toolboxs 0.1.0

A box-ah package for python

toolboxs

介绍

工具箱

软件架构

软件架构说明

安装教程

pip install toolboxs

或者 pip install toolboxs==xx.xx.xx

使用说明

项目结构

项目名
├── source
│   ├── 资源文件
├── src
│   ├── 程序1.py
│   ├── 程序2.py
│   ├── 程序3.py

request_session 模块

普通的GET请求

import os
from src.request_session import Request,RequestModule

if __name__ == "__main__" :
    with Request(os.path.abspath(__file__)) as request:
        def callback(resp):
            print(resp.text)
        
        request.send(url='https://www.4399.com/',module=RequestModule.GET)(callback)

运行结束之后，会在 source 目录下自动创建 log 目录，并记录当天的 请求日志

(reptile_env) box-ah-test tree source        
source
└── log
    └── request
        └── 程序名称-日期(yyyyMMdd).log

使用 xpath

在模块内部，已经封装了 lxml 的 xpath 方法，可以直接使用

def xpath(self,xpath_str) -> list:
    if self.response.status_code == requests.codes.ok:
        # 解决中文乱码问题
        self.response.encoding =  self.response.apparent_encoding
        html = etree.HTML(self.response.text,parser=None)
        return html.xpath(xpath_str)
    return []

示例如下；

import os
from src.network.request_session import Request,RequestModule

if __name__ == "__main__" :
    with Request(os.path.abspath(__file__),response_logging=False) as request:
        
        request.send(url='https://www.4399.com/',module=RequestModule.GET)
        
        a_list = request.xpath("//ul[@class='tm_list']/li/a")
        
        for a in a_list:
            print(a.xpath("./img/@alt")[0])
            print(a.xpath("./img/@src"))

将m3u8 转换成 视频代码示例 该功能依赖 ffmpeg 插件，完成对ts文件的合并

import os
import re
import json
from urllib.parse import urljoin
from src.network.download import M3u82Video
from src.network.request_session import Request,FileType,DataType


if __name__ == "__main__" :
    global_headers = {
        'Connection':'close',
        'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36'
    }
    
    project_file = os.path.abspath(__file__)
    
    with Request(project_file=project_file,response_logging=False,global_headers=global_headers) as  request:
    
        
        
        def get_m3u8_url(resp):
            js = request.execjs('m1905')
            
            p = js.call('build',584320,resp.url)
            
            def callback(resp):
                result:dict = request.parse_jsonp(resp.text)
                data:dict = result.get('data',{})
                host = data.get('quality',{}).get('uhd',{}).get('host')
                path = data.get('path',{}).get('uhd',{}).get('path')
                sign = data.get('sign',{}).get('uhd',{}).get('sign')
                
                m3u8_url:str = f'{host}{sign}{path}'
                
                def e(resp):
                    return list(filter(lambda x:x.endswith('m3u8'),resp.text.split('\n')))[0]
                
                m3u8_url = urljoin(m3u8_url,request.send(url=m3u8_url)(e))
                
                
                return m3u8_url
                
                
            return request.send(
                url='https://profile.m1905.com/mvod/getVideoinfo.php',
                params=p
            )(callback)
            
    
        def parse_ts_callback(url,line:str):
            return urljoin(url,line.replace('\n',''))
            
        sink = M3u82Video(request,m3u8_file_path='video/77dus',restart=True)
        sink.save_m3u8_file(web_url='https://www.1905.com/vod/play/584320.shtml?fr=vodnd_jrrb',callback=get_m3u8_url)
        sink.parse_m3u8_file(parse_ts_callback)
        sink.save2mp4('video','a')

sink2excel 示例代码

from src.sink.sink2excel import Sink2Excel,Cell,Row,CellPosition,CellDataType

if __name__ == "__main__" :
    with Sink2Excel() as excel:
        rows = [
            Row(
                Cell(val='姓名',subrows=[Row(Cell(val=''))],position=CellPosition.position_distributed),
                Cell(val='性别',subrows=[Row(Cell(val=''))],position=CellPosition.position_distributed),
                Cell(val='出生年月',subrows=[Row(Cell(val=''))],position=CellPosition.position_distributed),
                Cell(val='https://pics7.baidu.com/feed/96dda144ad345982bb1fa56dcbba18a3caef8410.jpeg@f_auto?token=c9ca84004bd6180ef43678b653a0f4f8',data_type=CellDataType.PIC,row_size=3)
            ),
            Row(
                Cell(val='身份证号码',subrows=[Row(Cell(val=''))],position=CellPosition.position_distributed),
                Cell(val='名族',subrows=[Row(Cell(val=''))],position=CellPosition.position_distributed),
                Cell(val='政治面貌',subrows=[Row(Cell(val=''))],position=CellPosition.position_distributed),
                row_index=4
            ),
            Row(
                Cell(val='婚姻状况',subrows=[Row(Cell(val=''))],position=CellPosition.position_distributed),
                Cell(val='健康状况',subrows=[Row(Cell(val=''))],position=CellPosition.position_distributed),
                Cell(val='身高',subrows=[Row(Cell(val=''))],position=CellPosition.position_distributed),
            ),
            Row(
                Cell(val='现户口所在地',subrows=[Row(Cell(val='',col_size=2))],position=CellPosition.position_distributed),
                Cell(val='所学专业',subrows=[Row(Cell(val='',col_size=1))],position=CellPosition.position_distributed),
                Cell(val='学历',subrows=[Row(Cell(val='',col_size=1))],position=CellPosition.position_distributed),
            ),
            Row(
                Cell(val='最后毕业学校',subrows=[Row(Cell(val='',col_size=2))],position=CellPosition.position_distributed),
                Cell(val='毕业时间',subrows=[Row(Cell(val='',col_size=1))],position=CellPosition.position_distributed),
                Cell(val='技术职称',subrows=[Row(Cell(val='',col_size=1))],position=CellPosition.position_distributed),
            ),
            Row(
                Cell(val='现工作单位',subrows=[Row(Cell(val='',col_size=2))],position=CellPosition.position_distributed),
                Cell(val='参考工作时间',subrows=[Row(Cell(val='',col_size=1))],position=CellPosition.position_distributed),
                Cell(val='现从事专业',subrows=[Row(Cell(val='',col_size=1))],position=CellPosition.position_distributed),
            ),
            Row(
                Cell(val='https://img1.baidu.com/it/u=842682090,490249809&fm=253&fmt=auto&app=138&f=JPEG?w=854&h=416',data_type=CellDataType.PIC,row_size=11,col_size=4,subrows=[
                    Row(
                        Cell(val='现工作单位',subrows=[Row(Cell(val='',col_size=2))],position=CellPosition.position_distributed)
                    ),
                    Row(
                        Cell(val='现工作单位',subrows=[Row(Cell(val='',col_size=2))],position=CellPosition.position_distributed)
                    )])),
            
        ]
        
        excel.write(
            headers=Row(Cell(val='个人简历',col_size=7,row_size=2)),
            rows=rows,
            sequence=False
        )
        excel.sink_file('xxxx/xxx/xx/yyyy.xlsx')

参与贡献

1. Fork 本仓库
2. 新建 Feat_xxx 分支
3. 提交代码
4. 新建 Pull Request

特技

1. 使用 Readme_XXX.md 来支持不同的语言，例如 Readme_en.md, Readme_zh.md
2. Gitee 官方博客 blog.gitee.com
3. 你可以 https://gitee.com/explore 这个地址来了解 Gitee 上的优秀开源项目
4. GVP 全称是 Gitee 最有价值开源项目，是综合评定出的优秀开源项目
5. Gitee 官方提供的使用手册 https://gitee.com/help
6. Gitee 封面人物是一档用来展示 Gitee 会员风采的栏目 https://gitee.com/gitee-stars/