(1, 2)
]
print "initUrls", initUrls
def getCurFileName():
filename = os.path.basename(__file__)
return filename[0:filename.find(".")]
crawler = Crawler(initUrls, initDir, headers, getCurFileName())
print "crawler初始化成功"
def fn1(url):
r = requests.get(url, headers=headers, timeout=100).text
maxCount = BeautifulSoup(r,
'lxml').find('div',
class_="page").find_all('a')[-2].text
# print maxCount
page_urls = [url + "/" + str(i) for i in range(1, int(maxCount) + 1)]
return page_urls
def fn2(url):
r = requests.get(url, headers=headers, timeout=100).text
URL = "https://www.ptt.cc/"
headers = {
'User-Agent':
'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko)\
Chrome/58.0.3029.96 Safari/537.36',
"cookies": "over18=1"
}
board = "Soft_Job"
#希望爬取ptt板面、但是頁面擷取的網址內容會缺乏URL,需要自行補上
res = requests.get(URL + "bbs/" + board + "/index.html", headers=headers)
soup = BeautifulSoup(res.text, 'lxml')
bottons = soup.select('a.btn.wide')
#totalpage=上一頁的頁數+1
totalpage = int(bottons[1]['href'].split('index')[1].split('.')[0]) + 1
crawler = Crawler(open_thread=True)
page_url = URL + "bbs/" + board + "/index{}.html"
crawler.grab_pagelinks_th_auto(page_url,
pttURL_crawler,
totalpage,
sleep_time=1,
header=headers)
links = crawler.get_alinks()
print(links)
# Call grab_content_th_auto to get content page by page
crawler.grab_content_th_auto(links, content_func, sleep_time=2)
# Call get_counter to get word count result
def crawl():
crawler = Crawler(False)
crawler.set_did(param_did)
crawler.crawl()
def main():
opts, args = parse_options()
url = args[0]
if opts.links:
getLinks(url)
raise SystemExit, 0
depth_limit = opts.depth_limit
confine_prefix = opts.confine
exclude = opts.exclude
sTime = time.time()
print >> sys.stderr, "Crawling %s (Max Depth: %d)" % (url, depth_limit)
crawler = Crawler(url, depth_limit, confine_prefix, exclude)
crawler.crawl()
# create log directory
if not os.path.exists(LOG_DIRECTORY):
os.makedirs(LOG_DIRECTORY)
num_links = 0
if opts.out_urls:
for url_crawl in crawler.urls_seen:
parsed_uri = urlparse.urlparse(url_crawl)
# only base url
if not re.match(".*%s" % parsed_uri.netloc.replace('www.', ''), url): # and not opts.skip_host:
continue
if not opts.out_path:
print url_crawl
else:
domain = '{uri.netloc}'.format(uri=parsed_uri)
log_file = "%s/%s.log" % (LOG_DIRECTORY, domain)
logging.basicConfig(
filename=log_file,
filemode='w+',
level=logging.DEBUG,
format='%(asctime)-15s [%(levelname)s] (%(threadName)-10s) %(message)s',
datefmt='%m/%d/%Y %I:%M:%S %p'
)
try:
directory = opts.out_path + domain + '/'
path = directory + toSeoFriendly(url_crawl, 50) + '.html'
if not os.path.exists(directory):
os.makedirs(directory)
r = requests.get(url_crawl, allow_redirects=True, timeout=30)
if not os.path.exists(path):
target = open(path, 'w')
target.write(r.text.encode('utf-8'))
target.close()
num_links = num_links + 1
logging.debug("Saving: {0}".format(url_crawl))
except IOError as e:
logging.error("IOError: {0} {1}".format(url, e.message))
pass
except Exception as e:
logging.error("Error({0}): {1}".format(url, e.__doc__, e.message), exc_info=True)
pass
if opts.out_links:
print "\n".join([str(l) for l in crawler.links_remembered])
if opts.out_dot:
d = DotWriter()
d.asDot(crawler.links_remembered)
eTime = time.time()
tTime = eTime - sTime
print >> sys.stderr, "Found: %d" % num_links
print >> sys.stderr, "Stats: (%d/s after %0.2fs)" % (
int(math.ceil(float(num_links) / tTime)), tTime)
