MasonLiu/PyBot
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 4 Wiki Activity

大型更新优化

Browse Source
This commit is contained in:
MasonLiu 2025-01-22 14:03:36 +08:00
parent 71cc3b4d22
commit fd7a51f24b
29 changed files with 3752 additions and 4185 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

167
Core.py
View File

@ -58,103 +58,130 @@ webhook_url_once, timestamp_once, sign_once = gen_sign()
e_hour, time_choice, choice, fs_activate, wx_activate, ding_activate, lx_activate, url_web = get_core_config()
def check_avaliable(info_long, info_short, title, webhook_url, timestamp, sign):
def check_avaliable(info_long, info_short, title):
if info_long: # 发送完整文章相关内容
# logger.info(f"{title} 递送中（飞书）：")
result = SendToFeishu(info_long, title, webhook_url, timestamp, sign)
logger.info(result)
time.sleep(15)
else:
pass
if fs_activate == "True":
# logger.info(f"{title} 递送中（飞书）：")
webhook_url, timestamp, sign = gen_sign()
result = SendToFeishu(info_long, title, webhook_url, timestamp, sign)
logger.info(result)
time.sleep(15)
if info_short: # 发送精简文章相关内容
# 企业微信相关
if wx_activate == "True":
# logger.info(f"{title} 递送中（企业微信）：")
result = SendToWX(info_short, title)
logger.info(result)
for info in info_short:
result = SendToWX(info, title)
logger.info(result)
time.sleep(15)
else:
pass
# 钉钉相关
if ding_activate == "True":
# logger.info(f"{title} 递送中（钉钉）：")
# result = SendToWX(info_short, title) # 待完善
logger.info(result)
# for info in info_short: # 开发中，暂未实现
# result = SendToDD(info, title)
# logger.info(result)
time.sleep(15)
else:
pass
if not info_long and not info_short:
logger.info(f"{title}数据为空，跳过执行。")
def send_job_RSS(time_1):
Doonsec_switch, Doonsec = get_kewords_config('Doonsec')
# print(f"当前配置信息：Doonsec_switch：{Doonsec_switch}")
# 爬取数据
seebug_main()
anquanke_main()
huawei_main()
doonsec_main()
qianxin_main()
freebuf_main()
xianzhi_main()
M_4hou_main()
# 分析各个数据源的结果（输出长结果）
result_4hou_long = Src_4hou(time_1, False)
result_anquanke_long = Src_anquanke(time_1, False)
result_doonsec_long = Src_doonsec(False, Doonsec_switch, Doonsec)
# print(result_doonsec_long)
result_xianzhi_long = Src_xianzhi(time_1, False)
result_freebuf_long = Src_freebuf(time_1, False)
result_qianxin_long = Src_qianxin(time_1, False)
result_seebug_long = Src_seebug(time_1, False)
# 分析各个数据源的结果（输出短结果）
result_4hou_short = Src_4hou(time_1, True)
result_anquanke_short = Src_anquanke(time_1, True)
result_doonsec_short = Src_doonsec(True, Doonsec_switch, Doonsec)
result_xianzhi_short = Src_xianzhi(time_1, True)
result_freebuf_short = Src_freebuf(time_1, True)
result_qianxin_short = Src_qianxin(time_1, True)
result_seebug_short = Src_seebug(time_1, True)
webhook_url, timestamp, sign = gen_sign()
check_avaliable(result_4hou_long, result_4hou_short, "嘶吼资讯", webhook_url, timestamp, sign)
check_avaliable(result_anquanke_long, result_anquanke_short, "安全客资讯", webhook_url, timestamp, sign)
check_avaliable(result_doonsec_long, result_doonsec_short, "洞见微信安全资讯", webhook_url, timestamp, sign)
check_avaliable(result_xianzhi_long, result_xianzhi_short, "先知社区资讯", webhook_url, timestamp, sign)
check_avaliable(result_freebuf_long, result_freebuf_short, "FreeBuf资讯", webhook_url, timestamp, sign)
check_avaliable(result_qianxin_long, result_qianxin_short, "奇安信攻防社区资讯", webhook_url, timestamp, sign)
check_avaliable(result_seebug_long, result_seebug_short, "Seebug社区资讯", webhook_url, timestamp, sign)
# Seebug数据获取分发
seebug_main()
seebug_results = Src_seebug(time_1)
if seebug_results != False:
result_seebug_long, result_seebug_short = seebug_results
check_avaliable(result_seebug_long, result_seebug_short, "Seebug社区资讯")
else:
logger.info("Seebug数据为空，跳过执行。")
# 安全客数据获取分发
anquanke_main()
anquanke_results = Src_anquanke(time_1)
if anquanke_results != False:
result_anquanke_long, result_anquanke_short = anquanke_results
check_avaliable(result_anquanke_long, result_anquanke_short, "安全客资讯")
else:
logger.info("安全客数据为空，跳过执行。")
# 华为数据获取分发
huawei_main()
# 奇安信数据获取分发
qianxin_main()
qianxin_results = Src_qianxin(time_1)
if qianxin_results != False:
result_qianxin_long, result_qianxin_short = qianxin_results
check_avaliable(result_qianxin_long, result_qianxin_short, "奇安信攻防社区资讯")
else:
logger.info("奇安信数据为空，跳过执行。")
# FreeBuf数据获取分发
freebuf_main()
freebuf_results = Src_freebuf(time_1)
if freebuf_results != False:
result_freebuf_long, result_freebuf_short = freebuf_results
check_avaliable(result_freebuf_long, result_freebuf_short, "FreeBuf资讯")
else:
logger.info("FreeBuf数据为空，跳过执行。")
# 先知数据获取分发
xianzhi_main()
xianzhi_results = Src_xianzhi(time_1)
if xianzhi_results != False:
result_xianzhi_long, result_xianzhi_short = xianzhi_results
check_avaliable(result_xianzhi_long, result_xianzhi_short, "先知社区资讯")
else:
logger.info("先知数据为空，跳过执行。")
# 4hou数据获取分发
M_4hou_main()
M_4hou_results = Src_4hou(time_1)
if M_4hou_results != False:
result_4hou_long, result_4hou_short = M_4hou_results
check_avaliable(result_4hou_long, result_4hou_short, "嘶吼资讯")
else:
logger.info("嘶吼数据为空，跳过执行。")
# 洞见微信安全数据获取分发
doonsec_main()
doonsec_results = Src_doonsec(False, Doonsec_switch, Doonsec)
if doonsec_results != False:
result_doonsec_long, result_doonsec_short = doonsec_results
check_avaliable(result_doonsec_long, result_doonsec_short, "洞见微信安全资讯")
else:
logger.info("洞见微信安全数据为空，跳过执行。")
def send_job_SX():
Sogou_WX = get_kewords_config('Sogou-WX')
sougou_wx_main(Sogou_WX)
result_sx_long = Src_sougou_wx(False)
result_sx_short = Src_sougou_wx(True)
webhook_url, timestamp, sign = gen_sign()
check_avaliable(result_sx_long, result_sx_short, "微信公众号关键词相关内容", webhook_url, timestamp, sign)
result_sx_long, result_sx_short = Src_sougou_wx()
check_avaliable(result_sx_long, result_sx_short, "微信公众号关键词相关内容")
def send_job_github(time_1):
keyword_list, tool_list, user_list, black_words = load_github_config()
github_main(keyword_list, tool_list, user_list, black_words)
result_github_1_long, result_github_2_long, result_github_3_long, result_github_4_long = Src_github(time_1, False)
result_github_1_short, result_github_2_short, result_github_3_short, result_github_4_short = Src_github(time_1, True)
webhook_url, timestamp, sign = gen_sign()
check_avaliable(result_github_1_long, result_github_1_short, "Github项目监控-关键词监控", webhook_url, timestamp, sign)
check_avaliable(result_github_2_long, result_github_2_short, "Github项目监控-项目更新情况", webhook_url, timestamp, sign)
webhook_url, timestamp, sign = gen_sign()
check_avaliable(result_github_3_long, result_github_3_short, "Github项目监控-大佬工具", webhook_url, timestamp, sign)
check_avaliable(result_github_4_long, result_github_4_short, "Github项目监控-项目版本发布监测", webhook_url, timestamp, sign)
results = Src_github(time_1)
# 解构返回的结果
result_github_1_long, result_github_1_short = results[0]
result_github_2_long, result_github_2_short = results[1]
result_github_3_long, result_github_3_short = results[2]
result_github_4_long, result_github_4_short = results[3]
# 检查并处理结果
check_avaliable(result_github_1_long, result_github_1_short, "Github项目监控-关键词监控")
check_avaliable(result_github_2_long, result_github_2_short, "Github项目监控-项目更新情况")
check_avaliable(result_github_3_long, result_github_3_short, "Github项目监控-大佬工具")
check_avaliable(result_github_4_long, result_github_4_short, "Github项目监控-项目版本发布监测")
def send_job_baidu():
Baidu = get_kewords_config('Baidu')
baidu_main(Baidu)
result_baidu_long = Src_baidu(False)
result_baidu_short = Src_baidu(True)
webhook_url, timestamp, sign = gen_sign()
check_avaliable(result_baidu_long, result_baidu_short, "百度搜索关键词相关内容", webhook_url, timestamp, sign)
result_baidu_long, result_baidu_short = Src_baidu()
check_avaliable(result_baidu_long, result_baidu_short, "百度搜索关键词相关内容")
# 探测rss源状态
def check_rss_status(url):

132
Dev_test.py
View File

@ -0,0 +1,132 @@
# -*- coding: utf-8 -*-
"""
@Author: MasonLiu
@Description: 本程序可以爬取各安全资讯源，并发送到飞书群组。
"""
import schedule
import os
import signal
import sys
import time
import yaml
import requests
from datetime import datetime, timedelta
from SendCore.FeishuSendBot import SendToFeishu, gen_sign
from SendCore.QiweiSendBot import SendToWX
from spider.common import run, seebug_main, M_4hou_main, anquanke_main, sec_wiki_main, huawei_main, doonsec_main, qianxin_main
from spider.freebuf import freebuf_main
from spider.xianzhi import xianzhi_main
from spider.sougou_wx import sougou_wx_main
from spider.github import github_main, load_github_config
from spider.baidu import baidu_main
from GotoSend.M_4hou import Src_4hou
from GotoSend.anquanke import Src_anquanke
from GotoSend.doonsec import Src_doonsec
from GotoSend.xianzhi import Src_xianzhi
from GotoSend.freebuf import Src_freebuf
from GotoSend.qianxin import Src_qianxin
from GotoSend.seebug import Src_seebug
from GotoSend.sougou_wx import Src_sougou_wx
from GotoSend.github import Src_github
from GotoSend.baidu import Src_baidu
from config.check_config import get_core_config, get_debug_config, get_kewords_config
from loguru import logger
# 清除所有已有的日志记录器配置
logger.remove()
logger.add("./resources/log/core.log",
format="{time:YYYY-MM-DD HH:mm:ss} - {level} - {name}:{function}:{line} - {message}",
rotation="100 MB",
compression="zip",
encoding="utf-8")
# shell终端打印日志
debug = get_debug_config()
if debug == "True":
logger.add(lambda msg: print(msg),
format="{time:YYYY-MM-DD HH:mm:ss} - {level} - {name}:{function}:{line} - {message}")
def signal_handler(sig, frame):
logger.info("接收到退出信号，程序即将退出...")
sys.exit(0)
# 全局变量
signal.signal(signal.SIGINT, signal_handler) # Ctrl+C
signal.signal(signal.SIGTERM, signal_handler) # kill命令
webhook_url_once, timestamp_once, sign_once = gen_sign()
e_hour, time_choice, choice, fs_activate, wx_activate, ding_activate, lx_activate, url_web = get_core_config()
def check_avaliable(info_long, info_short, title):
if info_short: # 发送精简文章相关内容
# 企业微信相关
if wx_activate == "True":
# logger.info(f"{title} 递送中（企业微信）：")
print("正在发送精简文章内容...")
for info in info_short:
result = SendToWX(info, title)
print(result)
logger.info(result)
time.sleep(15)
else:
print("精简文章内容为空，跳过执行。")
pass
if info_long: # 发送完整文章相关内容
if fs_activate == "True":
# logger.info(f"{title} 递送中（飞书）：")
webhook_url, timestamp, sign = gen_sign()
result = SendToFeishu(info_long, title, webhook_url, timestamp, sign)
logger.info(result)
time.sleep(15)
else:
pass
if not info_long and not info_short:
logger.info(f"{title}数据为空，跳过执行。")
def send_job_RSS(time_1):
Doonsec_switch, Doonsec = get_kewords_config('Doonsec')
results = Src_doonsec(Doonsec_switch, Doonsec)
if results != False:
result_doonsec_long, result_doonsec_short = results
check_avaliable(result_doonsec_long, result_doonsec_short, "洞见微信安全资讯")
def main_job(e_hour):
logger.info(f"发送程序启动，当前时间为：{datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
logger.info("正在启动各爬虫并获取资源中...")
if 0 in choice:
send_job_RSS(e_hour)
logger.info("单次运行结束，等待下一次运行...")
def main_loop(time_choice):
if time_choice == 1:
while True:
try:
# 执行任务
main_job(e_hour)
time.sleep(e_hour * 60 * 60 - 3 * 60)
except Exception as e:
logger.error(f"发生错误: {e}, 程序已暂停")
# result = SendToFeishu(f"发生错误: {e}, 程序已退出", "报错信息")
exit()
elif time_choice == 0:
# 设置每天的特定时间点执行job函数
schedule.every().day.at("09:00").do(main_job, 12)
schedule.every().day.at("12:00").do(main_job, 3)
schedule.every().day.at("15:00").do(main_job, 3)
schedule.every().day.at("18:00").do(main_job, 3)
schedule.every().day.at("21:00").do(main_job, 3)
while True:
schedule.run_pending()
time.sleep(60) # 每分钟检查一次是否有任务需要执行
if __name__ == "__main__":
logger.info("程序正在运行当中。")
main_loop(time_choice)

67
GotoSend/M_4hou.py
View File

@ -107,28 +107,45 @@ def record_md(result, filename="./resources/history/sec_news.md"):
# 写回文件
with open(filename, 'w', encoding='utf-8') as file:
file.write(new_content)
def get_filtered_articles(entries, Is_short):
result = ""
def get_filtered_articles(entries):
result_long = ""
result_short = ""
record = ""
short_results = []
for entry in entries:
if Is_short == False:
result += f"文章：[{entry[1]}]({entry[2]})\n作者：{entry[5]}\n"
result += f"上传时间：{entry[4]}\n"
result += "\n" + "-" * 40 + "\n" # 添加分隔线以便区分不同文章
if Is_short == True:
result += f"文章：[{entry[1]}]({entry[2]})\n"
result += f"链接：{entry[2]}\n上传时间：{entry[4]}\n"
result += "\n" + "-" * 3 + "\n" # 添加分隔线以便区分不同文章
# 构建长文本结果
result_long += f"文章：[{entry[1]}]({entry[2]})\n作者：{entry[5]}\n"
result_long += f"上传时间：{entry[4]}\n"
result_long += "\n" + "-" * 40 + "\n" # 添加分隔线以便区分不同文章
# 构建短文本结果并进行分块处理
current_entry = (
f"文章：[{entry[1]}]({entry[2]})\n"
f"链接：{entry[2]}\n上传时间：{entry[4]}\n"
"\n" + "-" * 3 + "\n" # 添加分隔线以便区分不同文章
)
temp_result = result_short + current_entry
if len(temp_result.encode('utf-8')) > 4096:
short_results.append(result_short)
result_short = current_entry
else:
result_short = temp_result
record += f"#### 文章：[{entry[1]}]({entry[2]})\n"
record += f"**作者**：{entry[5]}\n"
record += f"**上传时间**：{entry[4]}\n"
record += "\n" + "-" * 40 + "\n" # 添加分隔线以便区分不同文章
# 处理最后一个结果
if result_short:
short_results.append(result_short)
record_md(record)
return result
return result_long, short_results
def Src_4hou(e_hour, Is_short):
def Src_4hou(e_hour):
if not os.path.exists('./resources/db/4hou.db'):
# 创建数据库和表
create_database()
@ -147,17 +164,27 @@ def Src_4hou(e_hour, Is_short):
# print(filtered_articles)
if filtered_articles:
results = get_filtered_articles(filtered_articles, Is_short)
return results
result_long, short_results = get_filtered_articles(filtered_articles)
return result_long, short_results
else:
return ""
return False
if __name__ == "__main__":
reslts = Src_4hou(4, False)
if reslts != "":
print(reslts)
results = Src_4hou(4)
if results != False:
result_long, short_results = results
# 打印长文本结果
print("长文本结果：")
print(result_long)
print("\n" + "-" * 40 + "\n")
# 打印分块的短文本结果
print("分块的短文本结果：")
for short_result in short_results:
print(short_result)
print("\n" + "-" * 40 + "\n")
else:
# 如果为空，则跳过执行
print("-" * 40)
print("嘶吼数据为空，跳过执行。")
print("嘶吼数据为空，跳过执行。")

BIN
GotoSend/__pycache__/doonsec.cpython-312.pyc
View File

Binary file not shown.

BIN
GotoSend/__pycache__/github.cpython-312.pyc
View File

Binary file not shown.

64
GotoSend/anquanke.py
View File

@ -102,29 +102,46 @@ def record_md(result, filename="./resources/history/sec_news.md"):
with open(filename, 'w', encoding='utf-8') as file:
file.write(new_content)
def get_filtered_articles(entries, Is_short):
result = ""
def get_filtered_articles(entries):
result_long = ""
result_short = ""
record = ""
short_results = []
for entry in entries:
if Is_short == False:
result += f"文章：[{entry[1]}]({entry[2]})\n作者：{entry[6]}\n来源：{entry[3]}\n"
result += f"上传时间：{entry[5]}\n"
result += "\n" + "-" * 40 + "\n" # 添加分隔线以便区分不同文章
elif Is_short == True:
result += f"文章：{entry[1]}\n"
result += f"链接：{entry[2]}\n上传时间：{entry[5]}\n"
result += "\n" + "-" * 3 + "\n" # 添加分隔线以便区分不同文章
# 构建长文本结果
result_long += f"文章：[{entry[1]}]({entry[2]})\n作者：{entry[6]}\n来源：{entry[3]}\n"
result_long += f"上传时间：{entry[5]}\n"
result_long += "\n" + "-" * 40 + "\n" # 添加分隔线以便区分不同文章
# 构建短文本结果并进行分块处理
current_entry = (
f"文章：{entry[1]}\n"
f"链接：{entry[2]}\n上传时间：{entry[5]}\n"
"\n" + "-" * 3 + "\n" # 添加分隔线以便区分不同文章
)
temp_result = result_short + current_entry
if len(temp_result.encode('utf-8')) > 4096:
short_results.append(result_short)
result_short = current_entry
else:
result_short = temp_result
record += f"#### 文章：[{entry[1]}]({entry[2]})\n"
record += f"**作者**：{entry[6]}\n"
record += f"**来源**：{entry[3]}\n"
record += f"**上传时间**：{entry[5]}\n"
record += "\n" + "-" * 40 + "\n" # 添加分隔线以便区分不同文章
# 处理最后一个结果
if result_short:
short_results.append(result_short)
record_md(record)
return result
return result_long, short_results
def Src_anquanke(e_hour, Is_short):
def Src_anquanke(e_hour):
if not os.path.exists('./resources/db/anquanke.db'):
# 创建数据库和表
create_database()
@ -143,16 +160,27 @@ def Src_anquanke(e_hour, Is_short):
# print(filtered_articles)
if filtered_articles:
results = get_filtered_articles(filtered_articles, Is_short)
return results
result_long, short_results = get_filtered_articles(filtered_articles)
return result_long, short_results
else:
return False
if __name__ == "__main__":
reslts = Src_anquanke(4, False)
if reslts != False:
print(reslts)
results = Src_anquanke(4)
if results != False:
result_long, short_results = results
# 打印长文本结果
print("长文本结果：")
print(result_long)
print("\n" + "-" * 40 + "\n")
# 打印分块的短文本结果
print("分块的短文本结果：")
for short_result in short_results:
print(short_result)
print("\n" + "-" * 40 + "\n")
else:
# 如果为空，则跳过执行
print("-" * 40)
print("安全客数据为空，跳过执行。")
print("安全客数据为空，跳过执行。")

71
GotoSend/baidu.py
View File

@ -137,30 +137,48 @@ def record_md(result, filename="./resources/history/baidu_news.md"):
with open(filename, 'w', encoding='utf-8') as file:
file.write(new_content)
def get_filtered_articles(entries, Is_short):
result = ""
def get_filtered_articles(entries):
result_long = ""
result_short = ""
record = ""
short_results = []
for entry in entries:
if Is_short == False:
result += f"文章：[{entry[1]}]({entry[2]})\n描述：{entry[3]}\n"
result += f"发布时间：{entry[4]}\n"
result += f"来源：{entry[5]}\n"
result += f"关键词：{entry[6]}\n"
result += "\n" + "-" * 40 + "\n" # 添加分隔线以便区分不同文章
if Is_short == True:
result += f"文章：[{entry[1]}]({entry[2]})"
result += f"上传时间：{entry[4]}\n"
result += "\n" + "-" * 3 + "\n" # 添加分隔线以便区分不同文章
# 构建长文本结果
result_long += f"文章：[{entry[1]}]({entry[2]})\n描述：{entry[3]}\n"
result_long += f"发布时间：{entry[4]}\n"
result_long += f"来源：{entry[5]}\n"
result_long += f"关键词：{entry[6]}\n"
result_long += "\n" + "-" * 40 + "\n" # 添加分隔线以便区分不同文章
# 构建短文本结果并进行分块处理
current_entry = (
f"文章：[{entry[1]}]({entry[2]})"
f"上传时间：{entry[4]}\n"
"\n" + "-" * 3 + "\n" # 添加分隔线以便区分不同文章
)
temp_result = result_short + current_entry
if len(temp_result.encode('utf-8')) > 4096:
short_results.append(result_short)
result_short = current_entry
else:
result_short = temp_result
record += f"#### 文章：[{entry[1]}]({entry[2]})\n描述：{entry[3]}\n"
record += f"**上传时间**：{entry[4]}\n"
record += f"**来源**：{entry[5]}\n"
record += f"**关键词**：{entry[6]}\n"
record += "\n" + "-" * 40 + "\n" # 添加分隔线以便区分不同文章
record_md(record)
return result
def Src_baidu(Is_short):
# 处理最后一个结果
if result_short:
short_results.append(result_short)
record_md(record)
return result_long, short_results
def Src_baidu():
if not os.path.exists('./resources/db/baidu.db'):
# 创建数据库和表
create_database()
@ -179,16 +197,27 @@ def Src_baidu(Is_short):
# print(filtered_articles)
if filtered_articles:
results = get_filtered_articles(filtered_articles, Is_short)
return results
result_long, short_results = get_filtered_articles(filtered_articles)
return result_long, short_results
else:
return False
if __name__ == "__main__":
reslts = Src_baidu(False)
if reslts != False:
print(reslts)
results = Src_baidu()
if results != False:
result_long, short_results = results
# 打印长文本结果
print("长文本结果：")
print(result_long)
print("\n" + "-" * 40 + "\n")
# 打印分块的短文本结果
print("分块的短文本结果：")
for short_result in short_results:
print(short_result)
print("\n" + "-" * 40 + "\n")
else:
# 如果为空，则跳过执行
print("-" * 40)
print("微信公众号数据为空，跳过执行。")
print("百度数据为空，跳过执行。")

71
GotoSend/doonsec.py
View File

@ -147,31 +147,49 @@ def record_md(result, filename="./resources/history/tech_passage.md"):
with open(filename, 'w', encoding='utf-8') as file:
file.write(new_content)
def get_filtered_articles(entries, Is_short):
result = ""
def get_filtered_articles(entries):
result_long = ""
result_short = ""
record = ""
short_results = []
for entry in entries:
if Is_short == False:
result += f"文章：[{entry[1]}]({entry[2]})\n"
result += f"作者：{entry[5]}\n"
result += f"上传时间：{entry[4]}\n"
result += f"简介：{entry[3]}\n"
result += "\n" + "-" * 40 + "\n" # 添加分隔线以便区分不同文章
if Is_short == True:
result += f"文章：[{entry[1]}]({entry[2]})\n"
result += f"上传时间：{entry[4]}\n"
result += "\n" + "-" * 3 + "\n" # 添加分隔线以便区分不同文章
# 构建长文本结果
result_long += f"文章：[{entry[1]}]({entry[2]})\n"
result_long += f"作者：{entry[5]}\n"
result_long += f"上传时间：{entry[4]}\n"
result_long += f"简介：{entry[3]}\n"
result_long += "\n" + "-" * 40 + "\n" # 添加分隔线以便区分不同文章
# 构建短文本结果并进行分块处理
current_entry = (
f"文章：[{entry[1]}]({entry[2]})\n"
f"上传时间：{entry[4]}\n"
"\n" + "-" * 3 + "\n" # 添加分隔线以便区分不同文章
)
temp_result = result_short + current_entry
if len(temp_result.encode('utf-8')) > 4096:
short_results.append(result_short)
result_short = current_entry
else:
result_short = temp_result
record += f"#### 文章：[{entry[1]}]({entry[2]})\n"
record += f"**作者**：{entry[5]}\n"
record += f"**上传时间**：{entry[4]}\n"
record += f"**简介**：{entry[3]}\n"
record += "\n" + "-" * 40 + "\n" # 添加分隔线以便区分不同文章
# 处理最后一个结果
if result_short:
short_results.append(result_short)
record_md(record)
return result
return result_long, short_results
def Src_doonsec(Is_short, Doonsec_switch, Doonsec):
def Src_doonsec(Doonsec_switch, Doonsec):
if not os.path.exists('./resources/db/doonsec.db'):
# 创建数据库和表
create_database()
@ -180,25 +198,36 @@ def Src_doonsec(Is_short, Doonsec_switch, Doonsec):
# clear_table()
# 获取 JSON 数据
M_doonsec_data = get_doonsec_json()
doonsec_data = get_doonsec_json()
# 插入数据到数据库
insert_data(M_doonsec_data)
insert_data(doonsec_data)
# 查询指定时间段内的数据
filtered_articles = select_articles(Doonsec_switch, Doonsec)
# print(filtered_articles)
if filtered_articles:
results = get_filtered_articles(filtered_articles, Is_short)
return results
result_long, short_results = get_filtered_articles(filtered_articles)
return result_long, short_results
else:
return False
if __name__ == "__main__":
reslts = Src_doonsec(False, False, ["webshell", "2000", "POC", "SQL", "XSS", "CSRF", "漏洞"] )
if reslts != False:
print(reslts)
results = Src_doonsec(False, ["webshell", "2000", "POC", "SQL", "XSS", "CSRF", "漏洞"])
if results != False:
result_long, short_results = results
# 写入长文本结果
with open("./1.txt", "a", encoding="utf-8") as f:
f.write(result_long)
f.write("\n" + "-" * 40 + "\n")
# 写入分块的短文本结果
for short_result in short_results:
with open("./2.txt", "a", encoding="utf-8") as f:
f.write(short_result)
f.write("\n" + "-" * 40 + "\n")
else:
# 如果为空，则跳过执行
print("-" * 40)

62
GotoSend/freebuf.py
View File

@ -108,28 +108,45 @@ def record_md(result, filename="./resources/history/sec_news.md"):
with open(filename, 'w', encoding='utf-8') as file:
file.write(new_content)
def get_filtered_articles(entries, Is_short):
result = ""
def get_filtered_articles(entries):
result_long = ""
result_short = ""
record = ""
short_results = []
for entry in entries:
if Is_short == False:
result += f"文章：[{entry[1]}]({entry[2]})\n类型：{entry[5]}\n"
result += f"上传时间：{entry[4]}\n"
result += "\n" + "-" * 40 + "\n" # 添加分隔线以便区分不同文章
elif Is_short == True:
result += f"文章：[{entry[1]}]({entry[2]})\n"
result += f"上传时间：{entry[4]}\n"
result += "\n" + "-" * 3 + "\n" # 添加分隔线以便区分不同文章
# 构建长文本结果
result_long += f"文章：[{entry[1]}]({entry[2]})\n类型：{entry[5]}\n"
result_long += f"上传时间：{entry[4]}\n"
result_long += "\n" + "-" * 40 + "\n" # 添加分隔线以便区分不同文章
# 构建短文本结果并进行分块处理
current_entry = (
f"文章：[{entry[1]}]({entry[2]})\n"
f"上传时间：{entry[4]}\n"
"\n" + "-" * 3 + "\n" # 添加分隔线以便区分不同文章
)
temp_result = result_short + current_entry
if len(temp_result.encode('utf-8')) > 4096:
short_results.append(result_short)
result_short = current_entry
else:
result_short = temp_result
record += f"#### 文章：[{entry[1]}]({entry[2]})\n"
record += f"**类型**：{entry[5]}\n"
record += f"**上传时间**：{entry[4]}\n"
record += "\n" + "-" * 40 + "\n" # 添加分隔线以便区分不同文章
# 处理最后一个结果
if result_short:
short_results.append(result_short)
record_md(record)
return result
return result_long, short_results
def Src_freebuf(e_hour, Is_short):
def Src_freebuf(e_hour):
if not os.path.exists('./resources/db/freebuf.db'):
# 创建数据库和表
create_database()
@ -148,15 +165,26 @@ def Src_freebuf(e_hour, Is_short):
# print(filtered_articles)
if filtered_articles:
results = get_filtered_articles(filtered_articles, Is_short)
return results
result_long, short_results = get_filtered_articles(filtered_articles)
return result_long, short_results
else:
return False
if __name__ == "__main__":
reslts = Src_freebuf(4, False)
if reslts != False:
print(reslts)
results = Src_freebuf(24)
if results != False:
result_long, short_results = results
# 打印长文本结果
print("长文本结果：")
print(result_long)
print("\n" + "-" * 40 + "\n")
# 打印分块的短文本结果
print("分块的短文本结果：")
for short_result in short_results:
print(short_result)
print("\n" + "-" * 40 + "\n")
else:
# 如果为空，则跳过执行
print("-" * 40)

177
GotoSend/github.py
View File

@ -297,59 +297,81 @@ def record_md(result, filename="./resources/history/github.md"):
with open(filename, 'w', encoding='utf-8') as file:
file.write(new_content)
def get_filtered_articles(entries, Is_short, choice):
result = ""
def get_filtered_articles(entries, choice):
result_long = ""
result_short = ""
record = ""
short_results = []
for entry in entries:
if Is_short == False:
if choice == 1:
result += f"关键词【{entry[6]}】发现新项目：[{entry[1]}]({entry[2]})\n"
result += f"项目描述：{entry[3]}\n"
result += f"上传时间：{entry[4]}\n"
result += f"开发语言：{entry[7]}\t\t作者：{entry[5]}\n"
result += "\n" + "-" * 10 + "\n" # 添加分隔线以便区分不同文章
elif choice == 2:
result += f"项目：[{entry[1]}]({entry[2]})存在更新！！！\n"
result += f"更新描述：{entry[3]}\n"
result += f"更新时间：{entry[4]}\n"
result += f"提交者：{entry[5]}，[点此查看提交详情]({entry[7]})\n"
result += "\n" + "-" * 10 + "\n" # 添加分隔线以便区分不同文章
elif choice == 3:
result += f"大佬 {entry[5]} 上传了一个新工具：[{entry[1]}]({entry[2]})\n"
result += f"项目描述：{entry[3]}\n"
result += f"上传时间：{entry[4]}\n"
result += "\n" + "-" * 10 + "\n" # 添加分隔线以便区分不同文章
elif choice == 4:
result += f"【{entry[3]}】为[{entry[4]}]({entry[1]})发布了新版本，请及时查收！\n"
result += f"发布时间：{entry[2]}\n"
result += "\n" + "-" * 10 + "\n" # 添加分隔线以便区分不同文章
elif Is_short == True:
if choice == 1:
result += f"关键词【{entry[7]}】发现新项目：[{entry[1]}]({entry[2]})\n"
result += f"上传时间：{entry[4]}\n"
result += f"开发语言：{entry[6]}\t\t作者：{entry[5]}\n"
result += "\n" + "-" * 3 + "\n" # 添加分隔线以便区分不同文章
elif choice == 2:
result += f"项目：[{entry[1]}]({entry[2]})存在更新！！！\n"
result += f"更新描述：{entry[3]}\n"
result += f"更新时间：{entry[4]}\n"
result += f"提交者：{entry[5]}，[点此查看提交详情]({entry[7]})\n"
result += "\n" + "-" * 3 + "\n" # 添加分隔线以便区分不同文章
elif choice == 3:
result += f"大佬 {entry[5]} 上传了一个新工具：[{entry[1]}]({entry[2]})\n"
result += f"项目描述：{entry[3]}\n"
result += f"上传时间：{entry[4]}\n"
result += "\n" + "-" * 3 + "\n" # 添加分隔线以便区分不同文章
elif choice == 4:
result += f"【{entry[3]}】为[{entry[4]}]({entry[1]})发布了新版本，请及时查收！\n"
result += f"发布时间：{entry[2]}\n"
result += "\n" + "-" * 3 + "\n" # 添加分隔线以便区分不同文章
if choice == 1:
# 构建长文本结果
result_long += f"关键词【{entry[6]}】发现新项目：[{entry[1]}]({entry[2]})\n"
result_long += f"项目描述：{entry[3]}\n"
result_long += f"上传时间：{entry[4]}\n"
result_long += f"开发语言：{entry[7]}\t\t作者：{entry[5]}\n"
result_long += "\n" + "-" * 10 + "\n" # 添加分隔线以便区分不同文章
# 构建短文本结果并进行分块处理
current_entry = (
f"关键词【{entry[6]}】发现新项目：[{entry[1]}]({entry[2]})\n"
f"上传时间：{entry[4]}\n"
f"开发语言：{entry[7]}\t\t作者：{entry[5]}\n"
"\n" + "-" * 3 + "\n" # 添加分隔线以便区分不同文章
)
elif choice == 2:
# 构建长文本结果
result_long += f"项目：[{entry[1]}]({entry[2]})存在更新！！！\n"
result_long += f"更新描述：{entry[3]}\n"
result_long += f"更新时间：{entry[4]}\n"
result_long += f"提交者：{entry[5]}，[点此查看提交详情]({entry[7]})\n"
result_long += "\n" + "-" * 10 + "\n" # 添加分隔线以便区分不同文章
# 构建短文本结果并进行分块处理
current_entry = (
f"项目：[{entry[1]}]({entry[2]})存在更新！！！\n"
f"更新时间：{entry[4]}\n"
f"提交者：{entry[5]}，[点此查看提交详情]({entry[7]})\n"
"\n" + "-" * 3 + "\n" # 添加分隔线以便区分不同文章
)
elif choice == 3:
# 构建长文本结果
result_long += f"大佬 {entry[5]} 上传了一个新工具：[{entry[1]}]({entry[2]})\n"
result_long += f"项目描述：{entry[3]}\n"
result_long += f"上传时间：{entry[4]}\n"
result_long += "\n" + "-" * 10 + "\n" # 添加分隔线以便区分不同文章
# 构建短文本结果并进行分块处理
current_entry = (
f"大佬 {entry[5]} 上传了一个新工具：[{entry[1]}]({entry[2]})\n"
f"上传时间：{entry[4]}\n"
"\n" + "-" * 3 + "\n" # 添加分隔线以便区分不同文章
)
elif choice == 4:
# 构建长文本结果
result_long += f"【{entry[3]}】为[{entry[4]}]({entry[1]})发布了新版本，请及时查收！\n"
result_long += f"发布时间：{entry[2]}\n"
result_long += "\n" + "-" * 10 + "\n" # 添加分隔线以便区分不同文章
# 构建短文本结果并进行分块处理
current_entry = (
f"【{entry[3]}】为[{entry[4]}]({entry[1]})发布了新版本，请及时查收！\n"
f"发布时间：{entry[2]}\n"
"\n" + "-" * 3 + "\n" # 添加分隔线以便区分不同文章
)
temp_result = result_short + current_entry
if len(temp_result.encode('utf-8')) > 4096:
short_results.append(result_short)
result_short = current_entry
else:
result_short = temp_result
if choice == 1:
record += f"#### 关键词【{entry[7]}】发现新项目：[{entry[1]}]({entry[2]})\n"
record += f"#### 关键词【{entry[6]}】发现新项目：[{entry[1]}]({entry[2]})\n"
record += f"**项目描述**：{entry[3]}\n"
record += f"**上传时间**：{entry[4]}\n"
record += f"**开发语言**：{entry[6]}\n**作者**：{entry[5]}\n"
record += f"**开发语言**：{entry[7]}\n**作者**：{entry[5]}\n"
record += "\n" + "-" * 10 + "\n" # 添加分隔线以便区分不同文章
elif choice == 2:
record += f"#### 项目：[{entry[1]}]({entry[2]})存在更新！！！\n"
@ -367,11 +389,15 @@ def get_filtered_articles(entries, Is_short, choice):
record += f"**发布时间**：{entry[2]}\n"
record += "\n" + "-" * 10 + "\n" # 添加分隔线以便区分不同文章
# 处理最后一个结果
if result_short:
short_results.append(result_short)
record_md(record)
return result
return result_long, short_results
def Src_github(e_hour, Is_short):
def Src_github(e_hour):
if not os.path.exists('./resources/db/github.db'):
# 创建数据库和表
create_database()
@ -385,35 +411,48 @@ def Src_github(e_hour, Is_short):
# 查询指定时间段内的数据
keyword_data, repo_data, user_data, release_data = select_articles(e_hour)
results = []
if keyword_data:
result_1 = get_filtered_articles(keyword_data, Is_short, 1)
result_long_1, short_results_1 = get_filtered_articles(keyword_data, 1)
results.append((result_long_1, short_results_1))
else:
result_1 = ""
results.append(("", []))
if repo_data:
result_2 = get_filtered_articles(repo_data, Is_short, 2)
result_long_2, short_results_2 = get_filtered_articles(repo_data, 2)
results.append((result_long_2, short_results_2))
else:
result_2 = ""
results.append(("", []))
if user_data:
result_3 = get_filtered_articles(user_data, Is_short, 3)
result_long_3, short_results_3 = get_filtered_articles(user_data, 3)
results.append((result_long_3, short_results_3))
else:
result_3 = ""
results.append(("", []))
if release_data:
result_4 = get_filtered_articles(release_data, Is_short, 4)
result_long_4, short_results_4 = get_filtered_articles(release_data, 4)
results.append((result_long_4, short_results_4))
else:
result_4 = ""
return result_1, result_2, result_3, result_4
results.append(("", []))
return results
if __name__ == "__main__":
result_1, result_2, result_3, result_4 = Src_github(240, False)
if result_1 != "":
print(result_1)
if result_2 != "":
print(result_2)
if result_3 != "":
print(result_3)
if result_4 != "":
print(result_4)
if result_1 == "" and result_2 == "" and result_3 == "" and result_4 == "":
results = Src_github(240)
for i, (result_long, short_results) in enumerate(results, start=1):
if result_long != "":
print(f"长文本结果 {i}：")
print(result_long)
print("\n" + "-" * 10 + "\n")
if short_results:
print(f"分块的短文本结果 {i}：")
for short_result in short_results:
print(short_result)
print("\n" + "-" * 10 + "\n")
if all(result_long == "" and not short_results for result_long, short_results in results):
# 如果为空，则跳过执行
print("-" * 10)
print("github数据为空，跳过执行。")
print("github数据为空，跳过执行。")

66
GotoSend/qianxin.py
View File

@ -99,30 +99,47 @@ def record_md(result, filename="./resources/history/tech_passage.md"):
with open(filename, 'w', encoding='utf-8') as file:
file.write(new_content)
def get_filtered_articles(entries, Is_short):
result = ""
def get_filtered_articles(entries):
result_long = ""
result_short = ""
record = ""
short_results = []
for entry in entries:
if Is_short == False:
result += f"文章：[{entry[1]}]({entry[2]})\n来源：{entry[3]}\n"
result += f"上传时间：{entry[5]}\n"
result += f"描述：{entry[4]}\n"
result += "\n" + "-" * 40 + "\n" # 添加分隔线以便区分不同文章
if Is_short == True:
result += f"文章：[{entry[1]}]({entry[2]})\n"
result += f"上传时间：{entry[5]}\n"
result += "\n" + "-" * 3 + "\n" # 添加分隔线以便区分不同文章
# 构建长文本结果
result_long += f"文章：[{entry[1]}]({entry[2]})\n来源：{entry[3]}\n"
result_long += f"上传时间：{entry[5]}\n"
result_long += f"描述：{entry[4]}\n"
result_long += "\n" + "-" * 40 + "\n" # 添加分隔线以便区分不同文章
# 构建短文本结果并进行分块处理
current_entry = (
f"文章：[{entry[1]}]({entry[2]})\n"
f"上传时间：{entry[5]}\n"
"\n" + "-" * 3 + "\n" # 添加分隔线以便区分不同文章
)
temp_result = result_short + current_entry
if len(temp_result.encode('utf-8')) > 4096:
short_results.append(result_short)
result_short = current_entry
else:
result_short = temp_result
record += f"#### 文章：[{entry[1]}]({entry[2]})\n"
record += f"**来源**：{entry[3]}\n"
record += f"**上传时间**：{entry[5]}\n"
record += f"**描述**：{entry[4]}\n"
record += "\n" + "-" * 40 + "\n" # 添加分隔线以便区分不同文章
# 处理最后一个结果
if result_short:
short_results.append(result_short)
record_md(record)
return result
return result_long, short_results
def Src_qianxin(e_hour, Is_short):
def Src_qianxin(e_hour):
if not os.path.exists('./resources/db/qianxin.db'):
# 创建数据库和表
create_database()
@ -141,16 +158,27 @@ def Src_qianxin(e_hour, Is_short):
# print(filtered_articles)
if filtered_articles:
results = get_filtered_articles(filtered_articles, Is_short)
return results
result_long, short_results = get_filtered_articles(filtered_articles)
return result_long, short_results
else:
return False
if __name__ == "__main__":
reslts = Src_qianxin(4, False)
if reslts != False:
print(reslts)
results = Src_qianxin(4)
if results != False:
result_long, short_results = results
# 打印长文本结果
print("长文本结果：")
print(result_long)
print("\n" + "-" * 40 + "\n")
# 打印分块的短文本结果
print("分块的短文本结果：")
for short_result in short_results:
print(short_result)
print("\n" + "-" * 40 + "\n")
else:
# 如果为空，则跳过执行
print("-" * 40)
print("奇安信攻防社区数据为空，跳过执行。")
print("奇安信攻防社区数据为空，跳过执行。")

66
GotoSend/seebug.py
View File

@ -106,30 +106,47 @@ def record_md(result, filename="./resources/history/sec_news.md"):
with open(filename, 'w', encoding='utf-8') as file:
file.write(new_content)
def get_filtered_articles(entries, Is_short):
result = ""
def get_filtered_articles(entries):
result_long = ""
result_short = ""
record = ""
short_results = []
for entry in entries:
if Is_short == False:
result += f"文章：[{entry[1]}]({entry[2]})\n类型：{entry[3]}\n"
result += f"上传时间：{entry[5]}\n"
result += f"{entry[4]}\n"
result += "\n" + "-" * 40 + "\n" # 添加分隔线以便区分不同文章
if Is_short == True:
result += f"文章：[{entry[1]}]({entry[2]})"
result += f"上传时间：{entry[5]}\n"
result += "\n" + "-" * 3 + "\n" # 添加分隔线以便区分不同文章
# 构建长文本结果
result_long += f"文章：[{entry[1]}]({entry[2]})\n类型：{entry[3]}\n"
result_long += f"上传时间：{entry[5]}\n"
result_long += f"{entry[4]}\n"
result_long += "\n" + "-" * 40 + "\n" # 添加分隔线以便区分不同文章
# 构建短文本结果并进行分块处理
current_entry = (
f"文章：[{entry[1]}]({entry[2]})\n"
f"上传时间：{entry[5]}\n"
"\n" + "-" * 3 + "\n" # 添加分隔线以便区分不同文章
)
temp_result = result_short + current_entry
if len(temp_result.encode('utf-8')) > 4096:
short_results.append(result_short)
result_short = current_entry
else:
result_short = temp_result
record += f"#### 文章：[{entry[1]}]({entry[2]})\n"
record += f"**类型**：{entry[3]}\n"
record += f"**上传时间**：{entry[5]}\n"
record += f"{entry[4]}\n"
record += "\n" + "-" * 40 + "\n" # 添加分隔线以便区分不同文章
# 处理最后一个结果
if result_short:
short_results.append(result_short)
record_md(record)
return result
return result_long, short_results
def Src_seebug(e_hour, Is_short):
def Src_seebug(e_hour):
if not os.path.exists('./resources/db/seebug.db'):
# 创建数据库和表
create_database()
@ -148,16 +165,27 @@ def Src_seebug(e_hour, Is_short):
# print(filtered_articles)
if filtered_articles:
results = get_filtered_articles(filtered_articles, Is_short)
return results
result_long, short_results = get_filtered_articles(filtered_articles)
return result_long, short_results
else:
return False
if __name__ == "__main__":
reslts = Src_seebug(100, False)
if reslts != False:
print(reslts)
results = Src_seebug(100)
if results != False:
result_long, short_results = results
# 打印长文本结果
print("长文本结果：")
print(result_long)
print("\n" + "-" * 40 + "\n")
# 打印分块的短文本结果
print("分块的短文本结果：")
for short_result in short_results:
print(short_result)
print("\n" + "-" * 40 + "\n")
else:
# 如果为空，则跳过执行
print("-" * 40)
print("Seebug社区数据为空，跳过执行。")
print("Seebug社区数据为空，跳过执行。")

71
GotoSend/sougou_wx.py
View File

@ -139,30 +139,48 @@ def record_md(result, filename="./resources/history/wx_news.md"):
with open(filename, 'w', encoding='utf-8') as file:
file.write(new_content)
def get_filtered_articles(entries, Is_short):
result = ""
def get_filtered_articles(entries):
result_long = ""
result_short = ""
record = ""
short_results = []
for entry in entries:
if Is_short == False:
result += f"文章：[{entry[1]}]({entry[2]})\n描述：{entry[3]}\n"
result += f"上传时间：{entry[4]}\n"
result += f"作者：{entry[5]}\n"
result += f"关键词：{entry[6]}\n"
result += "\n" + "-" * 40 + "\n" # 添加分隔线以便区分不同文章
if Is_short == True:
result += f"文章：[{entry[1]}]({entry[2]})"
result += f"上传时间：{entry[4]}\n"
result += "\n" + "-" * 3 + "\n" # 添加分隔线以便区分不同文章
# 构建长文本结果
result_long += f"文章：[{entry[1]}]({entry[2]})\n描述：{entry[3]}\n"
result_long += f"上传时间：{entry[4]}\n"
result_long += f"作者：{entry[5]}\n"
result_long += f"关键词：{entry[6]}\n"
result_long += "\n" + "-" * 40 + "\n" # 添加分隔线以便区分不同文章
# 构建短文本结果并进行分块处理
current_entry = (
f"文章：[{entry[1]}]({entry[2]})"
f"上传时间：{entry[4]}\n"
"\n" + "-" * 3 + "\n" # 添加分隔线以便区分不同文章
)
temp_result = result_short + current_entry
if len(temp_result.encode('utf-8')) > 4096:
short_results.append(result_short)
result_short = current_entry
else:
result_short = temp_result
record += f"#### 文章：[{entry[1]}]({entry[2]})\n描述：{entry[3]}\n"
record += f"**上传时间**：{entry[4]}\n"
record += f"**作者**：{entry[5]}\n"
record += f"**关键词**：{entry[6]}\n"
record += "\n" + "-" * 40 + "\n" # 添加分隔线以便区分不同文章