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 BaseReq:
def __init__(self, is_crawl=True):
self.ses = db.session
self.is_crawl = is_crawl
self.logger = ContextLogger('crawl')
def _request(self, url, method='post', timeout=20, retry=5, **kwargs):
if kwargs.get('headers'):
headers = kwargs['headers']
else:
headers = {}
if kwargs.get('cookies'):
cookies = kwargs['cookies']
else:
cookies = {}
try:
resp = requests.request(method,
'{}'.format(url),
timeout=timeout,
headers=headers,
cookies=cookies,
**kwargs)
except Exception as e:
self.logger.warning(e)
if retry > 0:
return self._request(url,
method,
timeout,
retry=retry - 1,
**kwargs)
else:
return None
if resp.status_code != 200 and retry > 0:
return self._request(url,
method,
timeout,
retry=retry - 1,
**kwargs)
if self.is_crawl:
return resp.text
else:
try:
data = resp.json()
except Exception as e:
self.logger.warning(e)
data = None
return data
def get(self, url, **kwargs):
return self._request(url, method='get', **kwargs)
def post(self, url, **kwargs):
return self._request(url, method='post', **kwargs)
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 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 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 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 BaseReq:
def __init__(self, is_crawl=True):
self.ses = db.session
self.is_crawl = is_crawl
self.logger = ContextLogger('crawl')
self.headers = {
'Host': 'www.lagou.com',
'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': 'https://www.lagou.com/jobs/list_Python?px=new&city=%E5%85%A8%E5%9B%BD',
'Connection': 'keep-alive',
'Cache-Control': 'max-age=0',
'Content-Type': 'multipart/form-data'
}
def _request(self, url, method='post', timeout=20, retry=5, **kwargs):
if kwargs.get('cookies'):
cookies = kwargs['cookies']
else:
cookies = {}
try:
resp = requests.request(method, '{}'.format(url), timeout=timeout, headers=self.headers,
cookies=cookies, **kwargs)
except Exception as e:
if retry > 0:
return self._request(url, method, timeout, retry=retry-1, **kwargs)
else:
self.logger.warning('请求失败', e)
return None
if resp.status_code != 200 and retry > 0:
return self._request(url, method, timeout, retry=retry-1, **kwargs)
if self.is_crawl:
return resp.text
else:
try:
data = resp.json()
if (data['success'] is False or data is None) and retry > 0:
time.sleep(3)
return self._request(url, method, timeout, retry=retry - 1, **kwargs)
except Exception as e:
if retry > 0:
return self._request(url, method, timeout, retry=retry - 1, **kwargs)
else:
self.logger.warning('解析失败', e)
self.logger.warning(url)
data = None
return data
def get(self, url, **kwargs):
return self._request(url, method='get', **kwargs)
def post(self, url, **kwargs):
return self._request(url, method='post', **kwargs)
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 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 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 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 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 CrawlCnnvd(Task):
def __init__(self):
super().__init__('douban数据爬取')
self.logger = ContextLogger('douban')
def run_crawl(self):
begin_base_url = 'https://book.douban.com/tag/'
middle_base_url = '?start='
end_base_url = '&type=S'
for tag in tag_list:
start = 0
while True:
page_url = begin_base_url + tag + middle_base_url + str(
start) + end_base_url
print(page_url)
html = self.get(page_url)
start += 20
if html:
result = self.handle_list_html(html, tag)
if result:
break
def handle_list_html(self, html, tag):
soup = BeautifulSoup(html, 'lxml')
items = soup.find_all(class_='subject-item')
if not items:
return True
href_list = []
for item in items:
href = item.div.a['href']
href_list.append(href)
for href in href_list:
html = self.get(href)
if html:
result = self.handle_info_html(html, tag)
if result:
continue
return False
def handle_info_html(self, html, type_tag):
soup = BeautifulSoup(html, 'lxml')
book = Book()
# type_id = db.session.query(Type).filter_by(title=tag).first().id
try:
title = soup.h1.span.get_text()
info = soup.find(class_='article').find(class_='indent').find(
class_='subjectwrap clearfix').find(
class_='subject clearfix').find(id='info')
string = info.get_text().strip()
string = string.replace(' ', '')
string = string.replace(' ', '')
string = string.replace('\n', '')
tag_list = [
'出版社:', '出品方:', '副标题:', '原作名:', '译者:', '出版年:', '页数:', '定价:',
'装帧:', '丛书:', 'ISBN:'
]
value_list = []
if '作者:' in string:
string = string.replace('作者:', '')
flag = 0
for tag in tag_list:
if tag in string:
value = string.split(tag)[0]
value_list.append(value)
if flag != 0:
for i in range(flag):
value_list.append('')
flag = 0
else:
flag += 1
continue
string = string.split(tag)[1]
if tag == 'ISBN:':
value_list.append(string)
author = value_list[0]
publisher = value_list[1]
producer = value_list[2]
subtitle = value_list[3]
original_title = value_list[4]
translator = value_list[5]
year_of_publisher = value_list[6]
pages = value_list[7]
price = value_list[8]
binding = value_list[9]
series = value_list[10]
isbn = value_list[11]
pic_href = soup.find(class_='article').find(class_='indent').find(
class_='subjectwrap clearfix').find(
class_='subject clearfix').find(id='mainpic').a['href']
score = soup.find(
class_='rating_self clearfix').strong.get_text().strip()
score_people = soup.find(class_='rating_people').get_text()
related_info = soup.find(class_='related_info')
infos = related_info.find_all(class_='indent')[:2]
content_info = str(infos[0].find(class_='intro')).replace(
'<div class="intro">', '')
author_info = str(infos[1].find(class_='intro')).replace(
'<div class="intro">', '')
book.title = title
book.author = author
book.publisher = publisher
book.producer = producer
book.translator = translator
book.subtitle = subtitle
book.original_title = original_title
book.year_of_publisher = year_of_publisher
book.pages = pages
book.price = price
book.binding = binding
book.series = series
book.isbn = isbn
book.score = score
book.score_people = score_people
book.type = type_tag
book.content_info = content_info
book.author_info = author_info
book.pic_href = pic_href
self.safe_commit(book)
except Exception as e:
self.logger.warning('爬起失败', e)
return True
return False
class CrawlCnnvd(Task):
def __init__(self):
super().__init__('cnnvd数据爬取')
self.logger = ContextLogger('task_cnnvd')
def get_api_id(self, cnnvd_str):
str_1, str_2, str_3 = cnnvd_str.split('-')
if len(str_3) == 3:
return str_2 + '0' + str_3
return str_2 + str_3
def api_affect_product(self, id, name_str):
data = {'cvCveid': id, 'counts': 5}
json_datas = self.post('http://www.cnnvd.org.cn/web/xxk/getEntity.tag',
data=data)
if json_datas == '' or json_datas is None:
return name_str
else:
json_datas = json.loads(json_datas)
for json_data in json_datas:
name_str = name_str + json_data['cpr_product_name'] + ';'
return name_str
def api_patchs(self, id, patch_dict):
data = {'cvCveid': id, 'counts': 5}
json_datas = self.post('http://www.cnnvd.org.cn/web/xxk/getEntity.tag',
data=data)
if json_datas == '' or json_datas is None:
return patch_dict
else:
json_datas = json.loads(json_datas)
for json_data in json_datas:
patch_name = json_data['cp_cname']
patch_url = 'http://www.cnnvd.org.cn' + '/web/xxk/bdxqById.tag?id=' + str(
json_data['cp_id'])
patch_dict[patch_name] = patch_url
return patch_dict
def run_crawl(self):
begin_base_url = 'http://www.cnnvd.org.cn' + '/web/vulnerability/querylist.tag?pageno='
end_base_url = '&repairLd='
index = 1
while index < 10597:
next_page = begin_base_url + str(index) + end_base_url
print(next_page)
html = self.get_one_page(next_page)
if html:
result = self.handle_list_html(html)
if result:
break
index += 1
def handle_list_html(self, html):
soup = BeautifulSoup(html, 'lxml')
for url in soup.find(class_='list_list').ul.find_all('li'):
vul_url = 'http://www.cnnvd.org.cn' + url.div.a['href']
html = self.get_one_page(vul_url)
if html:
result = self.handle_info_html(html, vul_url)
if result:
return result
return False
def handle_info_html(self, html, url):
soup = BeautifulSoup(html, 'lxml')
try:
simple_list = []
title = soup.find(
class_="detail_xq w770").find('h2').get_text().strip()
cnnvd_id = soup.find(class_="detail_xq w770").find('ul').find_all(
'li')[0].span.get_text().strip().split('：')[1]
for li in soup.find(
class_="detail_xq w770").find('ul').find_all('li')[1:]:
if li.a:
simple_list.append(li.a.get_text().strip())
# 如果时间超过一个月， 返回True，暂停爬取
if simple_list[5] < end_time:
return True
vulner_source = soup.find(class_="detail_xq w770").find(
'ul').find_all('li')[-1].span.get_text().strip().split('：')[1]
list = []
for div in soup.find(class_="fl w770").find_all(class_='d_ldjj'):
str_value = ''
for p in div.find_all('p'):
str_value += p.get_text().strip()
list.append(str_value)
if list[3] != '暂无':
str_value = ''
affect_products = soup.find(class_="fl w770").find_all(
class_='d_ldjj')[3].find_all(class_='a_title2')
for i in affect_products:
str_value += i.get_text().strip() + ';'
if len(affect_products) == 5:
str_value = self.api_affect_product(
self.get_api_id(cnnvd_id), str_value)
list[3] = str_value
if list[4] != '暂无':
patch_dict = {}
patchs = soup.find(class_="fl w770").find_all(
class_='d_ldjj')[4].find_all(class_='a_title2')
for i in patchs:
name = i.get_text().strip()
patch_url = 'http://www.cnnvd.org.cn' + i['href']
patch_dict[name] = patch_url
if len(patchs) == 5:
patch_dict = self.api_patchs(self.get_api_id(cnnvd_id),
patch_dict)
list[4] = patch_dict
except Exception as e:
self.logger.warning(url + '--' + str(e))
return False
vul = db.session.query(Vulner).filter_by(cnnvd_id=cnnvd_id).first()
if vul:
print("查询成功")
else:
print("新数据")
vul = Vulner()
vul.title = title
vul.vulner_source = vulner_source
vul.cnnvd_id = cnnvd_id
vul.url = url
vul.level = simple_list[0]
vul.cve_id = simple_list[1]
vul.vulner_type = simple_list[2]
vul.posted_time = simple_list[3]
vul.threats_type = simple_list[4]
vul.update_time = simple_list[5]
vul.describe = list[0]
vul.source = 'cnnvd'
vul.solve_way = list[1]
vul.refer_link = list[2]
vul.affect_product = list[3]
vul.patch = list[4]
print(vul.title, '\n', vul.update_time, '\n', vul.cve_id, '\n',
vul.url, '\n\n')
self.safe_commit(vul)
return False
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 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 CrawlHackernews(Task):
def __init__(self):
super().__init__('hackernews数据爬取')
self.logger = ContextLogger('task_hackernews')
def run_crawl(self):
base_url = 'http://hackernews.cc/page/'
index = 1
while index < 275:
next_page = base_url + str(index)
html = self.get_one_page(next_page)
if html:
result = self.handle_list_html(html)
if result:
break
index += 1
def handle_list_html(self, html):
soup = BeautifulSoup(html, 'lxml')
for article in soup.find(class_="classic-lists clearfix").find_all(
id='article'):
article_url = article.find(class_="classic-list-left").a['href']
html = self.get_one_page(article_url)
if html:
result = self.handle_info_html(html, article_url)
if result:
return result
return False
def handle_info_html(self, html, url):
soup = BeautifulSoup(html, 'lxml')
try:
info_url = db.session.query(Infomation).filter_by(url=url).first()
if info_url:
return True
title = soup.find(class_="post-details-right").find(
class_="single-title").get_text().strip()
posted_time = soup.find(class_="post-details-right").find(
class_="light-post-meta").find_all('a')[1].get_text().strip()
author = soup.find(class_="post-details-right").find(
class_="light-post-meta").find_all('a')[0].get_text().strip()
summary = soup.find(
class_="post-body clearfix").find('p').get_text().strip()
source = 'HackerNews'
keys = ''
for category in soup.find(class_="post-details-right").find(
class_="light-post-meta").find(
class_="post-category").find_all('a'):
keys = keys + category.get_text().strip() + ';'
except Exception as e:
self.logger.warning(url + ' ' + str(e))
return False
info = Infomation()
info.source = source
info.summary = summary
info.keys = keys
info.author = author
info.posted_time = posted_time
info.title = title
info.url = url
print(info.title, '\n', info.author, '\n', info.posted_time, '\n',
info.url, '\n', info.keys, '\n', info.source, '\n', info.summary,
'\n')
self.safe_commit(info)
return False
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 CrawlFreebuf(Task):
def __init__(self):
super().__init__('LaGou数据爬取')
self.logger = ContextLogger('task_lagou')
self.is_crawl = False
self.headers = {
'Host': 'www.lagou.com',
'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':
'https://www.lagou.com/jobs/list_Python?px=new&city=%E5%85%A8%E5%9B%BD',
'Connection': 'keep-alive',
'Cookie':
'user_trace_token=20171103191801-9206e24f-9ca2-40ab-95a3-23947c0b972a; _ga=GA1.2.545192972.1509707889; LGUID=20171103191805-a9838dac-c088-11e7-9704-5254005c3644; JSESSIONID=ABAAABAACDBABJB2EE720304E451B2CEFA1723CE83F19CC; _gat=1; LGSID=20171228225143-9edb51dd-ebde-11e7-b670-525400f775ce; PRE_UTM=; PRE_HOST=www.baidu.com; PRE_SITE=https%3A%2F%2Fwww.baidu.com%2Flink%3Furl%3DKkJPgBHAnny1nUKaLpx2oDfUXv9ItIF3kBAWM2-fDNu%26ck%3D3065.1.126.376.140.374.139.129%26shh%3Dwww.baidu.com%26sht%3Dmonline_3_dg%26wd%3D%26eqid%3Db0ec59d100013c7f000000055a4504f6; PRE_LAND=https%3A%2F%2Fwww.lagou.com%2F; LGRID=20171228225224-b6cc7abd-ebde-11e7-9f67-5254005c3644; index_location_city=%E5%85%A8%E5%9B%BD; TG-TRACK-CODE=index_search; SEARCH_ID=3ec21cea985a4a5fa2ab279d868560c8',
'X-Requested-With': 'XMLHttpRequest',
'X-Anit-Forge-Token': 'None',
'X-Anit-Forge-Code': '0',
'Pragma': 'no-cache',
'Cache-Control': 'no-cache',
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
}
def process(self, page, tag):
base_url = 'https://www.lagou.com/jobs/positionAjax.json?'
params = {
'px': 'new',
'needAddtionalResult': 'false',
'isSchoolJob': '0'
}
data = {'first': 'false', 'pn': str(page), 'kd': tag}
html = self.post(base_url, data=data, params=params)
if html:
try:
count = int(html['content']['positionResult']['resultSize'])
job_list = html['content']['positionResult']['result']
if count == 0:
return True
for job in job_list:
self.storage(job, tag)
except Exception as e:
self.logger.warning('取值失败', e)
self.logger.warning(base_url)
def storage(self, job_dict, tag):
for key in job_dict:
job_dict[key] = self.switch_str(job_dict[key])
job = Job()
try:
job.companyId = job_dict['companyId']
job.positionName = job_dict['positionName']
job.workYear = job_dict['workYear']
job.education = job_dict['education']
job.jobNature = job_dict['jobNature']
job.companyLogo = job_dict['companyLogo']
job.salary = job_dict['salary']
job.city = job_dict['city']
job.financeStage = job_dict['financeStage']
job.industryField = job_dict['industryField']
job.positionId = job_dict['positionId']
job.approve = job_dict['approve']
job.createTime = job_dict['createTime']
job.positionAdvantage = job_dict['positionAdvantage']
job.companySize = job_dict['companySize']
job.companyLabelList = job_dict['companyLabelList']
job.publisherId = job_dict['publisherId']
job.score = job_dict['score']
job.district = job_dict['district']
job.companyShortName = job_dict['companyShortName']
job.positionLables = job_dict['positionLables']
job.industryLables = job_dict['industryLables']
job.businessZones = job_dict['businessZones']
job.longitude = job_dict['longitude']
job.latitude = job_dict['latitude']
job.adWord = job_dict['adWord']
job.formatCreateTime = job_dict['formatCreateTime']
job.hitags = job_dict['hitags']
job.resumeProcessRate = job_dict['resumeProcessRate']
job.resumeProcessDay = job_dict['resumeProcessDay']
job.companyFullName = job_dict['companyFullName']
job.imState = job_dict['imState']
job.lastLogin = job_dict['lastLogin']
job.explain = job_dict['explain']
job.plus = job_dict['plus']
job.pcShow = job_dict['pcShow']
job.appShow = job_dict['appShow']
job.deliver = job_dict['deliver']
job.gradeDescription = job_dict['gradeDescription']
job.promotionScoreExplain = job_dict['promotionScoreExplain']
job.firstType = job_dict['firstType']
job.secondType = job_dict['secondType']
job.isSchoolJob = job_dict['isSchoolJob']
job.subwayline = job_dict['subwayline']
job.stationname = job_dict['stationname']
job.linestaion = job_dict['linestaion']
job.job_type = tag
except Exception as e:
self.logger.warning('存储失败', e)
self.logger.warning(job_dict['publisherId'])
self.safe_commit(job)
def switch_str(self, value_list):
value_str = ''
try:
if type(value_list) != list:
return str(value_list)
for value in value_list:
value_str = value_str + value + ';'
except Exception as e:
self.logger.warning('转化失败', e)
return value_str
def control(self):
tag_list = []
with open(FILE_PATH, 'r') as f:
for line in f:
tag_list.append(line.strip())
for tag in tag_list:
page = 1
while (True):
result = self.process(page, tag)
if result:
break
print("当前页数{}".format(page))
page += 1
self.logger.warning(tag + '共发起了' + str(page) + '请求')
class CrawlZJ(Task):
def __init__(self):
super().__init__('智联招聘数据爬取')
self.logger = ContextLogger('task_zhilian')
def run_crawl(self):
tag_list = []
with open(FILE_PATH, 'r') as f:
for line in f:
tag_list.append(line.strip().lower())
for tag in tag_list:
base_url1 = 'http://sou.zhaopin.com/jobs/searchresult.ashx?jl=%E5%85%A8%E5%9B%BD&kw="'
base_url2 = '&sb=1&sm=0&isfilter=0&fl=489&isadv=0&sg=0e48987408d24799b14e9053dd9a00c7&p='
index = 1
while index < 91:
next_page = base_url1 + tag + base_url2 + str(index)
html = self.get_one_page(next_page)
if html:
result = self.handle_list_html(html, tag)
if result:
break
index += 1
def handle_list_html(self, html, tag):
soup = BeautifulSoup(html, 'lxml')
try:
list_content = soup.find(
class_="newlist_list_content").find_all("table")
except Exception as e:
self.logger.warning(e)
return False
for i, table in enumerate(list_content):
if i == 0:
continue
try:
position_url = table.tr.td.div.a['href']
position_name = table.tr.td.div.a.get_text().strip()
except Exception as e:
self.logger.warning(e)
return False
if tag not in position_name.lower():
return True
html = self.get_one_page(position_url)
if html:
result = self.handle_info_html(html, position_url, tag)
if result:
return result
return False
def handle_info_html(self, html, url, tag):
soup = BeautifulSoup(html, 'lxml')
try:
url = url
positionName = soup.find(
class_="inner-left fl").h1.get_text().strip()
companyFullName = soup.find(
class_="inner-left fl").h2.get_text().strip()
companyLabelList = ''
for i in soup.find(class_="inner-left fl").div.find_all('span'):
companyLabelList = companyLabelList + i.get_text().strip(
) + ';'
list_attr = []
for i in soup.find(class_="terminalpage-left").find(
class_='terminal-ul clearfix').find_all('li'):
list_attr.append(i.strong.get_text().strip())
except Exception as e:
self.logger.warning(url + ' ' + str(e))
return False
job = ZlJob()
job.url = url
job.positionName = positionName
job.companyFullName = companyFullName
job.companyLabelList = companyLabelList
job.salary = list_attr[0]
job.city = list_attr[1]
job.createTime = list_attr[2]
job.jobNature = list_attr[3]
job.workYear = list_attr[4]
job.education = list_attr[5]
job.positionCount = list_attr[6]
job.firstType = list_attr[7]
job.job_type = tag
self.safe_commit(job)
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 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))
class CrawlFreebuf(Task):
def __init__(self):
super().__init__('freebuf数据爬取')
self.logger = ContextLogger('task_freebuf')
def run_crawl(self):
base_url = 'http://www.freebuf.com/news/page/'
index = 1
while index < 290:
next_page = base_url + str(index)
html = self.get_one_page(next_page)
if html:
result = self.handle_list_html(html)
if result:
break
index += 1
def handle_list_html(self, html):
soup = BeautifulSoup(html, 'lxml')
for tag_div in soup.find_all("div", class_="news-img"):
article_url = tag_div.a['href']
print(article_url)
html = self.get_one_page(article_url)
if html:
result = self.handle_info_html(html, article_url)
if result:
return result
return False
def handle_info_html(self, html, url):
print(url)
soup = BeautifulSoup(html, 'lxml')
try:
url = url
info_url = db.session.query(Infomation).filter_by(url=url).first()
if info_url:
print("已经存在")
return True
posted_time = soup.find(class_="property").find(
class_="time").get_text().strip()
title = soup.find(class_="articlecontent").find(
class_="title").h2.get_text().strip()
author = soup.find(class_="property").find(
rel="author").get_text().strip()
keys_list = soup.find(class_="property").find(
class_="tags").find_all('a')
key_str = ''
for key in keys_list:
key_str = key_str + key.get_text().strip() + ';'
summary = ''
for p_string in soup.find(id="contenttxt").find_all(
style=re.compile("color: rgb\(0, 176, 80\);*$")):
if p_string.get_text() is None:
continue
summary += p_string.get_text().strip()
if summary == '':
summary = soup.find(
id="contenttxt").find('p').get_text().strip()
except Exception as e:
self.logger.warning(url + ' ' + str(e))
return False
info = Infomation()
info.title = title
info.url = url
info.posted_time = posted_time
info.author = author
info.summary = summary
info.source = 'Freebuf'
info.keys = key_str
print(info.title, info.author, info.posted_time, info.url, key_str)
self.safe_commit(info)
return False
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))
