..

Dockerfile

@@ -0,0 +1,15 @@
+FROM python:3.10-slim-buster
+
+WORKDIR /usr/src/app
+
+ENV PYTHONDONTWRITEBYTECODE 1
+ENV PYTHONUNBUFFERED 1
+
+COPY . /usr/src/app
+
+# install python dependencies
+RUN pip install --upgrade pip 
+RUN pip install --no-cache-dir -r requirements.txt
+
+# 6. Python main.py 파일을 실행합니다.
+CMD ["python", "main.py"]

README.md

@@ -1,7 +1,24 @@
 # wp-post-automation
-워드프레스 포스팅 자동화 프로젝트.
-make.com을 이용해서 만든 AutoMation Flow를 Python을 이용하여 변환.
-## 기존 Flow
+## 목적
+* 워드프레스 포스팅 자동화 기능 구현.
+
+## 주요내용
+### 프로젝트 소개
+2025.01.19 - 네이버 블로그 스크랩 및 워드프레스 임시글 등록 기능 구현
+* 초기 기능 구현 완료.
+2024.10.04 - 테스트 완료. 프로젝트 1차 종료.
+* 워드프레스 포스팅 자동화 프로젝트.
+* make.com을 이용해서 만든 AutoMation Flow를 Python을 이용하여 변환.
+
+### 사용방법
+* sample.env.dev를 복사하여 루트 디렉토리에 .env.prd | .env.dev | .env 중 하나로 생성하여 사용 합니다.
+* main.py가 기본 자동화 프로세스 입니다.
+    * 크롤링된 게시물을 OpenAI가 변형하여 마크다운으로 등록합니다.
+* main_naver_blog_html은 네이버 블로그 전용 프로세스 입니다.
+    * 크롤링된 게시물을 그대로 마크다운으로 등록합니다.
+
+---
+## 참고 워크 플로우
 * MariaDB에 저장된 최신 참고 url정보를 얻어온다.
 * HTTP모듈을 이용하여 참고 자료를 가져온다.
 * 가져온 HTML형태의 자료를 Text만 추출한다.
@@ -13,23 +30,48 @@ make.com을 이용해서 만든 AutoMation Flow를 Python을 이용하여 변환
 * WordPress에 포스팅을 한다.
 
 ## 개발 계획
+### 2025.01.19
+* 네이버 블로그 포스트를 크롤링한다.
+* API로 워드프레스에 임시글로 등록한다.
+### 2024.10.04
 * 기존 Flow를 Python으로 개발한다.
 * 트리거가 발생하면 실행시키는 컨테이너로 빌드한다.
 * kubectl create -f file.yaml을 이용하여 1회성 동작 하도록 구현한다.
 
-### Python 개발 순서
-* DB에서 url을 가져오는 코드작성.
-* url을 이용해서 파싱하고 텍스트만 추출하는 기능 구현.
-* OpenAI이용 코드 작성.
-* HTML문서 변환 코드 작성.
-* 워드프레스 등록 플로우 코드 작성.
-* 코드 리팩토링.
+## Python 개발 순서
+### 2025.01.19
+* 현재 DB연동 기능은 없음. 실행시키면 URL을 넣어야동작합니다(완료).
+* url을 이용해서 파싱하고 텍스트만 추출하는 기능 구현(완료).
+* 마크다운 형태로 추출(완료).
+* HTML문서 변환 코드 작성(완료).
+* 워드프레스 API를 이용한 임시 포스트 등록(완료).
+### 2024.10.04
+* DB에서 url을 가져오는 코드작성(완료).
+* url을 이용해서 파싱하고 텍스트만 추출하는 기능 구현(완료).
+* OpenAI이용 코드 작성(완료)-비용 절감을 위하여 제목, 이미지 생성 제외.
+* HTML문서 변환 코드 작성(완료).
+* 워드프레스 등록 플로우 코드 작성(완료).
+
+## 코드 리팩토링.
+### 2024.10.04
+* 전체 리팩토링(완료).
+* 모듈화, 패키지화(완료).
+
+## Docker Image Build
+### 2024.10.04 업데이트
+* Dockerfile 추가(완료).
+
+## Kubernetes manifests
+### 2024.10.04 업데이트
+* 샘플 템플릿 작성(완료)
+* 쿠버네티스 환경 테스트(완료).
+
+---
 
 ## 코드 이슈
-### 네이버 블로그 크롤링
-2024.10.02 기준
-* 현재 일반 뉴스 기사는 잘 동작되는 것으로 보임.
-* 네이버 블로그는 js이슈로 크롤링이 안되는 것으로 추측. selenium검토 필요.
+* 특이사항 없음.
+
+---
 
 ## 라이선스 
 ### 라이선스 검토 대상

archived/_archived_main_naver_blog_text.py

@@ -0,0 +1,37 @@
+import requests
+from bs4 import BeautifulSoup
+
+def get_naver_blog_content(url):
+    # 네이버 블로그의 모바일 버전으로 리다이렉트
+    mobile_url = url.replace("blog.naver.com", "m.blog.naver.com")
+    
+    headers = {
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
+    }
+    
+    # HTTP 요청
+    response = requests.get(mobile_url, headers=headers)
+    
+    if response.status_code != 200:
+        print(f"Failed to fetch the page: {response.status_code}")
+        return None
+    
+    # BeautifulSoup으로 HTML 파싱
+    soup = BeautifulSoup(response.text, 'html.parser')
+    
+    # 본문 추출 (모바일 버전의 본문 클래스 사용)
+    content = soup.find("div", class_="se-main-container")
+    
+    if content:
+        return content.get_text(strip=True)
+    else:
+        print("Failed to extract the blog content.")
+        return None
+
+# 예제 URL
+url = "https://blog.naver.com/kte1909/223724132196"
+blog_content = get_naver_blog_content(url)
+
+if blog_content:
+    print("Blog Content:")
+    print(blog_content)

bin/Activate.ps1

@@ -0,0 +1,247 @@
+<#
+.Synopsis
+Activate a Python virtual environment for the current PowerShell session.
+
+.Description
+Pushes the python executable for a virtual environment to the front of the
+$Env:PATH environment variable and sets the prompt to signify that you are
+in a Python virtual environment. Makes use of the command line switches as
+well as the `pyvenv.cfg` file values present in the virtual environment.
+
+.Parameter VenvDir
+Path to the directory that contains the virtual environment to activate. The
+default value for this is the parent of the directory that the Activate.ps1
+script is located within.
+
+.Parameter Prompt
+The prompt prefix to display when this virtual environment is activated. By
+default, this prompt is the name of the virtual environment folder (VenvDir)
+surrounded by parentheses and followed by a single space (ie. '(.venv) ').
+
+.Example
+Activate.ps1
+Activates the Python virtual environment that contains the Activate.ps1 script.
+
+.Example
+Activate.ps1 -Verbose
+Activates the Python virtual environment that contains the Activate.ps1 script,
+and shows extra information about the activation as it executes.
+
+.Example
+Activate.ps1 -VenvDir C:\Users\MyUser\Common\.venv
+Activates the Python virtual environment located in the specified location.
+
+.Example
+Activate.ps1 -Prompt "MyPython"
+Activates the Python virtual environment that contains the Activate.ps1 script,
+and prefixes the current prompt with the specified string (surrounded in
+parentheses) while the virtual environment is active.
+
+.Notes
+On Windows, it may be required to enable this Activate.ps1 script by setting the
+execution policy for the user. You can do this by issuing the following PowerShell
+command:
+
+PS C:\> Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser
+
+For more information on Execution Policies: 
+https://go.microsoft.com/fwlink/?LinkID=135170
+
+#>
+Param(
+    [Parameter(Mandatory = $false)]
+    [String]
+    $VenvDir,
+    [Parameter(Mandatory = $false)]
+    [String]
+    $Prompt
+)
+
+<# Function declarations --------------------------------------------------- #>
+
+<#
+.Synopsis
+Remove all shell session elements added by the Activate script, including the
+addition of the virtual environment's Python executable from the beginning of
+the PATH variable.
+
+.Parameter NonDestructive
+If present, do not remove this function from the global namespace for the
+session.
+
+#>
+function global:deactivate ([switch]$NonDestructive) {
+    # Revert to original values
+
+    # The prior prompt:
+    if (Test-Path -Path Function:_OLD_VIRTUAL_PROMPT) {
+        Copy-Item -Path Function:_OLD_VIRTUAL_PROMPT -Destination Function:prompt
+        Remove-Item -Path Function:_OLD_VIRTUAL_PROMPT
+    }
+
+    # The prior PYTHONHOME:
+    if (Test-Path -Path Env:_OLD_VIRTUAL_PYTHONHOME) {
+        Copy-Item -Path Env:_OLD_VIRTUAL_PYTHONHOME -Destination Env:PYTHONHOME
+        Remove-Item -Path Env:_OLD_VIRTUAL_PYTHONHOME
+    }
+
+    # The prior PATH:
+    if (Test-Path -Path Env:_OLD_VIRTUAL_PATH) {
+        Copy-Item -Path Env:_OLD_VIRTUAL_PATH -Destination Env:PATH
+        Remove-Item -Path Env:_OLD_VIRTUAL_PATH
+    }
+
+    # Just remove the VIRTUAL_ENV altogether:
+    if (Test-Path -Path Env:VIRTUAL_ENV) {
+        Remove-Item -Path env:VIRTUAL_ENV
+    }
+
+    # Just remove VIRTUAL_ENV_PROMPT altogether.
+    if (Test-Path -Path Env:VIRTUAL_ENV_PROMPT) {
+        Remove-Item -Path env:VIRTUAL_ENV_PROMPT
+    }
+
+    # Just remove the _PYTHON_VENV_PROMPT_PREFIX altogether:
+    if (Get-Variable -Name "_PYTHON_VENV_PROMPT_PREFIX" -ErrorAction SilentlyContinue) {
+        Remove-Variable -Name _PYTHON_VENV_PROMPT_PREFIX -Scope Global -Force
+    }
+
+    # Leave deactivate function in the global namespace if requested:
+    if (-not $NonDestructive) {
+        Remove-Item -Path function:deactivate
+    }
+}
+
+<#
+.Description
+Get-PyVenvConfig parses the values from the pyvenv.cfg file located in the
+given folder, and returns them in a map.
+
+For each line in the pyvenv.cfg file, if that line can be parsed into exactly
+two strings separated by `=` (with any amount of whitespace surrounding the =)
+then it is considered a `key = value` line. The left hand string is the key,
+the right hand is the value.
+
+If the value starts with a `'` or a `"` then the first and last character is
+stripped from the value before being captured.
+
+.Parameter ConfigDir
+Path to the directory that contains the `pyvenv.cfg` file.
+#>
+function Get-PyVenvConfig(
+    [String]
+    $ConfigDir
+) {
+    Write-Verbose "Given ConfigDir=$ConfigDir, obtain values in pyvenv.cfg"
+
+    # Ensure the file exists, and issue a warning if it doesn't (but still allow the function to continue).
+    $pyvenvConfigPath = Join-Path -Resolve -Path $ConfigDir -ChildPath 'pyvenv.cfg' -ErrorAction Continue
+
+    # An empty map will be returned if no config file is found.
+    $pyvenvConfig = @{ }
+
+    if ($pyvenvConfigPath) {
+
+        Write-Verbose "File exists, parse `key = value` lines"
+        $pyvenvConfigContent = Get-Content -Path $pyvenvConfigPath
+
+        $pyvenvConfigContent | ForEach-Object {
+            $keyval = $PSItem -split "\s*=\s*", 2
+            if ($keyval[0] -and $keyval[1]) {
+                $val = $keyval[1]
+
+                # Remove extraneous quotations around a string value.
+                if ("'""".Contains($val.Substring(0, 1))) {
+                    $val = $val.Substring(1, $val.Length - 2)
+                }
+
+                $pyvenvConfig[$keyval[0]] = $val
+                Write-Verbose "Adding Key: '$($keyval[0])'='$val'"
+            }
+        }
+    }
+    return $pyvenvConfig
+}
+
+
+<# Begin Activate script --------------------------------------------------- #>
+
+# Determine the containing directory of this script
+$VenvExecPath = Split-Path -Parent $MyInvocation.MyCommand.Definition
+$VenvExecDir = Get-Item -Path $VenvExecPath
+
+Write-Verbose "Activation script is located in path: '$VenvExecPath'"
+Write-Verbose "VenvExecDir Fullname: '$($VenvExecDir.FullName)"
+Write-Verbose "VenvExecDir Name: '$($VenvExecDir.Name)"
+
+# Set values required in priority: CmdLine, ConfigFile, Default
+# First, get the location of the virtual environment, it might not be
+# VenvExecDir if specified on the command line.
+if ($VenvDir) {
+    Write-Verbose "VenvDir given as parameter, using '$VenvDir' to determine values"
+}
+else {
+    Write-Verbose "VenvDir not given as a parameter, using parent directory name as VenvDir."
+    $VenvDir = $VenvExecDir.Parent.FullName.TrimEnd("\\/")
+    Write-Verbose "VenvDir=$VenvDir"
+}
+
+# Next, read the `pyvenv.cfg` file to determine any required value such
+# as `prompt`.
+$pyvenvCfg = Get-PyVenvConfig -ConfigDir $VenvDir
+
+# Next, set the prompt from the command line, or the config file, or
+# just use the name of the virtual environment folder.
+if ($Prompt) {
+    Write-Verbose "Prompt specified as argument, using '$Prompt'"
+}
+else {
+    Write-Verbose "Prompt not specified as argument to script, checking pyvenv.cfg value"
+    if ($pyvenvCfg -and $pyvenvCfg['prompt']) {
+        Write-Verbose "  Setting based on value in pyvenv.cfg='$($pyvenvCfg['prompt'])'"
+        $Prompt = $pyvenvCfg['prompt'];
+    }
+    else {
+        Write-Verbose "  Setting prompt based on parent's directory's name. (Is the directory name passed to venv module when creating the virtual environment)"
+        Write-Verbose "  Got leaf-name of $VenvDir='$(Split-Path -Path $venvDir -Leaf)'"
+        $Prompt = Split-Path -Path $venvDir -Leaf
+    }
+}
+
+Write-Verbose "Prompt = '$Prompt'"
+Write-Verbose "VenvDir='$VenvDir'"
+
+# Deactivate any currently active virtual environment, but leave the
+# deactivate function in place.
+deactivate -nondestructive
+
+# Now set the environment variable VIRTUAL_ENV, used by many tools to determine
+# that there is an activated venv.
+$env:VIRTUAL_ENV = $VenvDir
+
+if (-not $Env:VIRTUAL_ENV_DISABLE_PROMPT) {
+
+    Write-Verbose "Setting prompt to '$Prompt'"
+
+    # Set the prompt to include the env name
+    # Make sure _OLD_VIRTUAL_PROMPT is global
+    function global:_OLD_VIRTUAL_PROMPT { "" }
+    Copy-Item -Path function:prompt -Destination function:_OLD_VIRTUAL_PROMPT
+    New-Variable -Name _PYTHON_VENV_PROMPT_PREFIX -Description "Python virtual environment prompt prefix" -Scope Global -Option ReadOnly -Visibility Public -Value $Prompt
+
+    function global:prompt {
+        Write-Host -NoNewline -ForegroundColor Green "($_PYTHON_VENV_PROMPT_PREFIX) "
+        _OLD_VIRTUAL_PROMPT
+    }
+    $env:VIRTUAL_ENV_PROMPT = $Prompt
+}
+
+# Clear PYTHONHOME
+if (Test-Path -Path Env:PYTHONHOME) {
+    Copy-Item -Path Env:PYTHONHOME -Destination Env:_OLD_VIRTUAL_PYTHONHOME
+    Remove-Item -Path Env:PYTHONHOME
+}
+
+# Add the venv to the PATH
+Copy-Item -Path Env:PATH -Destination Env:_OLD_VIRTUAL_PATH
+$Env:PATH = "$VenvExecDir$([System.IO.Path]::PathSeparator)$Env:PATH"

bin/activate

@@ -0,0 +1,69 @@
+# This file must be used with "source bin/activate" *from bash*
+# you cannot run it directly
+
+deactivate () {
+    # reset old environment variables
+    if [ -n "${_OLD_VIRTUAL_PATH:-}" ] ; then
+        PATH="${_OLD_VIRTUAL_PATH:-}"
+        export PATH
+        unset _OLD_VIRTUAL_PATH
+    fi
+    if [ -n "${_OLD_VIRTUAL_PYTHONHOME:-}" ] ; then
+        PYTHONHOME="${_OLD_VIRTUAL_PYTHONHOME:-}"
+        export PYTHONHOME
+        unset _OLD_VIRTUAL_PYTHONHOME
+    fi
+
+    # This should detect bash and zsh, which have a hash command that must
+    # be called to get it to forget past commands.  Without forgetting
+    # past commands the $PATH changes we made may not be respected
+    if [ -n "${BASH:-}" -o -n "${ZSH_VERSION:-}" ] ; then
+        hash -r 2> /dev/null
+    fi
+
+    if [ -n "${_OLD_VIRTUAL_PS1:-}" ] ; then
+        PS1="${_OLD_VIRTUAL_PS1:-}"
+        export PS1
+        unset _OLD_VIRTUAL_PS1
+    fi
+
+    unset VIRTUAL_ENV
+    unset VIRTUAL_ENV_PROMPT
+    if [ ! "${1:-}" = "nondestructive" ] ; then
+    # Self destruct!
+        unset -f deactivate
+    fi
+}
+
+# unset irrelevant variables
+deactivate nondestructive
+
+VIRTUAL_ENV=/home/ubuntu/gitea-icurfer/wp-post-automation
+export VIRTUAL_ENV
+
+_OLD_VIRTUAL_PATH="$PATH"
+PATH="$VIRTUAL_ENV/"bin":$PATH"
+export PATH
+
+# unset PYTHONHOME if set
+# this will fail if PYTHONHOME is set to the empty string (which is bad anyway)
+# could use `if (set -u; : $PYTHONHOME) ;` in bash
+if [ -n "${PYTHONHOME:-}" ] ; then
+    _OLD_VIRTUAL_PYTHONHOME="${PYTHONHOME:-}"
+    unset PYTHONHOME
+fi
+
+if [ -z "${VIRTUAL_ENV_DISABLE_PROMPT:-}" ] ; then
+    _OLD_VIRTUAL_PS1="${PS1:-}"
+    PS1='(wp-post-automation) '"${PS1:-}"
+    export PS1
+    VIRTUAL_ENV_PROMPT='(wp-post-automation) '
+    export VIRTUAL_ENV_PROMPT
+fi
+
+# This should detect bash and zsh, which have a hash command that must
+# be called to get it to forget past commands.  Without forgetting
+# past commands the $PATH changes we made may not be respected
+if [ -n "${BASH:-}" -o -n "${ZSH_VERSION:-}" ] ; then
+    hash -r 2> /dev/null
+fi

bin/activate.csh

@@ -0,0 +1,26 @@
+# This file must be used with "source bin/activate.csh" *from csh*.
+# You cannot run it directly.
+# Created by Davide Di Blasi <davidedb@gmail.com>.
+# Ported to Python 3.3 venv by Andrew Svetlov <andrew.svetlov@gmail.com>
+
+alias deactivate 'test $?_OLD_VIRTUAL_PATH != 0 && setenv PATH "$_OLD_VIRTUAL_PATH" && unset _OLD_VIRTUAL_PATH; rehash; test $?_OLD_VIRTUAL_PROMPT != 0 && set prompt="$_OLD_VIRTUAL_PROMPT" && unset _OLD_VIRTUAL_PROMPT; unsetenv VIRTUAL_ENV; unsetenv VIRTUAL_ENV_PROMPT; test "\!:*" != "nondestructive" && unalias deactivate'
+
+# Unset irrelevant variables.
+deactivate nondestructive
+
+setenv VIRTUAL_ENV /home/ubuntu/gitea-icurfer/wp-post-automation
+
+set _OLD_VIRTUAL_PATH="$PATH"
+setenv PATH "$VIRTUAL_ENV/"bin":$PATH"
+
+
+set _OLD_VIRTUAL_PROMPT="$prompt"
+
+if (! "$?VIRTUAL_ENV_DISABLE_PROMPT") then
+    set prompt = '(wp-post-automation) '"$prompt"
+    setenv VIRTUAL_ENV_PROMPT '(wp-post-automation) '
+endif
+
+alias pydoc python -m pydoc
+
+rehash

bin/activate.fish

@@ -0,0 +1,69 @@
+# This file must be used with "source <venv>/bin/activate.fish" *from fish*
+# (https://fishshell.com/); you cannot run it directly.
+
+function deactivate  -d "Exit virtual environment and return to normal shell environment"
+    # reset old environment variables
+    if test -n "$_OLD_VIRTUAL_PATH"
+        set -gx PATH $_OLD_VIRTUAL_PATH
+        set -e _OLD_VIRTUAL_PATH
+    end
+    if test -n "$_OLD_VIRTUAL_PYTHONHOME"
+        set -gx PYTHONHOME $_OLD_VIRTUAL_PYTHONHOME
+        set -e _OLD_VIRTUAL_PYTHONHOME
+    end
+
+    if test -n "$_OLD_FISH_PROMPT_OVERRIDE"
+        set -e _OLD_FISH_PROMPT_OVERRIDE
+        # prevents error when using nested fish instances (Issue #93858)
+        if functions -q _old_fish_prompt
+            functions -e fish_prompt
+            functions -c _old_fish_prompt fish_prompt
+            functions -e _old_fish_prompt
+        end
+    end
+
+    set -e VIRTUAL_ENV
+    set -e VIRTUAL_ENV_PROMPT
+    if test "$argv[1]" != "nondestructive"
+        # Self-destruct!
+        functions -e deactivate
+    end
+end
+
+# Unset irrelevant variables.
+deactivate nondestructive
+
+set -gx VIRTUAL_ENV /home/ubuntu/gitea-icurfer/wp-post-automation
+
+set -gx _OLD_VIRTUAL_PATH $PATH
+set -gx PATH "$VIRTUAL_ENV/"bin $PATH
+
+# Unset PYTHONHOME if set.
+if set -q PYTHONHOME
+    set -gx _OLD_VIRTUAL_PYTHONHOME $PYTHONHOME
+    set -e PYTHONHOME
+end
+
+if test -z "$VIRTUAL_ENV_DISABLE_PROMPT"
+    # fish uses a function instead of an env var to generate the prompt.
+
+    # Save the current fish_prompt function as the function _old_fish_prompt.
+    functions -c fish_prompt _old_fish_prompt
+
+    # With the original prompt function renamed, we can override with our own.
+    function fish_prompt
+        # Save the return status of the last command.
+        set -l old_status $status
+
+        # Output the venv prompt; color taken from the blue of the Python logo.
+        printf "%s%s%s" (set_color 4B8BBE) '(wp-post-automation) ' (set_color normal)
+
+        # Restore the return status of the previous command.
+        echo "exit $old_status" | .
+        # Output the original/"old" prompt.
+        _old_fish_prompt
+    end
+
+    set -gx _OLD_FISH_PROMPT_OVERRIDE "$VIRTUAL_ENV"
+    set -gx VIRTUAL_ENV_PROMPT '(wp-post-automation) '
+end

bin/pip

@@ -0,0 +1,8 @@
+#!/home/ubuntu/gitea-icurfer/wp-post-automation/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from pip._internal.cli.main import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

bin/pip3

@@ -0,0 +1,8 @@
+#!/home/ubuntu/gitea-icurfer/wp-post-automation/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from pip._internal.cli.main import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

bin/pip3.10

@@ -0,0 +1,8 @@
+#!/home/ubuntu/gitea-icurfer/wp-post-automation/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from pip._internal.cli.main import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

bin/python

@@ -0,0 +1 @@
+python3

bin/python3

@@ -0,0 +1 @@
+/usr/bin/python3

bin/python3.10

@@ -0,0 +1 @@
+python3

dev.py

@@ -0,0 +1,79 @@
+import requests
+from bs4 import BeautifulSoup
+from markdownify import markdownify as md
+from package import GetConfig, MariaDB, ChangeTextToPost, WordPress
+import markdown
+
+# 현재 DB연동 기능은 없음. 실행시키면 URL을 넣어야동작합니다.
+def get_naver_blog_content_as_markdown(url):
+    # 네이버 블로그의 모바일 버전으로 리다이렉트
+    mobile_url = url.replace("blog.naver.com", "m.blog.naver.com")
+    
+    # 웹브라우저 위장 --------------------------------------------------
+    # 제외 하여도 이상 없이 동작하여 제외.
+    # headers = {
+    #     "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
+    # }
+    
+    
+    # response = requests.get(mobile_url, headers=headers)
+    # ---------------------------------------------------------------
+    response = requests.get(mobile_url)
+    
+    if response.status_code != 200:
+        print(f"Failed to fetch the page: {response.status_code}")
+        return None
+    
+    # BeautifulSoup으로 HTML 파싱
+    soup = BeautifulSoup(response.text, 'html.parser')
+    
+    # 본문 추출 (모바일 버전의 본문 클래스 사용)
+    content = soup.find("div", class_="se-main-container")
+    
+    if content:
+        html_content = str(content)
+        markdown_content = md(html_content)  # HTML → Markdown 변환
+        
+        # 빈 줄 제거
+        markdown_content = "\n".join([line for line in markdown_content.splitlines() if line.strip()])
+        
+        return markdown_content
+    else:
+        print("Failed to extract the blog content.")
+        return None
+
+
+# 2024-10-03 환경 변수 호출
+print('### Get values From .env')
+config = GetConfig()
+dict_data = config.get_config_as_dict()
+
+# 예제 URL
+url = input("Enter your blog address : ")
+# markdown_content = get_naver_blog_content_as_markdown(url)
+post_article = get_naver_blog_content_as_markdown(url)
+post_article = post_article.replace(">", "###")
+# if markdown_content:
+#     print("Markdown Content:")
+#     print(markdown_content)
+
+    # Markdown 파일로 저장
+    # with open("blog_content.md", "w", encoding="utf-8") as file:
+    #     file.write(markdown_content)
+    # print("Blog content saved as blog_content.md")
+
+# print('### Convert to HTML - markdown to html')
+# # 2024-10-03 Markdown을 HTML로 변환
+# html = markdown.markdown(post_article)
+# # 2024-10-03 워드프레스 포스팅 임시등록
+# print('### Create post')
+# wp = WordPress(dict_data)
+# rs = wp.create_post(2,html)
+
+# if __name__ == "__main__":
+#     # print(post_article)
+#     print("추가 확인을 위한 출력")
+#     if rs.ok:
+#         print(f"### 성공 code:{rs.status_code}")    
+#     else:
+#         print(f"### 실패 code:{rs.status_code} reason:{rs.reason} msg:{rs.text}")

get_url.py

@@ -1,45 +0,0 @@
-import mysql.connector
-from dotenv import load_dotenv
-import os
-
-# .env.demo 파일 로드
-load_dotenv(r'./.env.dev')
-# 환경 변수 가져오기
-host = os.getenv('DB_HOST')
-user = os.getenv('DB_USER')
-password = os.getenv('DB_PASSWORD')
-database = os.getenv('DB_NAME')
-# MariaDB에 연결하는 함수
-def fetch_data_from_mariadb():
-    try:
-        # 데이터베이스 연결
-        connection = mysql.connector.connect(
-            host=host,
-            user=user,
-            password=password,
-            database=database
-        )
-        
-        # 커서 생성
-        cursor = connection.cursor(dictionary=True)
-        
-        # 쿼리 실행
-        query = "SELECT * FROM healty_url_source ORDER BY idx DESC LIMIT 1;"
-        cursor.execute(query)
-        
-        # 결과 가져오기
-        result = cursor.fetchone()
-        return result
-    
-    except mysql.connector.Error as err:
-        print(f"Error: {err}")
-    finally:
-        if connection.is_connected():
-            cursor.close()
-            connection.close()
-
-if __name__ == "__main__":
-    # 결과 확인
-    data = fetch_data_from_mariadb()
-    print(data['url'])
-

k8s-manifests/env.yaml

@@ -0,0 +1,16 @@
+apiVersion: v1
+kind: Secret
+metadata:
+  name: wp-secret
+  namespace: default
+type: Opaque
+data:
+  DB_HOST: 
+  DB_USER: 
+  DB_PASSWORD: 
+  DB_NAME: 
+  OPENAI_API_KEY: 
+  WP_URL: 
+  WP_USER: 
+  WP_API_KEY: 
+  WP_POST_STYLE: ""

k8s-manifests/pod.yaml

@@ -0,0 +1,61 @@
+apiVersion: v1
+kind: Pod
+metadata:
+  name: wp-auto-pod
+  namespace: default
+  annotations:
+    sidecar.istio.io/inject: "false"
+spec:
+  containers:
+  - name: wp-auto-container
+    image: harbor.icurfer.com/py_prj/wp-auto:0.0.1
+    imagePullPolicy: IfNotPresent
+    env:
+    - name: DB_HOST
+      valueFrom:
+        secretKeyRef:
+          name: wp-secret
+          key: DB_HOST
+    - name: DB_USER
+      valueFrom:
+        secretKeyRef:
+          name: wp-secret
+          key: DB_USER
+    - name: DB_PASSWORD
+      valueFrom:
+        secretKeyRef:
+          name: wp-secret
+          key: DB_PASSWORD
+    - name: DB_NAME
+      valueFrom:
+        secretKeyRef:
+          name: wp-secret
+          key: DB_NAME
+    - name: OPENAI_API_KEY
+      valueFrom:
+        secretKeyRef:
+          name: wp-secret
+          key: OPENAI_API_KEY
+    - name: WP_URL
+      valueFrom:
+        secretKeyRef:
+          name: wp-secret
+          key: WP_URL
+    - name: WP_USER
+      valueFrom:
+        secretKeyRef:
+          name: wp-secret
+          key: WP_USER
+    - name: WP_API_KEY
+      valueFrom:
+        secretKeyRef:
+          name: wp-secret
+          key: WP_API_KEY
+    - name: WP_POST_STYLE
+      valueFrom:
+        secretKeyRef:
+          name: wp-secret
+          key: WP_POST_STYLE
+  restartPolicy: Never
+  imagePullSecrets:
+  - name: harbor-icurfer-private

lib64

@@ -0,0 +1 @@
+lib

main.py

@@ -0,0 +1,52 @@
+import package as pkg
+from package import GetConfig, MariaDB, ChangeTextToPost, WordPress
+import markdown
+
+# 2024-10-03 환경 변수 호출
+print('### Get values From .env')
+config = GetConfig()
+dict_data = config.get_config_as_dict()
+
+# 2024-10-03 db에서 url정보 호출
+# DB없이 url을 직접 넣어서 동작시켜도 가능합니다. - 2025.01.19
+print('### Get URL From DB')
+db = MariaDB(dict_data)
+url = db.fetch_data_from_mariadb()['url'] # 최근 항목 조회. - 2025.01.19
+
+print(url)
+# 2024-10-03 url을 이용해서 text추출
+print('### Get content From URL')
+origin_content = pkg.getContents(url)
+
+print(origin_content)
+# # 2024-10-03 openAI를 이용하여 게시글 스타일 변경
+print('### Convert to Post - openAI')
+openai_key = dict_data['openai_api_key']
+print(f"### OpenAI Key : {openai_key}")
+
+wp_reference_style = dict_data['wp_post_style']
+print(f"### WP Reference Style : {wp_reference_style}")
+
+open_ai = ChangeTextToPost(openai_key)
+
+
+post_article = open_ai.generate_blog_post(origin_content, wp_reference_style)
+print('### DEBUG ###')
+print(post_article)
+# print('### Convert to HTML - markdown to html')
+# # 2024-10-03 Markdown을 HTML로 변환
+# html = markdown.markdown(post_article)
+
+# # 2024-10-03 워드프레스 포스팅 임시등록
+# print('### Create post')
+# wp = WordPress(dict_data)
+# rs = wp.create_post(2,html)
+
+if __name__ == "__main__":
+    print(post_article)
+    print("추가 확인을 위한 출력")
+    if rs.ok:
+        print(f"### 성공 code:{rs.status_code}")    
+    else:
+        print(f"### 실패 code:{rs.status_code} reason:{rs.reason} msg:{rs.text}")
+    

main_naver_blog_html.py

@@ -0,0 +1,81 @@
+import requests
+from bs4 import BeautifulSoup
+from markdownify import markdownify as md
+from package import GetConfig, MariaDB, ChangeTextToPost, WordPress
+import markdown
+import re
+
+# 현재 DB연동 기능은 없음. 실행시키면 URL을 넣어야동작합니다.
+def get_naver_blog_content_as_markdown(url):
+    # 네이버 블로그의 모바일 버전으로 리다이렉트
+    mobile_url = url.replace("blog.naver.com", "m.blog.naver.com")
+    
+    # 웹브라우저 위장 --------------------------------------------------
+    # 제외 하여도 이상 없이 동작하여 제외.
+    # headers = {
+    #     "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
+    # }
+    
+    
+    # response = requests.get(mobile_url, headers=headers)
+    # ---------------------------------------------------------------
+    response = requests.get(mobile_url)
+    
+    if response.status_code != 200:
+        print(f"Failed to fetch the page: {response.status_code}")
+        return None
+    
+    # BeautifulSoup으로 HTML 파싱
+    soup = BeautifulSoup(response.text, 'html.parser')
+    
+    # 본문 추출 (모바일 버전의 본문 클래스 사용)
+    content = soup.find("div", class_="se-main-container")
+    
+    if content:
+        html_content = str(content)
+        markdown_content = md(html_content)  # HTML → Markdown 변환
+        
+        # 빈 줄 제거
+        markdown_content = "\n".join([line for line in markdown_content.splitlines() if line.strip()])
+        
+        return markdown_content
+    else:
+        print("Failed to extract the blog content.")
+        return None
+
+
+# 2024-10-03 환경 변수 호출
+print('### Get values From .env')
+config = GetConfig()
+dict_data = config.get_config_as_dict()
+
+# 예제 URL
+url = input("Enter your blog address : ")
+# markdown_content = get_naver_blog_content_as_markdown(url)
+post_article = get_naver_blog_content_as_markdown(url)
+post_article = post_article.replace(">", "###")
+post_article = re.sub(r"^\[!\[\].*?\]", "#### 이미지", post_article, flags=re.MULTILINE)
+# if markdown_content:
+#     print("Markdown Content:")
+#     print(markdown_content)
+
+    # Markdown 파일로 저장
+    # with open("blog_content.md", "w", encoding="utf-8") as file:
+    #     file.write(markdown_content)
+    # print("Blog content saved as blog_content.md")
+
+print('### Convert to HTML - markdown to html')
+# 2024-10-03 Markdown을 HTML로 변환
+html = markdown.markdown(post_article)
+# 2024-10-03 워드프레스 포스팅 임시등록
+print('### Create post')
+wp = WordPress(dict_data)
+rs = wp.create_post(2,html)
+
+if __name__ == "__main__":
+    # print(post_article)
+    print("추가 확인을 위한 출력")
+    if rs.ok:
+        print(f"### 성공 code:{rs.status_code}")    
+    else:
+        print(f"### 실패 code:{rs.status_code} reason:{rs.reason} msg:{rs.text}")

open_ai.py

@@ -1,50 +0,0 @@
-import os
-from openai import OpenAI
-from dotenv import load_dotenv
-import translate_article as ta
-
-# .env 파일에서 API 키 로드
-load_dotenv()
-client = OpenAI(
-    api_key=os.getenv("OPENAI_API_KEY"),
-)
-
-def generate_blog_post(article_text, style_reference):
-    
-    # ChatCompletion API를 사용하여 텍스트 변환
-    prompt = (
-        """
-        너는 대한민국에 거주하는 블로그 전문가이다. 
-        네가 작성한 블로그 글은 지난 3년간 높은 주목성, 관여도, 전환율을 만들었다. 
-        이 전문성을 이용해서 제공받는 기사를 블로그 형태로 변형하여 작성해야만 한다.
-        """
-        f"\n블로그 스타일은 아래 문서를 모방해줘. 적절한 사례들이 들어가도 좋겠어.\n---\n{style_reference}\n"
-        f"제공된 기사 내용:\n{article_text}"
-    )
-
-    response = client.chat.completions.create(
-        model="gpt-4o",
-        messages=[
-            {"role": "system", "content": "너는 대한민국에 거주하는 블로그 전문가이다."},
-            {"role": "user", "content": prompt}
-        ],
-        max_tokens=2000,
-        temperature=0.7,  # 창의성을 위한 적절한 값 조정
-    )
-
-    # 응답에서 텍스트 추출
-    blog_post = response.choices[0].message.content
-    return blog_post
-
-# 예시 기사 텍스트 (text 파싱 결과로 제공된 텍스트를 사용할 수 있습니다)
-article_text = ta.getContents()
-
-# 블로그 스타일 참고 텍스트
-style_reference = os.getenv("reference_style")
-
-# 블로그 포스트 생성
-blog_post = generate_blog_post(article_text, style_reference)
-
-# 결과 출력
-print(">>>>\n" * 3)
-print(blog_post)

package/GetConfig.py

@@ -0,0 +1,49 @@
+import os
+from dotenv import load_dotenv
+
+# 우선순위: .env.prd > .env.dev > .env
+if os.path.exists('.env.prd'):
+    print("Read ::: .env.prd")
+    load_dotenv('.env.prd')
+elif os.path.exists('.env.dev'):
+    print("Read ::: .env.dev")
+    load_dotenv('.env.dev')
+else:
+    print("Read ::: .env")
+    load_dotenv('.env')  # 기본 .env 파일
+
+class GetConfig:
+    def __init__(self):
+        self.db_host = os.getenv('DB_HOST')
+        self.db_user = os.getenv('DB_USER')
+        self.db_pw = os.getenv('DB_PASSWORD')
+        self.db_database = os.getenv('DB_NAME')
+        self.openai_api_key = os.getenv('OPENAI_API_KEY')
+        self.wp_url = os.getenv('WP_URL')
+        self.wp_user = os.getenv('WP_USER')
+        self.wp_api_key = os.getenv('WP_API_KEY')
+        self.wp_post_style = os.getenv('WP_POST_STYLE')
+        
+    def show_config(self):
+        for key, value in self.__dict__.items():
+            print(f"{key.upper()}: {value}")
+            
+    def get_config_as_dict(self):
+        # 인스턴스 속성을 딕셔너리로 반환
+        return self.__dict__
+        
+        
+if __name__ == "__main__":
+    # 결과 확인
+    config = GetConfig()
+    config.show_config()
+    
+    
+# 오랜만에 보다보니 헷갈려서 참고용으로 작성    
+# class GetConfig:
+#     def __init__(self, name=None):
+#         self.name = name if name is not None else "default_name"
+#         self.host = os.getenv('DB_HOST')
+#         self.user = os.getenv('DB_USER')
+#         self.password = os.getenv('DB_PASSWORD')
+#         self.database = os.getenv('DB_NAME')

package/MariaDB.py

@@ -0,0 +1,56 @@
+import mysql.connector
+
+class MariaDB:
+    
+    def __init__(self, dict):
+        self.db_host = dict['db_host']
+        self.db_user = dict['db_user']
+        self.db_pw = dict['db_pw']
+        self.db_database = dict['db_database']
+    
+    def show_config(self):
+        for key, value in self.__dict__.items():
+            print(f"{key.upper()}: {value}")
+            
+    def fetch_data_from_mariadb(self):
+        try:
+            # 데이터베이스 연결
+            connection = mysql.connector.connect(
+                host=self.db_host,
+                user=self.db_user,
+                password=self.db_pw,
+                database=self.db_database
+            )
+            
+            # 커서 생성
+            cursor = connection.cursor(dictionary=True)
+            
+            # 쿼리 실행
+            query = "SELECT * FROM healty_url_source ORDER BY idx DESC LIMIT 1;"
+            cursor.execute(query)
+            
+            # 결과 가져오기
+            result = cursor.fetchone()
+            return result
+        
+        except mysql.connector.Error as err:
+            print(f"Error: {err}")
+        finally:
+            if connection.is_connected():
+                cursor.close()
+                connection.close()
+            
+if __name__ == "__main__":
+    
+    import GetConfig    
+    
+    config = GetConfig.GetConfig()
+    # config 잘 가져오는지 확인
+    config_dict = config.get_config_as_dict()
+    
+    # MariaDB 테스트
+    dbg = MariaDB(config_dict)
+    # dbg.show_config()
+    url = dbg.fetch_data_from_mariadb()
+    print(url['url'])
+    

package/OpenAI.py

@@ -0,0 +1,37 @@
+from openai import OpenAI
+
+class ChangeTextToPost:
+    
+    def __init__(self, key):
+        self.client = OpenAI(
+            api_key=key,
+        )
+
+    def generate_blog_post(self, origin_content, wp_post_style):
+        
+        # ChatCompletion API를 사용하여 텍스트 변환
+        prompt = (
+            """
+            너는 대한민국에 거주하는 블로그 전문가이다. 
+            네가 작성한 블로그 글은 지난 3년간 높은 주목성, 관여도, 전환율을 만들었다. 
+            이 전문성을 이용해서 제공받는 기사를 블로그 형태로 변형하여 작성해야만 한다.
+            ---
+            글을 작성하고 제목을 만들어서 맨 마지막 줄에 추가해줘.
+            """
+            f"\n블로그 스타일은 아래 문서를 모방해줘. markdown형태로 작성되어야한다. 적절한 사례들이 들어가도 좋겠어.\n---\n{wp_post_style}\n"
+            f"제공된 기사 내용:\n{origin_content}"
+        )
+
+        response = self.client.chat.completions.create(
+            model="gpt-4o",
+            messages=[
+                {"role": "system", "content": "너는 대한민국에 거주하는 블로그 전문가이다."},
+                {"role": "user", "content": prompt}
+            ],
+            max_tokens=2000,
+            temperature=0.7,  # 창의성을 위한 적절한 값 조정
+        )
+
+        # 응답에서 텍스트 추출
+        blog_post = response.choices[0].message.content
+        return blog_post

package/Utility.py

@@ -0,0 +1,69 @@
+import requests, json
+from urllib.parse import urljoin
+from bs4 import BeautifulSoup
+from datetime import datetime
+
+def getContents(url):
+    # ✅ User-Agent 헤더 추가 (403 방지용)
+    headers = {
+        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) ' \
+                      'AppleWebKit/537.36 (KHTML, like Gecko) ' \
+                      'Chrome/113.0.0.0 Safari/537.36'
+    }
+    
+    # HTTP GET 요청으로 페이지 가져오기
+    response = requests.get(url, headers=headers)
+
+    # 응답 상태 확인
+    if response.status_code == 200:
+        # HTML 파싱
+        soup = BeautifulSoup(response.text, 'html.parser')
+        
+        # HTML 태그를 제거 후 페이지의 모든 텍스트 가져오기 (전체 내용)
+        page_content = soup.get_text()
+        print("### url DEBUG ###")
+        print(page_content)
+        
+        # 빈 줄을 제거하고 텍스트만 출력 (줄바꿈 문자를 기준으로 필터링)
+        lines = [line.strip() for line in page_content.splitlines() if line.strip()]
+        
+        # 결과 출력
+        contents = "\n".join(lines)
+        return contents
+    else:
+        print(f"Failed to fetch the URL. Status code: {response.status_code}")
+
+class WordPress():
+    
+    def __init__(self, dict):
+        self.wp_url = dict['wp_url']
+        self.wp_user = dict['wp_user']
+        self.wp_api_key = dict['wp_api_key']
+        
+    def create_post(self, category_id, content, media_id = None, status = "draft", title="파이썬 자동 포스팅"):
+        payload = {
+            "status": status, # publish / draft
+            "title": title,
+            "content": content,
+            "date": datetime.now().isoformat(), # YYYY-MM-DDTHH:MM:SS
+            "categories": category_id
+        }
+        if media_id is not None:
+            payload['featured_media'] = media_id
+
+
+
+        return requests.post(urljoin(self.wp_url, "wp-json/wp/v2/posts"),
+                            data=json.dumps(payload),
+                            headers={'Content-type': "application/json"},
+                            auth=(self.wp_user, self.wp_api_key))
+        # if result.ok:
+        #     print(f"성공 code:{result.status_code}")    
+        # else:
+        #     print(f"실패 code:{result.status_code} reason:{result.reason} msg:{result.text}")
+        
+if __name__ == "__main__":
+    # url = 'https://www.hani.co.kr/arti/science/science_general/1161001.html'
+    # tmp = getContents(url)
+    # print(tmp)
+    pass

package/__init__.py

@@ -0,0 +1,5 @@
+from .Utility import getContents
+from .Utility import WordPress
+from .GetConfig import GetConfig
+from .MariaDB import MariaDB
+from .OpenAI import ChangeTextToPost

pyvenv.cfg

@@ -0,0 +1,3 @@
+home = /usr/bin
+include-system-site-packages = false
+version = 3.10.12

sample.env.dev

@@ -0,0 +1,9 @@
+DB_HOST=192.168.0.1
+DB_USER=demo
+DB_PASSWORD=demo
+DB_NAME=demo
+OPENAI_API_KEY=demo
+WP_URL='https://www.example.com'
+WP_USER='demo'
+WP_API_KEY='demo'
+WP_POST_STYLE="문장" # OpenAI에 사용되는것.

tempCodeRunnerFile.py

@@ -0,0 +1,2 @@
+
+if rs.ok:

translate_article.py

@@ -1,30 +0,0 @@
-import requests
-from bs4 import BeautifulSoup
-import get_url
-
-
-url = get_url.fetch_data_from_mariadb()['url']
-
-def getContents():
-    # HTTP GET 요청으로 페이지 가져오기
-    response = requests.get(url)
-
-    # 응답 상태 확인
-    if response.status_code == 200:
-        # HTML 파싱
-        soup = BeautifulSoup(response.text, 'html.parser')
-        
-        # HTML 태그를 제거 후 페이지의 모든 텍스트 가져오기 (전체 내용)
-        page_content = soup.get_text()
-        
-        # 빈 줄을 제거하고 텍스트만 출력 (줄바꿈 문자를 기준으로 필터링)
-        lines = [line.strip() for line in page_content.splitlines() if line.strip()]
-        
-        # 결과 출력
-        contents = "\n".join(lines)
-        return contents
-    else:
-        print(f"Failed to fetch the URL. Status code: {response.status_code}")
-        
-tmp = getContents()
-print(tmp)

version

@@ -0,0 +1 @@
+0.1.2