From ab81ca865c34a12a172aec81bee36486edc790a8 Mon Sep 17 00:00:00 2001 From: kevin Date: Wed, 31 Jan 2024 23:09:11 +0800 Subject: [PATCH] init Signed-off-by: kevin --- .gitignore | 2 + data_demo.txt | 96 ++++++++++ myfunsion.py | 417 ++++++++++++++++++++++++++++++++++++++++++++ post.py | 19 ++ reptile.py | 374 +++++++++++++++++++++++++++++++++++++++ test.txt | 6 + 搜索引擎工作思路.md | 29 +++ 7 files changed, 943 insertions(+) create mode 100644 .gitignore create mode 100644 data_demo.txt create mode 100644 myfunsion.py create mode 100644 post.py create mode 100644 reptile.py create mode 100644 test.txt create mode 100644 搜索引擎工作思路.md diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..3d200cb --- /dev/null +++ b/.gitignore @@ -0,0 +1,2 @@ +__pycache__ +.vs diff --git a/data_demo.txt b/data_demo.txt new file mode 100644 index 0000000..c26e88e --- /dev/null +++ b/data_demo.txt @@ -0,0 +1,96 @@ +begin_url:https://wnfed.com +image: +['https://wnfed.com/usr/themes/handsome/assets/img/sj2/1.jpg', 'https://wnfed.com/usr/themes/handsome/assets/img/sj2/10.jpg', 'https://wnfed.com/usr/themes/handsome/assets/img/sj2/4.jpg', 'https://wnfed.com/usr/themes/handsome/assets/img/sj2/9.jpg', 'https://wnfed.com/usr/themes/handsome/assets/img/sj2/2.jpg', 'https://wnfed.com/usr/themes/handsome/assets/img/sj2/1.jpg', 'https://wnfed.com/usr/themes/handsome/assets/img/sj2/10.jpg', 'https://wnfed.com/usr/themes/handsome/assets/img/sj2/4.jpg', 'https://wnfed.com/usr/themes/handsome/assets/img/sj2/9.jpg', 'https://wnfed.com/usr/themes/handsome/assets/img/sj2/2.jpg'] +new_url: +['https://wnfed.com/action/xmlrpc', 'https://wnfed.com/action/xmlrpc?rsd', 'https://wnfed.com/action/xmlrpc?wlw', 'https://wnfed.com/feed/', 'https://wnfed.com/feed/rss/', 'https://wnfed.com/feed/atom/', 'https://wnfed.com/', 'https://wnfed.com/cross.html', +'https://wnfed.com/cross.html', 'https://wnfed.com/cross.html', 'https://wnfed.com/index.php/action/login?_=0b839b99f2d1bd12725b159914ec85d3', 'https://wnfed.com/', 'https://wnfed.com/cross.html', 'https://wnfed.com/', 'https://wnfed.com/index.php/category/image/', 'https://wnfed.com/index.php/cross.html', 'https://wnfed.com/index.php/8.html', 'https://wnfed.com/index.php/7.html', 'https://wnfed.com/index.php/12.html', 'https://wnfed.com/index.php/838.html', 'https://wnfed.com/index.php/archives/758/', 'https://www.ultralibrarian.com/', 'https://www.51zxw.net/', 'https://www.foreverblog.cn/', 'https://www.foreverblog.cn/feeds.html', 'https://www.foreverblog.cn/go.html', 'https://wnfed.com/category/default/', 'https://wnfed.com/category/image/', 'https://wnfed.com/category/DATA/', 'https://wnfed.com/category/A/', 'https://wnfed.com/category/B/', 'https://wnfed.com/category/C/', 'https://wnfed.com/category/D/', 'https://wnfed.com/category/E/', 'https://wnfed.com/category/F/', 'https://wnfed.com/category/EN/', 'https://wnfed.com/category/G/', 'https://wnfed.com/category/H/', 'https://wnfed.com/840.html', 'https://wnfed.com/838.html', 'https://wnfed.com/12.html', 'https://wnfed.com/cross.html', 'https://wnfed.com/7.html', 'https://wnfed.com/8.html', 'https://lmve.net', 'http://aheboke.com/', 'https://www.ujslxw.com/', 'https://yyyyyyounger.com/', 'https://www.57blog.cn/', 'https://wnfed.com/admin/', +'https://wnfed.com/feed/', 'https://wnfed.com/feed/comments/', 'https://wnfed.com/archives/1071/', 'https://wnfed.com/archives/1071/', 'https://wnfed.com/author/1/', 'https://wnfed.com/archives/1071/#comments', 'https://wnfed.com/archives/1066/', 'https://wnfed.com/archives/1066/', 'https://wnfed.com/author/1/', 'https://wnfed.com/archives/1066/#comments', 'https://wnfed.com/archives/1031/', 'https://wnfed.com/archives/1031/', 'https://wnfed.com/author/1/', 'https://wnfed.com/archives/1031/#comments', 'https://wnfed.com/archives/1018/', 'https://wnfed.com/archives/1018/', 'https://wnfed.com/author/1/', 'https://wnfed.com/archives/1018/#comments', 'https://wnfed.com/archives/959/', 'https://wnfed.com/archives/959/', 'https://wnfed.com/author/1/', 'https://wnfed.com/archives/959/#comments', 'https://wnfed.com/archives/945/', 'https://wnfed.com/archives/945/', 'https://wnfed.com/author/1/', 'https://wnfed.com/archives/945/#comments', 'https://wnfed.com/archives/941/', 'https://wnfed.com/archives/941/', 'https://wnfed.com/author/1/', 'https://wnfed.com/archives/941/#comments', 'https://wnfed.com/archives/933/', 'https://wnfed.com/archives/933/', 'https://wnfed.com/author/1/', 'https://wnfed.com/archives/933/#comments', 'https://wnfed.com/archives/924/', 'https://wnfed.com/archives/924/', 'https://wnfed.com/author/1/', 'https://wnfed.com/archives/924/#comments', 'https://wnfed.com/archives/899/', 'https://wnfed.com/archives/899/', 'https://wnfed.com/author/1/', 'https://wnfed.com/archives/899/#comments', 'https://wnfed.com/archives/874/', 'https://wnfed.com/archives/874/', 'https://wnfed.com/author/1/', 'https://wnfed.com/archives/874/#comments', 'https://wnfed.com/archives/871/', 'https://wnfed.com/archives/871/', 'https://wnfed.com/author/1/', 'https://wnfed.com/archives/871/#comments', 'https://wnfed.com/archives/851/', 'https://wnfed.com/archives/851/', 'https://wnfed.com/author/1/', 'https://wnfed.com/archives/851/#comments', 'https://wnfed.com/archives/846/', 'https://wnfed.com/archives/846/', 'https://wnfed.com/author/1/', 'https://wnfed.com/archives/846/#comments', 'https://wnfed.com/archives/811/', 'https://wnfed.com/archives/811/', 'https://wnfed.com/author/1/', 'https://wnfed.com/archives/811/#comments', 'https://wnfed.com/archives/808/', 'https://wnfed.com/archives/808/', 'https://wnfed.com/author/1/', 'https://wnfed.com/archives/808/#comments', 'https://wnfed.com/archives/789/', 'https://wnfed.com/archives/789/', 'https://wnfed.com/author/1/', 'https://wnfed.com/archives/789/#comments', 'https://wnfed.com/archives/778/', 'https://wnfed.com/archives/778/', 'https://wnfed.com/archives/778/', 'https://wnfed.com/archives/762/', 'https://wnfed.com/archives/762/', 'https://wnfed.com/author/1/', 'https://wnfed.com/archives/762/#comments', 'https://wnfed.com/archives/757/', 'https://wnfed.com/archives/757/', 'https://wnfed.com/author/1/', 'https://wnfed.com/archives/757/#comments', 'https://wnfed.com/page/1/', 'https://wnfed.com/page/2/', 'https://wnfed.com/page/3/', 'https://wnfed.com/page/4/', 'https://wnfed.com/page/6/', 'https://wnfed.com/page/2/', 'https://wnfed.com/archives/959/', 'https://wnfed.com/archives/959/', 'https://wnfed.com/archives/945/', 'https://wnfed.com/archives/945/', 'https://wnfed.com/archives/874/', 'https://wnfed.com/archives/874/', 'https://wnfed.com/archives/899/', +'https://wnfed.com/archives/899/', 'https://wnfed.com/archives/924/', 'https://wnfed.com/archives/924/', 'https://wnfed.com/archives/1066/#comment-190', 'https://secure.gravatar.com/avatar/9007c32dd9dd47971f12f111809e4e50?s=65&r=G&d=', 'https://wnfed.com/archives/1066/#comment-190', 'https://wnfed.com/archives/1066/#comment-190', 'https://wnfed.com/archives/1071/#comment-188', 'https://secure.gravatar.com/avatar/05adf5179ce2ed8b675ce0949495b621?s=65&r=G&d=', 'https://wnfed.com/archives/1071/#comment-188', 'https://wnfed.com/archives/1071/#comment-188', 'https://wnfed.com/archives/1018/#comment-183', 'https://q2.qlogo.cn/g?b=qq&nk=3320870795&s=100', 'https://wnfed.com/archives/1018/#comment-183', 'https://wnfed.com/archives/1018/#comment-183', 'https://wnfed.com/840.html#comment-179', 'https://q2.qlogo.cn/g?b=qq&nk=3320870795&s=100', 'https://wnfed.com/840.html#comment-179', 'https://wnfed.com/840.html#comment-179', 'https://wnfed.com/840.html#comment-176', 'https://q2.qlogo.cn/g?b=qq&nk=3320870795&s=100', 'https://wnfed.com/840.html#comment-176', 'https://wnfed.com/840.html#comment-176', 'https://wnfed.com/archives/1013/', 'https://wnfed.com/archives/1013/', 'https://wnfed.com/archives/233/', 'https://wnfed.com/archives/233/', 'https://wnfed.com/archives/289/', 'https://wnfed.com/archives/289/', 'https://wnfed.com/archives/268/', 'https://wnfed.com/archives/268/', 'https://wnfed.com/archives/212/', 'https://wnfed.com/archives/212/', 'https://wnfed.com/tag/10/', 'https://wnfed.com/tag/C/', 'https://wnfed.com/tag/%E6%8E%A7%E5%88%B6%E5%8F%B0/', 'https://wnfed.com/tag/8/', 'https://wnfed.com/tag/7/', 'https://wnfed.com/tag/QT/', 'https://wnfed.com/tag/5/', 'https://wnfed.com/tag/6/', 'https://wnfed.com/tag/BB/', 'https://wnfed.com/tag/stm32/', 'https://wnfed.com/tag/HAL/', 'https://wnfed.com/tag/arduino/', 'https://wnfed.com/tag/16/', 'https://wnfed.com/tag/15/', 'https://wnfed.com/tag/world-skills/', 'https://wnfed.com/tag/13/', 'https://wnfed.com/tag/2021/', 'https://wnfed.com/tag/12/', 'https://wnfed.com/tag/11/', 'https://wnfed.com/tag/9/', 'https://wnfed.com/tag/DFU/', 'https://wnfed.com/tag/PHP/', 'https://wnfed.com/tag/MYSQL/', 'https://wnfed.com/tag/OpenCV/', 'https://wnfed.com/tag/Linux/', 'https://wnfed.com/tag/LCD/', 'https://wnfed.com/tag/4/', 'https://wnfed.com/tag/FSMC/', 'https://wnfed.com/tag/FAT32/', 'https://wnfed.com/tag/Fatfs/', 'https://www.ihewro.com/archives/489/', 'https://www.ddg.ink/', +'http://www.typecho.org', 'https://www.ihewro.com/archives/489/'] +title: +['无闻风 - Blog'] +mate: +['爱生活更爱技术，文能放下键盘敲代码，武能拿起烙铁焊电路。', '吳文峰,无闻风,博客', 'Typecho 1.1/17.10.30', 'handsome'] +html: +无闻风 - Blog

无闻风

加载中……

Git服务器从gitblit升级到gitlab

gitblit其实挺好用的，就是功能有点少。升级到gitlab玩玩。Gitlab<-点击进入安装方法去官网 +gitlab参考安装命令，主要安装命令就两条curl https://packages.gitlab.com/install/repositories/gitlab/gitlab-ee/script.rpm.sh | sudo bashsudo EXTERNAL_URL=&qu...

  • Kevin
  • 2022 年 03 月 24 日
  • 2 条评论

    • QT学习作品，多线程IP扫描器

    摸了很长时间，又把QT捡起来学 +习了，突然想到的一个项目，想扫描一下网上有多少隐藏的Minecraft服务器。其实IP扫描器网上也有很多，我也用过来扫描...

  • Kevin
  • 2022 年 01 月 08 日
  • 2 条评论

    • 服务器小升级，装了 +个OpenWrt做端口转发

    起因最新发现即使在局域网，网站在加载大量图片的时候会有延时，有时 +候长达1秒，不止是网站，其他服务比如Minecraft服务器也有延时。猜测是我的辣鸡路由器...

  • Kevin
  • 2022 年 01 月 08 日
  • 暂无评论

    • 使用Gitblit搭建个人小型Git服务器

    git.lmve<-入 +口这个在很久以前就已将搭建了，一直在用，效果还不错，管理小项目足够给力。我的搭建方法1.先去Gitblit官网下载服务包。 2.下载JAVA解压 +下载的Gitblit服务包，里面应该会有这些文件修改gitblit.sh先cd把执行路径改成当前路径我这里是修改了java的路径java -cp "gitblit.jar:ext/*" com.gitb...

  • Kevin
  • 2021 年 12 月 04 日
  • 2 +条评论

    • 搭建了一个Minecraft服 +务器

    可我没什么开服的经验，只是用Spigot在ubuntu上开的一个插件服版本是1.17.1可以通过 +lmve.net wnfed.com 这两个域名进入测试过性能可好了 ::aru:thumb:: 用鞘翅到处飞都不卡（以前用群辉搭的服用鞘翅飞会很卡）

  • Kevin
  • 2021 年 11 月 14 日
  • 20 条评论

    • 换了个机箱

    新机箱这个机箱我眼馋很久了，就是有点小贵，最近才狠下心放血购买。旧机箱主要原因是旧机箱太 +‘赛博朋克’了，摇摇晃晃的，经过几次丢失数据后真的怕了就是蜗牛...

  • Kevin
  • 2021 年 11 月 14 日
  • 8 条评论

    • 服务器回档了：（

    前几天在公司摸鱼，想在服务器上安装个Gitlab替代现在的Gitblit，试了好多次没成功，好像是自带的nginx和宝塔的冲突了，在经过几次重装后没注意到Esxi的硬盘满了，然后服务器就一直卡在哪里，没有 +办法只能重启。重启了以后系统就进不去了。 我想只是系统挂了，问题不大，最多重装系统麻烦一点。等我重装好系统以后，就开始发现不对经了 +，先是恢复MySQL各种报错。忽略错误装好后就发现少了一点东...

  • Kevin
  • 2021 年 11 月 14 日
  • 1 条评论

    • MAX30102血氧心率传感器开发研究

    开发文档MAX30102.pdf开发平台stm32f103ze，m3s开发板连接方式MAX3012 IICLCD sfmcLCD_touc...

  • Kevin
  • 2021 年 08 月 31 日
  • 2 条评论

    • Git 常用命令

    Git默认名称master 默认开发分支origin 默认远程版本库Head 默认开发分支Head^Head 的父提交Git 常用命令创建版本库$ git clone <url> 克隆远程版本库$ git init初始 +化本地版本库修改和提交$ git status 查看状态$ git diff...

  • Kevin
  • 2021 +年 07 月 05 日
  • 2 条评论

    • 黑群晖折腾记

    自从开通公网以后 +，我用一台退役的游戏本搭建了一台winserver的服务器，而且已经开机差不多两年了，这台服务器经历了大大小小的数据灾难，存活至今，幸好我 +...

  • Kevin
  • 2021 年 03 月 30 日
  • 2 条评论

    • 用 +C控制台写一个‘华容道’小游戏

    去年年底写的一个小游戏玩法：方向键控制空格随机打乱按下字 +母a自动还原介绍：通过递归实现路径搜索控制台的简单驱动，（在某坐标写入某字符）HANDLE hOu...

  • Kevin
  • 2020 年 11 月 06 日
  • 2 条评论

    • 用C控制台写一个‘2048’小游戏

    去年年底写的代码，有点意思一些控制台函数HANDLE hOut = GetStdHandle(STD_OUTPUT_HANDLE);CONSOLE_CU...

  • Kevin
  • 2020 年 11 月 06 日
  • 暂无评论

    • 使用 +C控制台写一个‘推箱子’小游戏

    去年写的代码，突然发现在硬盘里躺了很久，贴出来分享一下可 +自定义关卡RGB性能加持控制台RBG驱动 ::aru:envious:: and获取按键状态HAN...

  • Kevin
  • 2020 年 11 月 06 日
  • 暂无评论

    • 使用C控制台写一个‘一笔画完’小游戏

    这是我2019年某月写的程序，主要玩法是方向键控制角色一次性走完所有格子不重复功能：自定义多关卡使用递归自动搜索路 +径操作：方向键控制角色按字母a自动计算路径

  • Kevin
  • 2020 年 11 月 06 日
  • 暂无评论

    • 蜂鸣 +器-C 以链表的方式播放音乐

    测试下性能而已不建议真的用链表做，容易爆内存。struct notes //一个音符{uint16_t freq;//频率uint8_t duty; //占空比uint16_t deley; //播放时长struct notes *next_note;//下一个音符};储存一个音 +符的结构体，void...

  • Kevin
  • 2020 年 10 月 24 日
  • 暂无评论

    • 更简单的编码器驱动

    encoder.c#include "encoder.h"struct encoder en;/*#define BU...

  • Kevin
  • 2020 年 10 月 24 日
  • 暂 +无评论

    • stm32-DFU下载升级（HAL）

    stm32的下载方式有很多种，最简单的是SW下载，不过这种方式会占用两个IO口，虽然可以程序中复用，但是在pcb设计、后期升级等也有一定的不便，所以加入D...

  • Kevin
  • 2020 年 10 月 24 日
  • 暂无评论

    • World skills 2021 澳门区宣传片

    Windows server 2016/2019从评估板升级到完整版

    评估版限制很多，安装了域控制器无法升级所以，重装系统后最好第 +一时间升级完整版无法从Windows Server Eval Datacenter升级到Windows Server Standard Full。Windows Server 2016：将评估转换为许可版本 +要将Windows Server Evaluation升级到完整版，您需要为Windows Server 2016使用公共KMS...

  • Kevin
  • 2020 年 08 月 23 日
  • 暂无评论

    • STM32+MPU6050 (HAL)

    在MXcube启动一个IIC接口extern I2C_HandleTypeDef hi2c1;//IIC写一个字节 //reg:寄存器地址//da...

  • Kevin
  • 2020 年 08 月 23 日
  • 暂无评论
    • © 2022 Copyright Powered by our story...
    +words: +['无', '闻风', 'Blog', 'WNFED', '动态', '日历', 'Loading', '分类', '雷达', '图', '发布', '统计', '统计图', '标签', '碎语', '闲言 +碎语', '邮箱', '炸', '了', 'March', '23rd', '2022', 'at', '03', ':', '20', 'pm', '新', '版本', 'Kicad', '依然', '无法', '在', '原 +生', 'ARM', '运行', 'December', '26th', '2021', '12', '57', '吵死', '人', '隔壁', '又', '装修', '11th', '11', '34', 'am', '用户', '户名', '用户名', '密码', '登录', '中', '刷新', '页面', '后', 'Kevin', '爱', '生活', '更爱', '技术', '文能', '放下', '键盘', '敲 +', '代码', '武能', '拿', '起', '烙铁', '焊', '电路', '下午', '好', '是', '时候', '打个', '盹', '导航', '首页', '相册', '闲言', ' +留言', '归档', '观影', '仓库', '记事', '推荐', 'ultralibrarian', '我要', '自学', '网', '十年', '之约', '聚合', '虫', '洞', '组成', '18', '瞎', '写', '14', '资源', '21', '单片', '单片机', '编程', '29', '计算', '算机', '计算机', '19', '杂谈', '4', '折腾', '瞎 +折腾', '1', '音乐', '5', '视频', '3', 'EN', '2', '啊', '8', '资讯', '友情', '链接', '友情链接', '走马', '走马观花', '友链', '电子 +', '硬件', '社区', '阿', '和', '博客', '刘', '希望', 'Y', '哥', 'の', '小站', '无心', '管理', '文章', '评论', '加载', '…', 'Git', '服务', '务器', '服务器', '从', 'gitblit', '升级', '到', 'gitlab', '其实', '挺好用', '的', '就是', '功能', '有点', '少', '玩玩', 'Gitlab', 'lt', '点击', '进入', '安装', '方法', '去', '官网', '参考', '命令', '主要', '就', '两条', 'curl', 'https', '/', 'packages', 'com', 'install', 'repositories', 'ee', 'script', 'rpm', 'sh', 'sudo', 'bashsudo', 'EXTERNAL', 'URL', '=', 'qu', '年', '月', '24', '日', '条', 'QT', '学习', '作品', '多线', '线程', '多线程', 'IP', '扫描', '扫描器', '摸', '很', '时间', '长时间', '把', '捡起', '起来', '捡起来', '突然', '想到', '一个', '项目', '想', '一下', '网上', '有', '多少', '隐藏', 'Minecraft', '也', '很多', '我', '用', '过来', '01', '08', '小', '装', '个', 'OpenWrt', '做', '端口', '转发', '起因', '最新', '发现', '即使', '局域', '局域网 +', '网站', '大量', '图片', '会', '延时', '有时', '有时候', '长达', '秒', '不止', '其他', '比如', '猜测', '辣鸡', '路由', '路由器', '暂无', '使用', 'Gitblit', '搭建', '个人', '小型', 'git', 'lmve', '入口', '这个', '很久', '以前', '很久以前', '已', '将', '一直 +', '效果', '还', '不错', '足够', '给力', '先去', '下载', '包', 'JAVA', '解压', '里面', '应该', '这些', '文件', '修改', '先', 'cd', '执行', '路径', '改成', '当前', '这里', 'java', 'cp', 'quot', 'jar', 'ext', 'gitb', '04', '可', '什么', '没什么', '开服', '经验 +', '只是', 'Spigot', 'ubuntu', '上开', '插件', '服', '117', '可以', '通过', 'net', 'wnfed', '这', '两个', '域名', '测试', '过', '性能', '可好', 'aru', 'thumb', '鞘翅', '到处', '飞', '都', '不卡', '群辉', '搭', '服用', '飞会', '卡', '换', '机箱', '眼馋', '小 +贵', '最近', '才', '狠下', '心', '放血', '购买', '旧', '原因', '太', '‘', '赛博', '朋克', '’', '摇摇', '摇晃', '晃晃', '摇摇晃晃', '经过', '几次', '丢失', '数据', '真的', '怕', '蜗牛', '回档', '前', '几天', '公司', '摸鱼', '服务器上安装', '替代', '现在', '试 +', '多次', '没', '成功', '好像', '自带', 'nginx', '宝塔', '冲突', '重装', '注意', 'Esxi', '硬盘', '满', '然后', '哪里', '没有', '办法', '只能', '重启', '以后', '系统', '进不去', '挂', '问题', '不', '大', '最', '多', '重装系统', '麻烦', '一点', '等', '开始', +'不对', '不对经', '先是', '恢复', 'MySQL', '各种', '报错', '忽略', '错误', '装好', '东', 'MAX30102', '血氧', '心率', '传感', '感 +器', '传感器', '开发', '研究', '文档', 'pdf', '平台', 'stm32f103ze', 'm3s', '开发板', '连接', '方式', 'MAX3012', 'IICLCD', 'sfmcLCD', 'touc', '31', '常用', '常用命令', '默认', '名称', 'master', '分支', 'origin', '远程', '库', 'Head', '^', '父', '提交', '创建 +', 'clone', 'url', 'gt', '克隆', 'init', '初始', '初始化', '本地', 'status', '查看', '状态', 'diff', '07', '05', '黑群晖', '记', +'自从', '开通', '公网', '我用', '一台', '退役', '游戏', '本', 'winserver', '而且', '已经', '开机', '不多', '差不多', '两年', '这 +台', '经历', '大大', '大小', '小小', '大大小小', '灾难', '存活', '至今', '幸好', '30', 'C', '控制', '控制台', '华容', '华容道', '小游戏', '去年', '年底', '玩法', '方向', '方向键', '空格', '随机', '打乱', '按下', '字母', 'a', '自动', '还原', '介绍', '递归', '实现', '搜索', '简单', '驱动', '某', '坐标', '写入', '字符', 'HANDLE', 'hOu', '2020', '06', '2048', '意思', '一些', '函数', 'hOut', 'GetStdHandle', 'STD', 'OUTPUT', 'CONSOLE', 'CU', '推', '箱子', '里', '躺', '久', '贴出', '出来', '贴出来', '分享', '自定', ' +定义', '自定义', '关卡', 'RGB', '加持', 'RBG', 'envious', 'and', '获取', '按键', 'HAN', '一', '笔画', '完', '2019', '某月', '程序 +', '角色', '一次', '一次性', '走', '所有', '格子', '重复', '操作', '按', '蜂鸣器', '以', '链表', '播放', '下', '而已', '建议', ' +容易', '爆', '内存', 'struct', 'notes', '音符', 'uint16', 't', 'freq', '频率', 'uint8', 'duty', '占空比', 'deley', '时长', 'next', 'note', '储存', '结构', '体', 'void', '10', '更', '编码', '码器', '编码器', 'encoder', 'c#', 'include', 'h', 'en', '#', 'define', 'BU', 'stm32', 'DFU', 'HAL', '下载方式', '多种', 'SW', '不过', '这种', '占用', 'IO', '口', '虽然', '复用', '但是', 'pcb', '设 +计', '、', '后期', '一定', '不便', '所以', '加入', 'D', 'World', 'skills', '澳门', '区', '宣传', '宣传片', 'Windows', 'server', '2016', '评估', '板', '完整', '整版', '完整版', '版', '限制', '控制器', '域控制器', '最好', '第一', 'Server', 'Eval', 'Datacenter', 'Standard', 'Full', '转换', '为', '许可', '要', 'Evaluation', '您', '需要', '公共', 'KMS', '23', 'STM32', '+', 'MPU6050', 'MXcube', '启动', 'IIC', '接口', 'extern', 'I2C', 'HandleTypeDef', 'hi2c1', '字节', 'reg', '寄存', '寄存器', '地址', 'da', '6', '热门', '数', '芭比', '看不懂', '萧瑟', '冒昧', '问', '一句', '私服', '云', '上', '还是', '自己', '家里', 'v', '哇', '更新', '头像', 'cdn', 'jsdeli', '您好', '介于', '未', '看到', '本站', '故', '决定', '取消', '贵', '站友', '链', '请悉', '知', '中山', '中山市', ' +技师', '学院', '0', 'eagle', '仿真', '电容', '属性', '简易', 'P', '站', '爬虫', '脚本', '中文', '英文', '手册', '使用手册', 'DS3231', '信息', '130', '数目', '153', '192', '天', '天数', '最后', '活动', '算法', '笔记', 'C++', 'BB', 'arduino', '无人', '人机', '无人机', '四', '旋翼', '飞行', '飞行器', 'world', '世界', '职业', '技能', '职业技能', '大赛', '语言', 'C语言', 'PHP', 'MYSQL', 'OpenCV', 'Linux', 'LCD', '彩屏', 'FSMC', 'FAT32', 'Fatfs', '目录', 'Powered', 'by', 'typecho', 'Theme', 'handsome', 'Copyright', 'Typecho', 'nbsp', 'copy', 'our', 'story'] \ No newline at end of file diff --git a/myfunsion.py b/myfunsion.py new file mode 100644 index 0000000..5e30fb9 --- /dev/null +++ b/myfunsion.py @@ -0,0 +1,417 @@ +import requests +import re +import html +import json +import jieba +from urllib.parse import urlparse +class myfunsion: + def a(): + print("test") + +class det:#测试url类型 + def image(url): + style_type_list=[".jpg",".jpeg",".png",".gif",".svg"] + #将url转小写 + url=url.lower() + for i in style_type_list: + if i in url: + return True + return False + + def style(url): + style_type_list=[".js",".css"] + url=url.lower() + for i in style_type_list: + if i in url: + return True + return False + + #检查是否有重复 + # arr 数组 + # i 数据 + def repeat(arr,i): + b=0 + for a in arr: + if a==i: + return b + b+=1 + return -1 + + #检测url域名 + def domin(url): + domin=urlparse(url) + return domin + +class net: + headers = { + 'user-agent': 'my-app/0.0.1', + 'Content-Type': 'text/html; charset=utf-8' + } + def get_html(url): + return_js={} + return_js['url']=url + try : + r = requests.get(url,headers=net.headers,verify=False,timeout=(60, 60)) + return_js['status']=r.status_code + get_content_type='text/html' + content_type=re.findall(get_content_type,r.headers['Content-Type']) + if(len(content_type)==0): + return_js['contenttype']=r.headers['Content-Type'] + else: + return_js['contenttype']=get_content_type + + if(return_js['contenttype']=='text/html'): + get_gb2312='gb2312' + charset=re.findall(get_gb2312,r.headers['Content-Type']) + if(len(charset)==0): + return_js['charset_type']='utf-8' + else: + return_js['charset_type']='gb2312' + htmlx_byt=r.content + htmlx=str(htmlx_byt,return_js['charset_type']) + return_js['html']=htmlx + except: + return_js['status']=0 + + return return_js + + def ana_html(webdata): + return_js={} + return_js['status']=webdata['status'] + return_js['url']=webdata['url'] + if webdata['status']==0: + return_js['score']="0" + return_js['contenttype']="none" + return return_js + return_js['contenttype']=webdata['contenttype'] + #return_js['charset_type']=webdata['charset_type'] + if(return_js['contenttype']=='text/html'): + thisurlscore=100 + htmlx=webdata['html'] + ur=urlparse(return_js['url']) + domain=ur.netloc + return_js['domain']=domain + + + #根url + if(ur.path==''): + thisurlscore+=50 + if(ur.path=='/'): + thisurlscore+=50 + #是否带参数 + if(ur.query!=''): + thisurlscore-=10 + #是否带位置 + if(ur.fragment!=''): + thisurlscore-=50 + #获取js + get_htmlx_js='' + htmlx_js=re.findall(get_htmlx_js,htmlx) + #清除htmlx js + for i in htmlx_js: + htmlx=htmlx.replace(i,"") + + htmlx_kuaizhao=html.escape(htmlx) #干掉js后截取快照 + htmlx_yasuo=["\n","\r","\t"," "] + for i in htmlx_yasuo: + htmlx_kuaizhao=htmlx_kuaizhao.replace(i,"")#压缩一下 + + #获取style + get_htmlx_style='' + htmlx_style=re.findall(get_htmlx_style,htmlx) + #print(htmlx_style) + #清除htmlx style + for i in htmlx_style: + htmlx=htmlx.replace(i,"") + + #获取textarea ,像百度这样的阴间网站有隐藏的输入框里面会有样式什么的奇怪东西 + get_htmlx_textarea='' + htmlx_textarea=re.findall(get_htmlx_textarea,htmlx) + for i in htmlx_textarea: + htmlx=htmlx.replace(i,"") + + #获取页面中的url并分类 + get_url=r'\"(http[s]?://[\S]*)\"' + all_url=re.findall(get_url,htmlx) + style_url_list=[] + image_url_list=[] + new_url_list=[] + for i in all_url: + if det.style(i): + style_url_list.append(i) + else: + if det.image(i): + image_url_list.append(i) + else: + new_url_list.append(i) + + #干掉url + image_url=[] + new_url=[] + image_url_js={} + new_url_js={} + image_url_int=0 + new_url_int=0 + for i in style_url_list: + htmlx=htmlx.replace(i,"") + for i in image_url_list: + htmlx=htmlx.replace(i,"") + if det.repeat(image_url,i)==-1: + image_url.append(i) + image_url_js[str(image_url_int)]=i + image_url_int+=1 + thisurlscore+=2#图片加分 + for i in new_url_list: + htmlx=htmlx.replace(i,"") + if det.repeat(new_url,i)==-1: + new_url.append(i) + new_url_js[str(new_url_int)]=i + new_url_int+=1 + + #pending + image_url_str=json.dumps(image_url_js) + new_url_str=json.dumps(new_url_js) + return_js['images']=image_url_str + return_js['newurls']=new_url_str + + #对新url评分 + new_urlscore_js={} + new_urldomain_js={} + new_url_int=0 + for i in new_url: + score=100 + try : + te=urlparse(i) + + #根url + if(te.path==''): + score+=10 + if(te.path=='/'): + score+=10 + + #是否站内url + if(te.netloc==domain): + score-=10 + else: + score+=10 + thisurlscore+=5#站外url加分 + + #是否带参数 + if(te.query!=''): + score-=10 + + #是否带位置 + if(te.fragment!=''): + score-=50 + except: + score=0 + + new_urlscore_js[str(new_url_int)]=score + new_urldomain_js[str(new_url_int)]=te.netloc + new_url_int+=1 + + new_urlscore_js_str=json.dumps(new_urlscore_js) + new_urldomain_js_str=json.dumps(new_urldomain_js) + return_js['newurlscore']=new_urlscore_js_str + return_js['newurldomain']=new_urldomain_js_str + + + + #获取标题 + get_htmlx_title='([\s\S]*?)' + htmlx_title=re.findall(get_htmlx_title,htmlx) + if(len(htmlx_title)>0): + return_js['title']=htmlx_title[0] + print(htmlx_title) + else: + return_js['title']=return_js['url'] + + #get all mate + get_htmlx_mate_lab='' + htmlx_mate_lab=re.findall(get_htmlx_mate_lab,htmlx) + htmlx_mate=[] + htmlx_mate_str="" + htmlx_mate_js={} + for i in htmlx_mate_lab: + get_htmlx_mate_name='name="([\S ]*?)"' + htmlx_mate_name=re.findall(get_htmlx_mate_name,i) + if len(htmlx_mate_name)==1:#只允许有1个名字 其他阴间标签不要 + get_htmlx_mate_val='content="([\S\s]*?)"' + htmlx_mate_val=re.findall(get_htmlx_mate_val,i) + if len(htmlx_mate_val)==1: + if htmlx_mate_name[0]!='': + #print(htmlx_mate_name[0]) + #print(htmlx_mate_val[0]) + #htmlx_mate_str+="\""+htmlx_mate_name[0]+"\":\""+htmlx_mate_val[0]+"\"," + htmlx_mate_js[htmlx_mate_name[0]]=htmlx_mate_val[0] + htmlx_mate.append(htmlx_mate_val[0]) + htmlx_mate_str=json.dumps(htmlx_mate_js) + return_js['mate']=htmlx_mate_str + + #获取所有标签内容 + get_htmlx_all_tab='>([\s\S]*?)<' + htmlx_tab=re.findall(get_htmlx_all_tab,htmlx) + #print(htmlx_tab) + + #inpute mate + for i in htmlx_mate: + htmlx_tab.append(i) + + #先干掉\r\n\t 保留其他标点符号做语义识别 + get_text_rnt=['\r','\n','\t',' '] + htmlx_tab_len=len(htmlx_tab) + for i in range(htmlx_tab_len-1,-1,-1):#从后往前数 + for t in get_text_rnt:htmlx_tab[i]=htmlx_tab[i].replace(t,"") + htmlx_tab[i]=htmlx_tab[i].strip() + if htmlx_tab[i]=='':del htmlx_tab[i]#删除空 + #print(htmlx_tab) + + get_htmlx_BDFH=["\"","\\","^","’","=","/","、","“","”","#","©","|","_","-"," ","*",";","&","$","%","!","?",",",".","(",")","[","]","{","}","<",">","￥","%","！","？","，","。","（","）","【","】","《","》","："] + #提取关键词 + htmlx_sents_js={} + htmlx_words_js={} + sents=[] + words=[] + words_int=0 + links_js={} + links_int=0 + sents_int=0 + for i in range(len(htmlx_tab)): + sent=htmlx_tab[i] #获取每个句子 + word=jieba.cut_for_search(sent)#从每个句子获取单词 + #数据库限制每个句子256字符 + sent=sent[0:256] + if det.repeat(sents,sent)==-1: #查重 + sents.append(sent) + htmlx_sents_js[str(sents_int)]=sent + + for t in word: + #删除一些意义不大的符号 + #数据库限制每个单词8字符 + w=t[0:8] + for n in get_htmlx_BDFH: + w=w.replace(n,"") + if w!='': + words_det_int=-1 + words_det_int=det.repeat(words,w) + if words_det_int==-1: + words.append(w) + words_det_int=words_int + htmlx_words_js[str(words_int)]=w + words_int+=1 + links_js[str(links_int)]=str(words_det_int)+":"+str(sents_int) + links_int+=1 + sents_int+=1 + else: + #重复的内容 + thisurlscore-=1 + + return_js['sents_int']=sents_int + return_js['words_int']=words_int + return_js['links_int']=links_int + + htmlx_sents_str=json.dumps(htmlx_sents_js) + htmlx_words_str=json.dumps(htmlx_words_js) + links_str=json.dumps(links_js) + + return_js['sents']=htmlx_sents_str + return_js['words']=htmlx_words_str + return_js['links']=links_str + + return_js['htmlx']=htmlx_kuaizhao + return_js['score']=thisurlscore#对当前url评分 + else: + return_js['title']=return_js['url'] + return return_js + + + + + + + + +test=0 + +getone={} +getone['password']="(*&RV^*(&VRH*(V)))" +getone_post_url="https://lmve.net/php/getoneurl.php" +post_url="https://lmve.net/php/newurlreptile.php" + +if test==0: + while 1: + print("**本地消息**\n获取url..") + try: + r = requests.post(getone_post_url,data=getone) + if r.status_code==200: + html_byt=r.content + html_text=str(html_byt,'utf-8') + print("获取url成功:") + print(html_text) + print("\n") + r.close() + if html_text!='': + print("获取text..") + text=net.get_html(html_text) + print("开始分析..") + postdata=net.ana_html(text) + print("分析完成") + postdata['password']="(*&RV^*(&VRH*(V)))" + if postdata['contenttype']=='text/html': + print("分离数据成功") + print("url:") + print(postdata['url']) + print("status code:") + print(postdata['status']) + print("content type:") + print(postdata['contenttype']) + print("Title:") + print(postdata['title']) + print("Sents const:") + print(postdata['sents_int']) + print("Words const:") + print(postdata['words_int']) + print("Links const:") + print(postdata['links_int']) + else : + print("分离数据成功 no html") + print("url:") + print(postdata['url']) + print("status code:") + print(postdata['status']) + print("content type:") + print(postdata['contenttype']) + print("开始发送..") + try: + r1 = requests.post(post_url,data=postdata) + if r1.status_code==200: + html_byt=r1.content + html_text=str(html_byt,'utf-8') + print("发送成功:200") + print(html_text) + r1.close() + else: + print("error"+str(r1.status_code)) + except: + print("try aga") + else: + print("获取url失败") + except: + print("tyr agin") + + + + + +if test==1: + postdata=net.ana_html(net.get_html("https://www.foreverblog.cn/blog/1958.html")) + postdata['password']="(*&RV^*(&VRH*(V)))" + r1 = requests.post(post_url,data=postdata) + if r1.status_code==200: + html_byt=r1.content + html_text=str(html_byt,'utf-8') + print("发送成功:200\n") + print(html_text) + r1.close() + else: + print("error"+str(r1.status_code)) diff --git a/post.py b/post.py new file mode 100644 index 0000000..218e9c2 --- /dev/null +++ b/post.py @@ -0,0 +1,19 @@ +# encoding:utf-8 +import requests +def main(): + post_url="https://lmve.net/php/reptile.php" + headers = { + 'user-agent': 'my-app/0.0.1', + 'Content-Type': 'text/html; charset=utf-8' + } + data={} + data['password']="adswewd" + + r = requests.post(post_url,data=data) + if r.status_code!=200: + return r.status_code + html_byt=r.content + html=str(html_byt,'utf-8') + print(html) + +main() \ No newline at end of file diff --git a/reptile.py b/reptile.py new file mode 100644 index 0000000..93b3fea --- /dev/null +++ b/reptile.py @@ -0,0 +1,374 @@ +# encoding:utf-8 +#简易爬虫 + +# requests 用于下载网页源码 第三方库 通过pip安装 +# re 正则表达式要用到 +# threading 启用多线程 +# os，sys 用于创建目录 +# time 用于获得当天时间 +from asyncio.windows_events import NULL +import requests +import re +import jieba +import html +import json +from myfunsion import myfunsion +#from bs4 import BeautifulSoup as bs +#from lxml import etree + +def det_image(url): + style_type_list=[".jpg",".jpeg",".png",".gif"] + #将url转小写 + url=url.lower() + for i in style_type_list: + if i in url: + return True + return False + +def det_style(url): + style_type_list=[".js",".css"] + url=url.lower() + for i in style_type_list: + if i in url: + return True + return False + +def det_repeat(arr,i): + b=0 + for a in arr: + if a==i: + return b + b+=1 + return -1 + +def get_page_words(url): + + retunrn_js={} + begin_url=url + headers = { + 'user-agent': 'my-app/0.0.1', + 'Content-Type': 'text/html; charset=utf-8' + } + + retunrn_js['url']=begin_url + #print(begin_url) + #获取整个页面 + try: + r = requests.get(begin_url,headers=headers,verify=False) + retunrn_js['status']=r.status_code + get_content_type='text/html' + content_type=re.findall(get_content_type,r.headers['Content-Type']) + if(len(content_type)==0): + retunrn_js['contenttype']=r.headers['Content-Type'] + else: + retunrn_js['contenttype']=get_content_type + + get_gb2312='gb2312' + charset=re.findall(get_gb2312,r.headers['Content-Type']) + if(len(charset)==0): + charset_type='utf-8' + else: + charset_type='gb2312' + + if(retunrn_js['contenttype']=='text/html'): + + htmlx_byt=r.content + htmlx=str(htmlx_byt,charset_type) + #print(htmlx) + + #获取js + get_htmlx_js='' + htmlx_js=re.findall(get_htmlx_js,htmlx) + #清除htmlx js + for i in htmlx_js: + htmlx=htmlx.replace(i,"") + + htmlx_kuaizhao=html.escape(htmlx) #干掉js后截取快照 + htmlx_yasuo=["\n","\r","\t"," "] + for i in htmlx_yasuo: + htmlx_kuaizhao=htmlx_kuaizhao.replace(i,"")#压缩一下 + + #获取style + get_htmlx_style='' + htmlx_style=re.findall(get_htmlx_style,htmlx) + #print(htmlx_style) + #清除htmlx style + for i in htmlx_style: + htmlx=htmlx.replace(i,"") + + #print(htmlx) + + #获取textarea ,像百度这样的阴间网站有隐藏的输入框里面会有样式什么的奇怪东西 + get_htmlx_textarea='' + htmlx_textarea=re.findall(get_htmlx_textarea,htmlx) + for i in htmlx_textarea: + htmlx=htmlx.replace(i,"") + + #获取页面中的url并分类 + get_url=r'"(http[s]?://[\S]*)"' + all_url=re.findall(get_url,htmlx) + style_url_list=[] + image_url_list=[] + new_url_list=[] + for i in all_url: + if det_style(i): + style_url_list.append(i) + else: + if det_image(i): + image_url_list.append(i) + else: + new_url_list.append(i) + + #干掉url + image_url=[] + new_url=[] + image_url_js={} + new_url_js={} + image_url_int=0 + new_url_int=0 + for i in style_url_list: + htmlx=htmlx.replace(i,"") + for i in image_url_list: + htmlx=htmlx.replace(i,"") + if det_repeat(image_url,i)==-1: + image_url.append(i) + image_url_js[str(image_url_int)]=i + image_url_int+=1 + for i in new_url_list: + htmlx=htmlx.replace(i,"") + if det_repeat(new_url,i)==-1: + new_url.append(i) + new_url_js[str(new_url_int)]=i + new_url_int+=1 + + image_url_str=json.dumps(image_url_js) + new_url_str=json.dumps(new_url_js) + + #获取标签内容 + #soup=bs(htmlx,'htmlx.parser') + #dom = etree.htmlx(htmlx) + #print(soup.body) + + #获取标题 + get_htmlx_title='([\s\S]*?)' + htmlx_title=re.findall(get_htmlx_title,htmlx) + #print(htmlx_title) + + #get all mate + get_htmlx_mate_lab='' + htmlx_mate_lab=re.findall(get_htmlx_mate_lab,htmlx) + htmlx_mate=[] + htmlx_mate_str="" + htmlx_mate_js={} + for i in htmlx_mate_lab: + get_htmlx_mate_name='name="([\S ]*?)"' + htmlx_mate_name=re.findall(get_htmlx_mate_name,i) + if len(htmlx_mate_name)==1:#只允许有1个名字 其他阴间标签不要 + get_htmlx_mate_val='content="([\S\s]*?)"' + htmlx_mate_val=re.findall(get_htmlx_mate_val,i) + if len(htmlx_mate_val)==1: + if htmlx_mate_name[0]!='': + #print(htmlx_mate_name[0]) + #print(htmlx_mate_val[0]) + #htmlx_mate_str+="\""+htmlx_mate_name[0]+"\":\""+htmlx_mate_val[0]+"\"," + htmlx_mate_js[htmlx_mate_name[0]]=htmlx_mate_val[0] + htmlx_mate.append(htmlx_mate_val[0]) + htmlx_mate_str=json.dumps(htmlx_mate_js) + + #获取所有标签内容 + get_htmlx_all_tab='>([\s\S]*?)<' + htmlx_tab=re.findall(get_htmlx_all_tab,htmlx) + #print(htmlx_tab) + + #inpute mate + for i in htmlx_mate: + htmlx_tab.append(i) + + #先干掉\r\n\t 保留其他标点符号做语义识别 + get_text_rnt=['\r','\n','\t',' '] + htmlx_tab_len=len(htmlx_tab) + for i in range(htmlx_tab_len-1,-1,-1):#从后往前数 + for t in get_text_rnt:htmlx_tab[i]=htmlx_tab[i].replace(t,"") + htmlx_tab[i]=htmlx_tab[i].strip() + if htmlx_tab[i]=='':del htmlx_tab[i]#删除空 + #print(htmlx_tab) + + get_htmlx_BDFH=["\"","\\","^","’","=","/","、","“","”","#","©","|","_","-"," ","*",";","&","$","%","!","?",",",".","(",")","[","]","{","}","<",">","￥","%","！","？","，","。","（","）","【","】","《","》","："] + #提取关键词 + htmlx_sents_js={} + htmlx_words_js={} + sents=[] + words=[] + words_int=0 + links_js={} + links_int=0 + sents_int=0 + for i in range(len(htmlx_tab)): + sent=htmlx_tab[i] #获取每个句子 + word=jieba.cut_for_search(sent)#从每个句子获取单词 + #数据库限制每个句子256字符 + sent=sent[0:256] + if det_repeat(sents,sent)==-1: #查重 + sents.append(sent) + htmlx_sents_js[str(sents_int)]=sent + + for t in word: + #删除一些意义不大的符号 + #数据库限制每个单词8字符 + w=t[0:8] + for n in get_htmlx_BDFH: + w=w.replace(n,"") + if w!='': + words_det_int=-1 + words_det_int=det_repeat(words,w) + if words_det_int==-1: + words.append(w) + words_det_int=words_int + htmlx_words_js[str(words_int)]=w + words_int+=1 + links_js[str(links_int)]=str(words_det_int)+":"+str(sents_int) + links_int+=1 + sents_int+=1 + + htmlx_sents_str=json.dumps(htmlx_sents_js) + htmlx_words_str=json.dumps(htmlx_words_js) + links_str=json.dumps(links_js) + + + + if len(htmlx_title)==0: + retunrn_js['title']=begin_url + else: + retunrn_js['title']=htmlx_title[0] + retunrn_js['mate']=htmlx_mate_str + retunrn_js['sents']=htmlx_sents_str + retunrn_js['words']=htmlx_words_str + retunrn_js['links']=links_str + retunrn_js['images']=image_url_str + retunrn_js['new_url']=new_url_str + retunrn_js['htmlx']=htmlx_kuaizhao + + print("分离数据成功") + print("url:") + print(retunrn_js['url']) + print("status code:") + print(retunrn_js['status']) + print("content type:") + print(retunrn_js['contenttype']) + print("Title:") + print(retunrn_js['title']) + print("Sents const:") + print(sents_int) + print("Words const:") + print(words_int) + print("Links const:") + print(links_int) + else: + retunrn_js['title']=begin_url + print("分离数据成功 no html") + print("url:") + print(retunrn_js['url']) + print("status code:") + print(retunrn_js['status']) + print("content type:") + print(retunrn_js['contenttype']) + print("Title:") + print(retunrn_js['title']) + r.close() + except: + print("连接失败") + retunrn_js['status']=0 + retunrn_js['contenttype']="Cant connect" + + + return retunrn_js + + +def getandpost(bgurl): + page_data={} + page_data=get_page_words(bgurl) + page_data['password']="(*&RV^*(&VRH*(V)))" + print("本地爬取完成,开始发送\n") + post_url="https://lmve.net/php/reptile.php" + r1 = requests.post(post_url,data=page_data) + if r1.status_code==200: + html_byt=r1.content + html_text=str(html_byt,'utf-8') + print("发送成功:200\n") + print(html_text) + r1.close() + else: + print("error"+str(r.status_code)) + +def getoneurl(): + page_data={} + page_data['password']="(*&RV^*(&VRH*(V)))" + post_url="https://lmve.net/php/getoneurl.php" + try : + r = requests.post(post_url,data=page_data) + if r.status_code==200: + html_byt=r.content + html_text=str(html_byt,'utf-8') + print("获取url成功:") + print(html_text) + print("\n") + r.close() + return html_text + else: + print("获取url失败\n") + return "-1" + except: + print("获取url失败\n") + return "-1" + + + +test=1 + +if test==0: + while 1: + theurl=getoneurl() + if theurl!='-1': + getandpost(theurl) + else : + print("获取url失败,自动重试") + +if test==1: + theurl="https://lmve.net" + getandpost(theurl) + +if test==2: + theurl=getoneurl() + print(theurl) + getandpost(theurl) + +if test==3: + headers = { + 'user-agent': 'my-app/0.0.1', + 'Content-Type': 'text/html; charset=utf-8' + } + + #print(begin_url) + #获取整个页面 + url1="https://git.lmve.net/kevin/um-all-index-web/-/avatar" + url2="https://yyyyyyounger.com/" + try : + r = requests.get(url2,headers=headers,verify=False) + htmlx_byt=r.content + print(r.headers['Content-Type']) + except: + print("11") +if test==4: + #js=get_page_words("https://lmve.net") + #print(js) + myfunsion.a() + + + + + + + + + + diff --git a/test.txt b/test.txt new file mode 100644 index 0000000..16b0a2e --- /dev/null +++ b/test.txt @@ -0,0 +1,6 @@ +百度一下，你就知道