class CrawlBadips(Task):
def __init__(self):
super().__init__('badips 数据爬取')
self.logger = ContextLogger('threat_ip')
def run_crawl(self):
start = time.time()
ips = []
url = 'https://www.badips.com/get/list/any/2?age=7d'
source = 'www.badips.com'
_info = self.get(url=url)
if _info is None:
self.logger.warning("request returned None " + source)
return None
info = _info.split('\n')
for _ip in info:
if _ip.startswith('#'): continue
if _ip == '': continue
ip = _ip.strip()
block = [ip, source]
ips.append(block)
stop = time.time()
crawl_time = str(stop - start) + "秒"
self.save_info(ips, source, crawl_time)
def save_info(self, ips, source, crawl_time):
start = time.time()
all_count = len(ips)
avail_count = 0
_time = datetime.now().strftime("%Y-%m-%d")
if len(ips) > 0:
try:
for ip, source in ips:
flag = db.session.query(IP).filter(
IP.ip == ip, IP.source == source).first()
if flag is None:
new_ip = IP()
new_ip.ip = ip
new_ip.source = source
db.session.add(new_ip)
avail_count += 1
else:
flag.updatetime = _time
db.session.add(flag)
db.session.commit()
except Exception as e:
self.logger.warning("Error writing to database" + str(e) +
source)
else:
self.logger.warning("NO record found from: %s" % source)
stop = time.time()
storage_time = str(stop - start) + "秒"
self.logger.info("badips 共收集{0}条数据， 新数据{1}条".format(
all_count, avail_count))
self.logger.info("badips 抓取时间{0}，数据遍历时间{1}".format(
crawl_time, storage_time))
class CrawlBambenekconsulting(Task):
def __init__(self):
super().__init__('bambenekconsulting 数据爬取')
self.logger = ContextLogger('threat_domain')
def run_crawl(self):
start = time.time()
domains = []
url = 'http://osint.bambenekconsulting.com/feeds/c2-dommasterlist-high.txt'
source = 'osint.bambenekconsulting.com'
_info = self.get(url=url)
if _info is None:
self.logger.warning("request returned None "+source)
return None
info = _info.split('\n')
for _domain in info:
if _domain.startswith('#'): continue
if _domain == '': continue
domain = _domain.split(',')[0]
description = re.search('Domain used by (.*)', _domain.split(',')[1]).group(1)
updatetime = _domain.split(',')[2].split(' ')[0]
block = [domain, updatetime, description, source]
domains.append(block)
stop = time.time()
crawl_time = str(stop - start) + "秒"
self.save_info(domains, source, crawl_time)
def save_info(self, domains, source, crawl_time):
start = time.time()
all_count = len(domains)
avail_count = 0
if len(domains) > 0:
try:
for domain, updatetime, description, source in domains:
flag = db.session.query(Domain).filter(Domain.domain == domain, Domain.source == source).first()
if flag is None:
new_domain = Domain()
new_domain.domain = domain
new_domain.updatetime = updatetime
new_domain.description = description
new_domain.source = source
db.session.add(new_domain)
avail_count += 1
else:
flag.updatetime = updatetime
db.session.add(flag)
db.session.commit()
except Exception as e:
self.logger.warning("Error writing to database" + str(e) + source)
else:
self.logger.warning("NO record found from: %s" % source)
stop = time.time()
storage_time = str(stop - start) + "秒"
self.logger.info("bambenekconsulting 共收集{0}条数据， 新数据{1}条".format(all_count, avail_count))
self.logger.info("bambenekconsulting 抓取时间{0}，数据遍历时间{1}".format(crawl_time, storage_time))
class CrawlMaxmind(Task):
def __init__(self):
super().__init__('maxmind 数据爬取')
self.logger = ContextLogger('threat_ip')
def run_crawl(self):
start = time.time()
ips = []
url = 'https://www.maxmind.com/en/high-risk-ip-sample-list'
source = 'www.maxmind.com'
_info = self.get(url=url)
if _info is None:
self.logger.warning("request returned None " + source)
return None
_ips = re.findall(r'[0-9]+(?:\.[0-9]+){3}', _info)
description = 'Higher Risk IP'
for ip in _ips:
block = [ip, description, source]
ips.append(block)
stop = time.time()
crawl_time = str(stop - start) + "秒"
self.save_info(ips, source, crawl_time)
def save_info(self, ips, source, crawl_time):
start = time.time()
all_count = len(ips)
avail_count = 0
_time = datetime.now().strftime("%Y-%m-%d")
if len(ips) > 0:
try:
for ip, description, source in ips:
flag = db.session.query(IP).filter(
IP.ip == ip, IP.source == source).first()
if flag is None:
new_ip = IP()
new_ip.ip = ip
new_ip.description = description
new_ip.source = source
db.session.add(new_ip)
avail_count += 1
else:
flag.updatetime = _time
db.session.add(flag)
db.session.commit()
except Exception as e:
self.logger.warning("Error writing to database" + str(e) +
source)
else:
self.logger.warning("NO record found from: %s" % source)
stop = time.time()
storage_time = str(stop - start) + "秒"
self.logger.info("maxmind 共收集{0}条数据， 新数据{1}条".format(
all_count, avail_count))
self.logger.info("maxmind 抓取时间{0}，数据遍历时间{1}".format(
crawl_time, storage_time))
class CrawlMalwaredomains(Task):
def __init__(self):
super().__init__('malwaredomains 数据爬取')
self.logger = ContextLogger('threat_domain')
def run_crawl(self):
start = time.time()
domains = []
url = 'http://mirror4.malwaredomains.com/files/justdomains'
source = 'mirror4.malwaredomains.com'
_info = self.get(url=url)
if _info is None:
self.logger.warning("request returned None " + source)
return None
info = _info.split('\n')
for domain in info:
block = [domain, source]
domains.append(block)
stop = time.time()
crawl_time = str(stop - start) + "秒"
self.save_info(domains, source, crawl_time)
def save_info(self, domains, source, crawl_time):
start = time.time()
all_count = len(domains)
avail_count = 0
_time = datetime.now().strftime("%Y-%m-%d")
if len(domains) > 0:
try:
for domain, source in domains:
flag = db.session.query(Domain).filter(
Domain.domain == domain,
Domain.source == source).first()
if flag is None:
new_domain = Domain()
new_domain.domain = domain
new_domain.source = source
db.session.add(new_domain)
avail_count += 1
else:
flag.updatetime = _time
db.session.add(flag)
db.session.commit()
except Exception as e:
self.logger.warning("Error writing to database" + str(e) +
source)
else:
self.logger.warning("NO record found from: %s" % source)
stop = time.time()
storage_time = str(stop - start) + "秒"
self.logger.info("malwaredomains 共收集{0}条数据， 新数据{1}条".format(
all_count, avail_count))
self.logger.info("malwaredomains 抓取时间{0}，数据遍历时间{1}".format(
crawl_time, storage_time))
class CrawlCybersweat(Task):
def __init__(self):
super().__init__('cybersweat 数据爬取')
self.logger = ContextLogger('threat_ip')
def run_crawl(self):
start = time.time()
ips = []
url = 'https://cybersweat.shop/iprep/iprep_ramnode.txt' # ERROR
source = 'cybersweat.shop'
proxies = {'http': 'socks5://127.0.0.1:1080', 'https': 'socks5://127.0.0.1:1080'}
_info = self.get(url=url, proxies=proxies)
if _info is None:
self.logger.warning("request returned None "+source)
return None
info = _info.split('\n')
for _ip in info:
if _ip.startswith('#'): continue
if _ip == '': continue
ip = _ip.split(';')[0].strip()
updatetime = _ip.split(';')[1].strip().split()[0].strip()
block = [ip, updatetime, source]
ips.append(block)
stop = time.time()
crawl_time = str(stop - start) + "秒"
self.save_info(ips, source, crawl_time)
def save_info(self, ips, source, crawl_time):
start = time.time()
all_count = len(ips)
avail_count = 0
if len(ips) > 0:
try:
for ip, updatetime, source in ips:
flag = db.session.query(IP).filter(IP.ip == ip, IP.source == source).first()
if flag is None:
new_ip = IP()
new_ip.ip = ip
new_ip.updatetime = updatetime
new_ip.source = source
db.session.add(new_ip)
avail_count += 1
else:
flag.updatetime = updatetime
db.session.add(flag)
db.session.commit()
except Exception as e:
self.logger.warning("Error writing to database" + str(e) + source)
else:
self.logger.warning("NO record found from: %s" % source)
stop = time.time()
storage_time = str(stop - start) + "秒"
self.logger.info("cybersweat 共收集{0}条数据， 新数据{1}条".format(all_count, avail_count))
self.logger.info("cybersweat 抓取时间{0}，数据遍历时间{1}".format(crawl_time, storage_time))
class CrawlGithubusercontent(Task):
def __init__(self):
super().__init__('githubusercontent 数据爬取')
self.logger = ContextLogger('threat_ip')
def run_crawl(self):
start = time.time()
ips = []
urls = ['https://raw.githubusercontent.com/firehol/blocklist-ipsets/master/botscout_1d.ipset',
'https://raw.githubusercontent.com/firehol/blocklist-ipsets/master/cruzit_web_attacks.ipset'
]
source = 'raw.githubusercontent.com'
for url in urls:
_info = self.get(url=url)
if _info is None:
self.logger.warning("request returned None " + source)
return None
info = _info.split('\n')
for _ip in info:
if _ip.startswith('#'): continue
if _ip == '': continue
ip = _ip.strip()
block = [ip, source]
ips.append(block)
stop = time.time()
crawl_time = str(stop - start) + "秒"
self.save_info(ips, source, crawl_time)
def save_info(self, ips, source, crawl_time):
start = time.time()
all_count = len(ips)
avail_count = 0
_time = datetime.now().strftime("%Y-%m-%d")
if len(ips) > 0:
try:
for ip, source in ips:
flag = db.session.query(IP).filter(IP.ip == ip, IP.source == source).first()
if flag is None:
new_ip = IP()
new_ip.ip = ip
new_ip.source = source
db.session.add(new_ip)
avail_count += 1
else:
flag.updatetime = _time
db.session.add(flag)
db.session.commit()
except Exception as e:
self.logger.warning("Error writing to database" + str(e) + source)
else:
self.logger.warning("NO record found from: %s" % source)
stop = time.time()
storage_time = str(stop - start) + "秒"
self.logger.info("githubusercontent 共收集{0}条数据， 新数据{1}条".format(all_count, avail_count))
self.logger.info("githubusercontent 抓取时间{0}，数据遍历时间{1}".format(crawl_time, storage_time))
class Crawlemergingthreats(Task):
def __init__(self):
super().__init__('emergingthreats 数据爬取')
self.logger = ContextLogger('threat_ip')
def run_crawl(self):
start = time.time()
ips = []
url = 'http://rules.emergingthreats.net/open/suricata/rules/botcc.rules'
source = 'rules.emergingthreats.net'
_info = self.get(url=url)
if _info is None:
self.logger.warning("request returned None "+source)
return None
blocks = re.findall(r'(\[.*\))', _info)
for block in blocks:
_ips = re.findall(r'[0-9]+(?:\.[0-9]+){3}', block)
description = re.search('classtype:(.*?);', block).group(1)
for ip in _ips:
block = [ip, description, source]
ips.append(block)
stop = time.time()
crawl_time = str(stop - start) + "秒"
self.save_info(ips, source, crawl_time)
def save_info(self, ips, source, crawl_time):
start = time.time()
all_count = len(ips)
avail_count = 0
_time = datetime.now().strftime("%Y-%m-%d")
if len(ips) > 0:
try:
for ip, description, source in ips:
flag = db.session.query(IP).filter(IP.ip == ip, IP.source == source).first()
if flag is None:
new_ip = IP()
new_ip.ip = ip
new_ip.description = description
new_ip.source = source
db.session.add(new_ip)
avail_count += 1
else:
flag.updatetime = _time
db.session.add(flag)
db.session.commit()
except Exception as e:
self.logger.warning("Error writing to database" + str(e) + source)
else:
self.logger.warning("NO record found from: %s" % source)
stop = time.time()
storage_time = str(stop - start) + "秒"
self.logger.info("emergingthreats 共收集{0}条数据， 新数据{1}条".format(all_count, avail_count))
self.logger.info("emergingthreats 抓取时间{0}，数据遍历时间{1}".format(crawl_time, storage_time))
class CrawlRansomwaretracker(Task):
def __init__(self):
super().__init__('ransomwaretracker 数据爬取')
self.logger = ContextLogger('threat_domain')
def run_crawl(self):
start = time.time()
domains = []
url = 'https://ransomwaretracker.abuse.ch/downloads/RW_DOMBL.txt'
source = 'ransomwaretracker.abuse.ch'
_info = self.get(url=url)
if _info is None:
self.logger.warning("request returned None "+source)
return None
info = _info.split('\n')
description = 'Ransomware'
for domain in info:
if domain.startswith('#'): continue
if domain == '': continue
block = [domain, description, source]
domains.append(block)
stop = time.time()
crawl_time = str(stop - start) + "秒"
self.save_info(domains, source, crawl_time)
def save_info(self, domains, source, crawl_time):
start = time.time()
all_count = len(domains)
avail_count = 0
_time = datetime.now().strftime("%Y-%m-%d")
if len(domains) > 0:
try:
for domain, description, source in domains:
flag = db.session.query(Domain).filter(Domain.domain == domain, Domain.source == source).first()
if flag is None:
new_domain = Domain()
new_domain.domain = domain
new_domain.description = description
new_domain.source = source
db.session.add(new_domain)
avail_count += 1
else:
flag.updatetime = _time
db.session.add(flag)
db.session.commit()
except Exception as e:
self.logger.warning("Error writing to database" + str(e) + source)
else:
self.logger.warning("NO record found from: %s" % source)
stop = time.time()
storage_time = str(stop - start) + "秒"
self.logger.info("ransomwaretracker 共收集{0}条数据， 新数据{1}条".format(all_count, avail_count))
self.logger.info("ransomwaretracker 抓取时间{0}，数据遍历时间{1}".format(crawl_time, storage_time))
class Task(BaseReq):
def __init__(self, name, time=None):
super().__init__()
self.logger = ContextLogger('sync_sqlite')
self.name = name
self.time = time
def start(self):
self.logger.info("Task Started: {}".format(self.name))
def exit(self):
sys.exit()
def process(self):
pass
def finish(self):
self.logger.info("Task Finished: {}".format(self.name))
def safe_commit(self, value):
try:
db.session.add(value)
db.session.commit()
self.logger.info('同步成功')
except Exception as e:
self.logger.warning(e)
db.session.rollback()
def run(self):
self.start()
self.process()
self.finish()
class Task(BaseReq):
def __init__(self, name, time=None):
super().__init__()
self.logger = ContextLogger('task')
self.name = name
self.time = time
self.headers = {
'Upgrade - Insecure - Requests': '1',
'User-Agent':
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:43.0) Gecko/20100101 Firefox/43.0',
'Accept':
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
'Accept-Language': 'zh-CN,zh;q=0.9',
'Accept-Encoding': 'gzip, deflate',
'Referer': 'http://www.baidu.com',
'Connection': 'keep-alive',
'Cache-Control': 'max-age=0',
}
self.cookies = {}
def start(self):
self.logger.info("Task Started: {}".format(self.name))
def exit(self):
sys.exit()
def finish(self):
self.logger.info("Task Finished: {}".format(self.name))
def run(self):
self.start()
self.run_crawl()
self.finish()
def safe_commit(self, value):
try:
db.session.add(value)
db.session.commit()
self.logger.info(value.title + '提交成功')
except Exception as e:
self.logger.warning(e)
db.session.rollback()
class Task(BaseReq):
def __init__(self, name, time=None):
super().__init__()
self.logger = ContextLogger('task')
self.name = name
self.time = time
self.cookies = {}
self.headers = {}
def start(self):
self.logger.info("Task Started: {}".format(self.name))
def exit(self):
sys.exit()
def finish(self):
self.logger.info("Task Finished: {}".format(self.name))
def run(self):
self.start()
self.run_crawl()
self.finish()
def safe_commit(self, value):
try:
db.session.add(value)
db.session.commit()
self.logger.info(value.job_type + value.createTime + '提交成功')
except Exception as e:
self.logger.warning(e)
db.session.rollback()
def get_one_page(self, url):
"""
Crawl a url and return the HTML code for this url.
Args:
url: The url you need to crawl.
Returns:
the HTML code for this url
"""
# try:
# response = requests.get(url, headers=self.headers)
# except Exception as e:
# self.logger.warning(url + ' ' + str(e))
# return False
# return response.text
response = self.get(url)
return response
def run_crawl(self):
"""
Traverse all the pages you need to crawl.
"""
pass
def handle_list_html(self, html, tag):
"""
The analysis page gets all the urls you need to crawl.
Args:
html: The page HTML that needs to be analyzed
"""
pass
def handle_info_html(self, html, url, tag):
"""
The analysis page extracts all vulnerability information and commit to database.
Args:
html: The page HTML that needs to be analyzed
url: The page url that needs to be analyzed
"""
pass
class Task(BaseReq):
def __init__(self, name, time=None):
super().__init__()
self.logger = ContextLogger('task')
self.name = name
self.time = time
self.header = {
'Accept-Language':
'zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3',
'Accept':
'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'User-Agent':
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.13; rv:52.0) Gecko/20100101'
}
self.cookies = {}
def start(self):
self.logger.info("Task Started: {}".format(self.name))
def exit(self):
sys.exit()
def finish(self):
self.logger.info("Task Finished: {}".format(self.name))
def run(self):
self.start()
self.run_crawl()
self.finish()
def safe_commit(self, value):
try:
db.session.add(value)
db.session.commit()
self.logger.info(value.title + '提交成功')
except Exception as e:
self.logger.warning(e)
db.session.rollback()
def get_one_page(self, url):
"""
Crawl a url and return the HTML code for this url.
Args:
url: The url you need to crawl.
Returns:
the HTML code for this url
"""
# try:
# response = requests.get(url, headers=self.headers)
# except Exception as e:
# self.logger.warning(url + ' ' + str(e))
# return False
# return response.text
response = self.get(url)
return response
def run_crawl(self):
"""
Traverse all the pages you need to crawl.
"""
pass
def handle_list_html(self, html):
"""
The analysis page gets all the urls you need to crawl.
Args:
html: The page HTML that needs to be analyzed
"""
pass
def handle_info_html(self, html, url):
"""
The analysis page extracts all vulnerability information and commit to database.
Args:
html: The page HTML that needs to be analyzed
url: The page url that needs to be analyzed
"""
pass
def is_ip(self, _str):
p = re.compile(
'^((25[0-5]|2[0-4]\d|[01]?\d\d?)\.){3}(25[0-5]|2[0-4]\d|[01]?\d\d?)$'
)
if p.match(_str):
return True
else:
return False
class CrawlDataplane(Task):
def __init__(self):
super().__init__('dataplane 数据爬取')
self.logger = ContextLogger('threat_ip')
def run_crawl(self):
start = time.time()
ips = []
urls = ['https://dataplane.org/dnsrd.txt',
'https://dataplane.org/dnsrdany.txt',
'https://dataplane.org/dnsversion.txt',
'https://dataplane.org/sipinvitation.txt',
'https://dataplane.org/sipquery.txt',
'https://dataplane.org/sipregistration.txt',
'https://dataplane.org/sshclient.txt',
'https://dataplane.org/sshpwauth.txt',
'https://dataplane.org/vncrfb.txt'
]
source = 'dataplane.org'
for url in urls:
_info = self.get(url=url)
if _info is None:
self.logger.warning("request returned None " + source)
return None
info = _info.split('\n')
for _ip in info:
if _ip.startswith('#'): continue
if _ip == '': continue
asn = _ip.split('|')[0].strip()
asname = _ip.split('|')[1].strip()
ip = _ip.split('|')[2].strip()
updatetime = _ip.split('|')[3].strip().split()[0]
category = _ip.split('|')[4].strip()
block = [ip, updatetime, source, asname, asn, category]
ips.append(block)
stop = time.time()
crawl_time = str(stop - start) + "秒"
self.save_info(ips, source, crawl_time)
def save_info(self, ips, source, crawl_time):
start = time.time()
all_count = len(ips)
avail_count = 0
if len(ips) > 0:
try:
for ip, updatetime, source, asname, asn, category in ips:
flag = db.session.query(IP).filter(IP.ip == ip, IP.source == source).first()
if flag is None:
new_ip = IP()
new_ip.ip = ip
new_ip.updatetime = updatetime
new_ip.source = source
new_ip.asname = asname
new_ip.asn = asn
new_ip.category = category
db.session.add(new_ip)
avail_count += 1
else:
flag.updatetime = updatetime
db.session.add(flag)
db.session.commit()
except Exception as e:
self.logger.warning("Error writing to database" + str(e) + source)
else:
self.logger.warning("NO record found from: %s" % source)
stop = time.time()
storage_time = str(stop - start) + "秒"
self.logger.info("dataplane 共收集{0}条数据， 新数据{1}条".format(all_count, avail_count))
self.logger.info("dataplane 抓取时间{0}，数据遍历时间{1}".format(crawl_time, storage_time))
class CrawlMalwaredomainlist(Task):
def __init__(self):
super().__init__('dshield 数据爬取')
self.logger = ContextLogger('threat_domain')
def run_crawl(self):
start = time.time()
domains = []
urls = [
'https://secure.dshield.org/feeds/suspiciousdomains_High.txt',
'https://secure.dshield.org/feeds/suspiciousdomains_Medium.txt',
'https://secure.dshield.org/feeds/suspiciousdomains_Low.txt'
]
source = 'secure.dshield.org'
for url in urls:
obj = urlparse(url)
description = obj.path.split('/')[-1].split('.')[0]
_info = self.get(url=url)
if _info is None:
self.logger.warning("request returned None " + source)
return None
info = _info.split('\n')
for domain in info:
if domain.startswith('#'): continue
if domain == 'Site': continue
block = [domain, source, description]
domains.append(block)
stop = time.time()
crawl_time = str(stop - start) + "秒"
self.save_info(domains, source, crawl_time)
def save_info(self, domains, source, crawl_time):
start = time.time()
all_count = len(domains)
avail_count = 0
_time = datetime.now().strftime("%Y-%m-%d")
if len(domains) > 0:
try:
for domain, source, description in domains:
flag = db.session.query(Domain).filter(
Domain.domain == domain,
Domain.source == source).first()
if flag is None:
new_domain = Domain()
new_domain.domain = domain
new_domain.source = source
new_domain.description = description
db.session.add(new_domain)
avail_count += 1
else:
flag.updatetime = _time
db.session.add(flag)
db.session.commit()
except Exception as e:
self.logger.warning("Error writing to database" + str(e) +
source)
else:
self.logger.warning("NO record found from: %s" % source)
stop = time.time()
storage_time = str(stop - start) + "秒"
self.logger.info("dshield 共收集{0}条数据， 新数据{1}条".format(
all_count, avail_count))
self.logger.info("dshield 抓取时间{0}，数据遍历时间{1}".format(
crawl_time, storage_time))
class CrawlNetlab(Task):
def __init__(self):
super().__init__('netlab 数据爬取')
self.logger = ContextLogger('threat_domain')
def run_crawl(self):
start = time.time()
domains = []
url = 'http://data.netlab.360.com/feeds/dga/dga.txt'
# url='http://67.209.191.170:81/1.txt'
source = 'data.netlab.360.com'
_info = self.get(url=url)
if _info is None:
self.logger.warning("request returned None " + source)
return None
info = _info.split('\n')
for _domain in info:
if _domain.startswith('#'): continue
if _domain == '': continue
domain = _domain.split()[1]
description = _domain.split()[0]
updatetime = _domain.split()[2]
block = [domain, updatetime, description, source]
domains.append(block)
stop = time.time()
crawl_time = str(stop - start) + "秒"
self.save_info(domains, source, crawl_time)
def save_info(self, domains, source, crawl_time):
start = time.time()
all_count = len(domains)
avail_count = 0
if len(domains) > 0:
try:
for domain, updatetime, description, source in domains:
flag = db.session.query(Domain).filter(
Domain.domain == domain,
Domain.source == source).first()
if flag is None:
new_domain = Domain()
new_domain.domain = domain
new_domain.updatetime = updatetime
new_domain.description = description
new_domain.source = source
db.session.add(new_domain)
avail_count += 1
else:
flag.updatetime = updatetime
db.session.add(flag)
db.session.commit()
except Exception as e:
self.logger.warning("Error writing to database" + str(e) +
source)
else:
self.logger.warning("NO record found from: %s" % source)
stop = time.time()
storage_time = str(stop - start) + "秒"
self.logger.info("netlab 共收集{0}条数据， 新数据{1}条".format(
all_count, avail_count))
self.logger.info("netlab 抓取时间{0}，数据遍历时间{1}".format(
crawl_time, storage_time))
class CrawlAlienvault(Task):
def __init__(self):
super().__init__('alienvault 数据爬取')
self.logger = ContextLogger('threat_ip')
def run_crawl(self):
start = time.time()
ips = []
url = 'https://reputation.alienvault.com/reputation.generic'
source = 'reputation.alienvault.com'
_info = self.get(url=url)
if _info is None:
self.logger.warning("request returned None " + source)
return None
info = _info.split('\n')
for _ip in info:
if _ip.startswith('#'): continue
if _ip == '': continue
ip = re.findall(r'[0-9]+(?:\.[0-9]+){3}', _ip)[0]
des = re.findall(r'# (.*?)(([A-Z]{2})|(\s)?),', _ip)
description = des[0][0]
area = des[0][1] + ',' + re.findall(r',(.*?),', _ip)[0]
block = [ip, description, area, source]
ips.append(block)
stop = time.time()
crawl_time = str(stop - start) + "秒"
self.save_info(ips, source, crawl_time)
def save_info(self, ips, source, crawl_time):
start = time.time()
all_count = len(ips)
avail_count = 0
_time = datetime.now().strftime("%Y-%m-%d")
if len(ips) > 0:
try:
for ip, description, area, source in ips:
flag = db.session.query(IP).filter(
IP.ip == ip, IP.source == source).first()
if flag is None:
new_ip = IP()
new_ip.ip = ip
new_ip.description = description
new_ip.area = area
new_ip.source = source
db.session.add(new_ip)
avail_count += 1
else:
flag.updatetime = _time
db.session.add(flag)
db.session.commit()
except Exception as e:
self.logger.warning("Error writing to database" + str(e) +
source)
else:
self.logger.warning("NO record found from: %s" % source)
stop = time.time()
storage_time = str(stop - start) + "秒"
self.logger.info("alienvault 共收集{0}条数据， 新数据{1}条".format(
all_count, avail_count))
self.logger.info("alienvault 抓取时间{0}，数据遍历时间{1}".format(
crawl_time, storage_time))
class CrawlRulez(Task):
def __init__(self):
super().__init__('rulez 数据爬取')
self.logger = ContextLogger('threat_ip')
def run_crawl(self):
start = time.time()
ips = []
url = 'http://danger.rulez.sk/projects/bruteforceblocker/blist.php'
source = 'danger.rulez.sk'
_info = self.get(url=url)
if _info is None:
self.logger.warning("request returned None " + source)
return None
info = _info.split('\n')
for _ip in info:
if _ip.startswith('#'): continue
if _ip == '': continue
ip = _ip.split('#')[0].strip()
updatetime = _ip.split('#')[1].strip().split()[0].strip()
block = [ip, updatetime, source]
ips.append(block)
stop = time.time()
crawl_time = str(stop - start) + "秒"
self.save_info(ips, source, crawl_time)
def save_info(self, ips, source, crawl_time):
start = time.time()
all_count = len(ips)
avail_count = 0
if len(ips) > 0:
try:
for ip, updatetime, source in ips:
flag = db.session.query(IP).filter(
IP.ip == ip, IP.source == source).first()
if flag is None:
new_ip = IP()
new_ip.ip = ip
new_ip.updatetime = updatetime
new_ip.source = source
db.session.add(new_ip)
avail_count += 1
else:
flag.updatetime = updatetime
db.session.add(flag)
db.session.commit()
except Exception as e:
self.logger.warning("Error writing to database" + str(e) +
source)
else:
self.logger.warning("NO record found from: %s" % source)
stop = time.time()
storage_time = str(stop - start) + "秒"
self.logger.info("rulez 共收集{0}条数据， 新数据{1}条".format(
all_count, avail_count))
self.logger.info("rulez 抓取时间{0}，数据遍历时间{1}".format(
crawl_time, storage_time))
class CrawlCybercrime(Task):
def __init__(self):
super().__init__('cybercrime 数据爬取')
self.logger = ContextLogger('threat_domain')
def run_crawl(self):
start = time.time()
domains = []
url = 'http://cybercrime-tracker.net/ccam.php'
source = 'cybercrime-tracker.net'
_info = self.get(url=url)
if _info is None:
self.logger.warning("request returned None " + source)
return None
soup = BeautifulSoup(_info, 'lxml')
table = soup.findChildren('tbody')[2]
rows = table.findChildren('tr', attrs={'class': 'monitoring'})
for row in rows:
date_str = row.findChildren('td')[1].string
time_obj = time.strptime(date_str, "%d/%m/%Y %H:%M:%S")
updatetime = time.strftime("%Y-%m-%d", time_obj)
domain = row.findChildren('td')[2].string
hashstr = row.findChildren('td')[3].string
if self.is_ip(domain): continue
block = [domain, updatetime, source]
domains.append(block)
stop = time.time()
crawl_time = str(stop - start) + "秒"
self.save_info(domains, source, crawl_time)
def save_info(self, domains, source, crawl_time):
start = time.time()
all_count = len(domains)
avail_count = 0
if len(domains) > 0:
try:
for domain, updatetime, source in domains:
flag = db.session.query(Domain).filter(
Domain.domain == domain,
Domain.source == source).first()
if flag is None:
new_domain = Domain()
new_domain.domain = domain
new_domain.updatetime = updatetime
new_domain.source = source
db.session.add(new_domain)
avail_count += 1
else:
flag.updatetime = updatetime
db.session.add(flag)
db.session.commit()
except Exception as e:
self.logger.warning("Error writing to database" + str(e) +
source)
else:
self.logger.warning("NO record found from: %s" % source)
stop = time.time()
storage_time = str(stop - start) + "秒"
self.logger.info("cybercrime 共收集{0}条数据， 新数据{1}条".format(
all_count, avail_count))
self.logger.info("cybercrime 抓取时间{0}，数据遍历时间{1}".format(
crawl_time, storage_time))
