def get_domain_info(domain):
if is_domain(domain):
url = 'http://searchdns.netcraft.com/?restriction=site+contains&host={0}&lookup=wait..&position=limited'\
.format(domain)
try:
headers = {
'User-Agent':
"Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:47.0) Gecko/20100101 Firefox/47.0"
}
result = requests.get(url, headers=headers).text
bs = BeautifulSoup(result, 'html.parser')
content = bs.find('div', id="content")
if content is not None:
rule = re.compile('(\/\?host=)')
finally_result = rule.sub(
'http://searchdns.netcraft.com/?host=', content.prettify())
script_path = os.path.abspath(
os.path.dirname(os.path.dirname(__file__)))
finally_path = os.path.join(
script_path, 'output/{0}'.format("subdoamin.html"))
sty = '<head><meta charset="UTF-8"><link href="../static/subdomain.css" rel="stylesheet" ' \
'type="text/css" /></head>'
out_page(finally_path, sty, finally_result)
except Exception as e:
print(e)
def get_sub_info(domain):
session = requests.session()
if is_domain(domain):
url = 'http://i.links.cn/subdomain/'
new_value = []
try:
payload = {'b2': 1, 'b3': 1, 'b4': 1, 'domain': domain}
result = session.post(url, data=payload,
headers=config.headers).text
bs = BeautifulSoup(result, 'html.parser')
content = bs.find_all('a', attrs={'rel': "nofollow"})
if content is not None:
for i in content:
if i.text:
new_value.append(i.text)
f = xlwt.Workbook(encoding='utf-8', style_compression=0)
sheet = f.add_sheet('sub', cell_overwrite_ok=True)
script_path = os.path.abspath(
os.path.dirname(os.path.dirname(__file__)))
finally_path = os.path.join(script_path,
'output/{0}'.format("subdomain.xls"))
if len(new_value) != 0:
for index, item in enumerate(new_value):
sheet.write(index, 0, item)
f.save(finally_path)
except Exception as e:
print(e)
def get_rebots_info(domain):
if is_domain(domain):
try:
finally_url = "http://" + domain + '/robots.txt'
result = http_get(finally_url)
return result
# script_path = os.path.abspath(os.path.dirname(os.path.dirname(__file__)))
# finally_path = os.path.join(script_path, 'output/{0}'.format("robots.txt"))
# if result:
# with open(finally_path, 'wb') as f:
# f.write(result.encode('utf-8'))
except Exception as e:
# print(e)
return "robots not find"
def dns(domain):
if is_domain(domain):
url = 'https://who.is/dns/{0}'.format(domain)
try:
result = http_get(url)
bs = BeautifulSoup(result, 'html.parser')
content = bs.find('table')
script_path = os.path.abspath(
os.path.dirname(os.path.dirname(__file__)))
finally_path = os.path.join(script_path,
'output/{0}'.format("dns.html"))
sty = '<head><meta charset="UTF-8"><link href="../static/Bootstrap.css" rel="stylesheet" ' \
'type="text/css" /><link href="../static/main.css" rel="stylesheet" type="text/css" /></head>'
out_page(finally_path, sty, content)
except Exception as e:
print(e)
def get_who_is_page(domain):
if is_domain(domain):
url = "http://whois.chinaz.com/{0}".format(domain)
payload = {'DomainName': domain}
try:
content = http_post(url, payload)
bs = BeautifulSoup(content, 'html.parser')
ul = bs.find('ul', class_="WhoisLeft")
if ul is not None:
script_path = os.path.abspath(
os.path.dirname(os.path.dirname(__file__)))
finally_path = os.path.join(
script_path,
'..\\templates\\output\\{0}'.format("whois2.html"))
sty = '<head><meta charset="UTF-8"> <link rel="stylesheet" href="../../static/css/whois.css"> ' \
'<link rel="stylesheet" href="../../static/css/whois_base.css"></head>'
out_page(finally_path, sty, ul.prettify())
except Exception as e:
print(e)
def get_who_page(domain):
if is_domain(domain):
url = "https://who.is/whois/{0}".format(domain)
try:
web_content = http_get(url)
bs = BeautifulSoup(web_content, "html.parser")
result = bs.find("div", class_="col-md-8")
rule = re.compile('(\/tools\/)')
finally_result = rule.sub('https://who.is//tools/',
result.prettify())
script_path = os.path.abspath(
os.path.dirname(os.path.dirname(__file__)))
finally_path = os.path.join(script_path,
'output/{0}'.format("whois1.html"))
sty = '<head><meta charset="UTF-8"><link href="../static/Bootstrap.css" rel="stylesheet" ' \
'type="text/css" /><link href="../static/main.css" rel="stylesheet" type="text/css" /></head>'
out_page(finally_path, sty, finally_result)
except Exception as e:
print(e)