├── .gitignore
├── Confluence-html-to-github-markdown.js
├── LICENSE
├── README.md
└── package.json


/.gitignore:
--------------------------------------------------------------------------------
 1 | # Logs
 2 | logs
 3 | *.log
 4 | npm-debug.log*
 5 | yarn-debug.log*
 6 | yarn-error.log*
 7 | 
 8 | # Runtime data
 9 | pids
10 | *.pid
11 | *.seed
12 | *.pid.lock
13 | 
14 | # Directory for instrumented libs generated by jscoverage/JSCover
15 | lib-cov
16 | 
17 | # Coverage directory used by tools like istanbul
18 | coverage
19 | 
20 | # nyc test coverage
21 | .nyc_output
22 | 
23 | # Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
24 | .grunt
25 | 
26 | # Bower dependency directory (https://bower.io/)
27 | bower_components
28 | 
29 | # node-waf configuration
30 | .lock-wscript
31 | 
32 | # Compiled binary addons (https://nodejs.org/api/addons.html)
33 | build/Release
34 | 
35 | # Dependency directories
36 | node_modules/
37 | jspm_packages/
38 | 
39 | # TypeScript v1 declaration files
40 | typings/
41 | 
42 | # Optional npm cache directory
43 | .npm
44 | 
45 | # Optional eslint cache
46 | .eslintcache
47 | 
48 | # Optional REPL history
49 | .node_repl_history
50 | 
51 | # Output of 'npm pack'
52 | *.tgz
53 | 
54 | # Yarn Integrity file
55 | .yarn-integrity
56 | 
57 | # dotenv environment variables file
58 | .env
59 | 
60 | # parcel-bundler cache (https://parceljs.org/)
61 | .cache
62 | 
63 | # next.js build output
64 | .next
65 | 
66 | # nuxt.js build output
67 | .nuxt
68 | 
69 | # vuepress build output
70 | .vuepress/dist
71 | 
72 | # Serverless directories
73 | .serverless


--------------------------------------------------------------------------------
/Confluence-html-to-github-markdown.js:
--------------------------------------------------------------------------------
  1 | #!/usr/bin/env node
  2 | var fs = require('fs-extra')
  3 | var exec = require('sync-exec')
  4 | var path = require('path');
  5 | 
  6 | var divePath = process.cwd();
  7 | var attachmentsExportPath = "public/assets/images/"
  8 | var markdownImageReference = "assets/images/"
  9 | // print process.argv
 10 | process.argv.forEach(function (val, index, array) {
 11 |   if (index === 2){
 12 |     divePath = process.cwd() + "/" + val;
 13 |   }else if (index === 3){
 14 |     attachmentsExportPath = val
 15 |   }else if(index === 4){
 16 |     markdownImageReference = val
 17 |   }
 18 | });
 19 | dive(divePath)
 20 | 
 21 | function dive(dir) {
 22 |   var list = []
 23 |   var stat = ""
 24 |     // Read the directory
 25 |   list = fs.readdirSync(dir);
 26 |   list.forEach(function (file) {
 27 |     // Full path of that file
 28 |     var p = path.join(dir , file)
 29 | 
 30 |     // Get the file's stats
 31 |     stat = fs.statSync(p)
 32 | 
 33 |     // If the file is a directory
 34 |     if (stat && stat.isDirectory()) {
 35 |       dive(p);
 36 |     } else {
 37 |       console.log(file)
 38 |       if (file.endsWith('.html')) {
 39 |         var titleRegex = /<title>([^<]*)<\/title>/i
 40 |         var content = fs.readFileSync(p, 'utf8')
 41 |         var match = content.match(titleRegex)
 42 |         if (match != null && match.length > 1) {
 43 |           fs.ensureDir("Markdown")
 44 |           var sanitizedfilename = match[1].replace(/[^0-9a-zA-Z]/g,"_")
 45 |           var outputFile = path.join("Markdown", sanitizedfilename + ".md")
 46 |           var command = "pandoc -f html -t markdown -o " + outputFile + " " + p
 47 |           var out = exec(command, {cwd: process.cwd()})
 48 |           console.log(out)
 49 |             //images
 50 |           console.log("Reading : " + outputFile)
 51 |           var content = fs.readFileSync(outputFile, 'utf8')
 52 |           var matches = uniq(content.match(/(<img src=")([a-z||_|0-9|.|]+)\/([a-z||_|0-9|.|]+)\/([a-z||_|0-9|.|]+)/ig))
 53 |           matches.forEach(function (img) {
 54 |             img = img.replace('<img src="', '')
 55 |             var attachments = img.replace("attachments/", "");
 56 |             if (attachments == img) {
 57 |               return;
 58 |             }
 59 |             var fileName = attachmentsExportPath + attachments;
 60 |             //            console.log("Creating Folder : " + fileName.substr(0, fileName.lastIndexOf('/')))
 61 |             mkdirpSync(fileName.substr(0, fileName.lastIndexOf('/')))
 62 |               //            console.log("creating filename: " + fileName)
 63 |               //            fs.createReadStream(img).pipe(fs.createWriteStream(fileName));
 64 |             try {
 65 | //              var img_content = fs.readFileSync(dir + "/" + img);
 66 | //              fs.writeFileSync(fileName, img);
 67 |               fs.accessSync(dir + "/" + img, fs.F_OK);
 68 |               fs.createReadStream(dir + "/" + img).pipe(fs.createWriteStream(process.cwd() + "/" + fileName));
 69 |               console.log("Wrote: " + dir + "/" + img + "\n To: " + process.cwd() + "/" + fileName)
 70 |             } catch (e) {
 71 |               console.log("Can't read: " + dir + "/" + img)
 72 |             }
 73 |           })
 74 |           var lines = content.replace(/(<img src=")([a-z||_|0-9|.|]+)\/([a-z||_|0-9|.|]+)\/([a-z||_|0-9|.|]+)/ig, "$1"+ markdownImageReference +"$3/$4")
 75 | 
 76 |           fs.writeFileSync(outputFile, lines)
 77 |         }
 78 |       }
 79 | 
 80 | 
 81 |     }
 82 |   })
 83 | }
 84 | 
 85 | function uniq(a) {
 86 |   return Array.from(new Set(a));
 87 | }
 88 | 
 89 | function mkdirSync(path) {
 90 |   try {
 91 |     fs.mkdirSync(path);
 92 |   } catch (e) {
 93 |     if (e.code != 'EEXIST') throw e;
 94 |   }
 95 | }
 96 | 
 97 | function mkdirpSync(dirpath) {
 98 | //  console.log("Making : " + dirpath)
 99 |   var parts = dirpath.split(path.sep);
100 |   for (var i = 1; i <= parts.length; i++) {
101 |     mkdirSync(path.join.apply(null, parts.slice(0, i)));
102 |   }
103 | }
104 | 


--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
 1 | The MIT License (MIT)
 2 | 
 3 | Copyright (c) 2016 Eric White
 4 | 
 5 | Permission is hereby granted, free of charge, to any person obtaining a copy
 6 | of this software and associated documentation files (the "Software"), to deal
 7 | in the Software without restriction, including without limitation the rights
 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 9 | copies of the Software, and to permit persons to whom the Software is
10 | furnished to do so, subject to the following conditions:
11 | 
12 | The above copyright notice and this permission notice shall be included in all
13 | copies or substantial portions of the Software.
14 | 
15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
21 | SOFTWARE.
22 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # Not maintained
 2 | May want to fork: https://github.com/meridius/confluence-to-markdown
 3 | # Confluence-to-Github-Markdown
 4 | Convert Confluence Html export to Github Markdown
 5 | # Requirements
 6 |  **Must have pandoc command line tool**
 7 |  
 8 |  http://pandoc.org/installing.html
 9 | 
10 |  Make sure it was installed properly by doing `pandoc --version`
11 | # Installation
12 | `npm install -g confluence-to-github-markdown`
13 | # Usage
14 |   `confluence-to-github-markdown`
15 |   
16 |   `confluence-to-github-markdown <htmlFilesDirectory> <attachmentsExportPath> <markdownImageReference>`
17 |   
18 | ### Defaults
19 |   * `<htmlFilesDirectory>` : `Current Working Directory`
20 |   * `<attachmentsExportPath>` : `"/public/assets/images/"` Where to export images
21 |   * `<markdownImageReference>` : `"assets/images/"` Image reference in markdown files
22 | 
23 | 
24 | # Export to HTML
25 | Note that if the converter does not know how to handle a style, HTML to Markdown typically just leaves the HTML untouched (Markdown does allow for HTML tags).
26 | 
27 | ### Step by Step Guide
28 | 
29 | 1. Go to the space and choose Space tools > Content Tools on the sidebar. 
30 | 2. Choose Export. This option will only be visible if you have the 'Export Space' permission.
31 | 3. Select HTML  then choose Next.
32 | 4. Decide whether you need to customise the export:
33 |   * Select Normal Export to produce an HTML file containing all the pages that you have permission to view.
34 |   * Select Custom Export if you want to export a subset of pages, or to exclude comments from the export. 
35 | 5. [Export Pages](https://confluence.atlassian.com/doc/export-content-to-word-pdf-html-and-xml-139475.html#ExportContenttoWord,PDF,HTMLandXML-ExportmultiplepagestoHTML,XML,orPDF)
36 | 6. Extract zip
37 | 7. Open shell in extracted zip
38 | 8. run `confluence-to-github-markdown` in shell
39 | 


--------------------------------------------------------------------------------
/package.json:
--------------------------------------------------------------------------------
 1 | {
 2 |   "name": "confluence-to-github-markdown",
 3 |   "version": "1.1.2",
 4 |   "description": "Convert Confluence Pages to github markdown",
 5 |   "bin": {
 6 |     "confluence-to-github-markdown": "./Confluence-html-to-github-markdown.js"
 7 |   },
 8 |   "main": "Confluence-html-to-github-markdown.js",
 9 |   "repository": "git@github.com:EWhite613/Confluence-to-Github-Markdown.git",
10 |   "dependencies": {
11 |     "path": "^0.12.7",
12 |     "sync-exec": "^0.6.2",
13 |     "fs-extra":"^7.0.0"
14 |   },
15 |   "devDependencies": {},
16 |   "keywords": [
17 |     "Confluence",
18 |     "Markdown",
19 |     "Confluence to Markdown",
20 |     "Confluence to Github Markdown",
21 |     "ember",
22 |     "Github Markdown",
23 |     "Images",
24 |     "export images",
25 |     "reference images"
26 |   ],
27 |   "scripts": {
28 |     "test": "echo \"Error: no test specified\" && exit 1"
29 |   },
30 |   "author": "Eric White",
31 |   "license": "MIT"
32 | }
33 | 


--------------------------------------------------------------------------------