├── .github
└── workflows
│ └── nodejs.yml
├── .gitignore
├── CONTRIBUTING.md
├── LICENSE
├── README.md
├── dom-node.js
├── dom-node.test.js
├── jest.config.js
├── package-lock.json
├── package.json
├── serialize.js
├── serialize.test.js
├── subtree.js
├── subtree.test.js
└── test
├── iframe.json
├── inlineIframe-false.html
├── inlineIframe-true.html
├── simple.html
├── simple.json
├── web-component.html
└── web-component.json
/.github/workflows/nodejs.yml:
--------------------------------------------------------------------------------
1 | name: Run tests
2 |
3 | on: [push, pull_request]
4 |
5 | jobs:
6 | build:
7 |
8 | runs-on: ubuntu-latest
9 |
10 | strategy:
11 | matrix:
12 | node-version: [10.x, 12.x, 13.x]
13 |
14 | steps:
15 | - uses: actions/checkout@v1
16 | - name: Use Node.js ${{ matrix.node-version }}
17 | uses: actions/setup-node@v1
18 | with:
19 | node-version: ${{ matrix.node-version }}
20 | - name: npm install, build, and test
21 | run: |
22 | npm ci
23 | npm test
24 | env:
25 | CI: true
26 |
--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
1 | # Logs
2 | logs
3 | *.log
4 | npm-debug.log*
5 | yarn-debug.log*
6 | yarn-error.log*
7 | lerna-debug.log*
8 |
9 | # Diagnostic reports (https://nodejs.org/api/report.html)
10 | report.[0-9]*.[0-9]*.[0-9]*.[0-9]*.json
11 |
12 | # Runtime data
13 | pids
14 | *.pid
15 | *.seed
16 | *.pid.lock
17 |
18 | # Directory for instrumented libs generated by jscoverage/JSCover
19 | lib-cov
20 |
21 | # Coverage directory used by tools like istanbul
22 | coverage
23 | *.lcov
24 |
25 | # nyc test coverage
26 | .nyc_output
27 |
28 | # Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
29 | .grunt
30 |
31 | # Bower dependency directory (https://bower.io/)
32 | bower_components
33 |
34 | # node-waf configuration
35 | .lock-wscript
36 |
37 | # Compiled binary addons (https://nodejs.org/api/addons.html)
38 | build/Release
39 |
40 | # Dependency directories
41 | node_modules/
42 | jspm_packages/
43 |
44 | # TypeScript v1 declaration files
45 | typings/
46 |
47 | # TypeScript cache
48 | *.tsbuildinfo
49 |
50 | # Optional npm cache directory
51 | .npm
52 |
53 | # Optional eslint cache
54 | .eslintcache
55 |
56 | # Microbundle cache
57 | .rpt2_cache/
58 | .rts2_cache_cjs/
59 | .rts2_cache_es/
60 | .rts2_cache_umd/
61 |
62 | # Optional REPL history
63 | .node_repl_history
64 |
65 | # Output of 'npm pack'
66 | *.tgz
67 |
68 | # Yarn Integrity file
69 | .yarn-integrity
70 |
71 | # dotenv environment variables file
72 | .env
73 | .env.test
74 |
75 | # parcel-bundler cache (https://parceljs.org/)
76 | .cache
77 |
78 | # Next.js build output
79 | .next
80 |
81 | # Nuxt.js build / generate output
82 | .nuxt
83 | dist
84 |
85 | # Gatsby files
86 | .cache/
87 | # Comment in the public line in if your project uses Gatsby and *not* Next.js
88 | # https://nextjs.org/blog/next-9-1#public-directory-support
89 | # public
90 |
91 | # vuepress build output
92 | .vuepress/dist
93 |
94 | # Serverless directories
95 | .serverless/
96 |
97 | # FuseBox cache
98 | .fusebox/
99 |
100 | # DynamoDB Local files
101 | .dynamodb/
102 |
103 | # TernJS port file
104 | .tern-port
105 | node_modules
106 |
--------------------------------------------------------------------------------
/CONTRIBUTING.md:
--------------------------------------------------------------------------------
1 | # How to Contribute
2 |
3 | We'd love to accept your patches and contributions to this project. There are
4 | just a few small guidelines you need to follow.
5 |
6 | ## How to set up your local environment
7 |
8 | With [node.js](https://nodejs.org) installed, follow the steps below or run the following commands:
9 |
10 | 1. Get a local copy of this repository
11 | 2. Install the dependencies with `npm install`
12 |
13 | ```
14 | git clone https://github.com/GoogleChromeLabs/dom2html.git
15 | cd dom2html
16 | npm install
17 | ```
18 |
19 | ## Writing and running tests
20 |
21 | The tests are written with [Jest](https://jestjs.io/) and can be found in the `*.test.js` files, named like the code they test (e.g. `serialize.js` functionality is tested in the `serialize.test.js` file). HTML test files (called fixtures) are stored in the `test` folder.
22 |
23 | Tests can be run with `npm test`.
24 |
25 | ## What to include in a pull request
26 |
27 | - The commits with the things you want to add / remove / fix :)
28 | - A test case for the fix or feature (not applicable for docs-only pull requests)
29 | - Updated docs, matching the code changes (if applicable)
30 |
31 | ## Contributor License Agreement
32 |
33 | Contributions to this project must be accompanied by a Contributor License
34 | Agreement. You (or your employer) retain the copyright to your contribution;
35 | this simply gives us permission to use and redistribute your contributions as
36 | part of the project. Head over to to see
37 | your current agreements on file or to sign a new one.
38 |
39 | You generally only need to submit a CLA once, so if you've already submitted one
40 | (even if it was for a different project), you probably don't need to do it
41 | again.
42 |
43 | ## Code reviews
44 |
45 | All submissions, including submissions by project members, require review. We
46 | use GitHub pull requests for this purpose. Consult
47 | [GitHub Help](https://help.github.com/articles/about-pull-requests/) for more
48 | information on using pull requests.
49 |
50 | ## Community Guidelines
51 |
52 | This project follows
53 | [Google's Open Source Community Guidelines](https://opensource.google/conduct/).
54 |
--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
1 |
2 | Apache License
3 | Version 2.0, January 2004
4 | http://www.apache.org/licenses/
5 |
6 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
7 |
8 | 1. Definitions.
9 |
10 | "License" shall mean the terms and conditions for use, reproduction,
11 | and distribution as defined by Sections 1 through 9 of this document.
12 |
13 | "Licensor" shall mean the copyright owner or entity authorized by
14 | the copyright owner that is granting the License.
15 |
16 | "Legal Entity" shall mean the union of the acting entity and all
17 | other entities that control, are controlled by, or are under common
18 | control with that entity. For the purposes of this definition,
19 | "control" means (i) the power, direct or indirect, to cause the
20 | direction or management of such entity, whether by contract or
21 | otherwise, or (ii) ownership of fifty percent (50%) or more of the
22 | outstanding shares, or (iii) beneficial ownership of such entity.
23 |
24 | "You" (or "Your") shall mean an individual or Legal Entity
25 | exercising permissions granted by this License.
26 |
27 | "Source" form shall mean the preferred form for making modifications,
28 | including but not limited to software source code, documentation
29 | source, and configuration files.
30 |
31 | "Object" form shall mean any form resulting from mechanical
32 | transformation or translation of a Source form, including but
33 | not limited to compiled object code, generated documentation,
34 | and conversions to other media types.
35 |
36 | "Work" shall mean the work of authorship, whether in Source or
37 | Object form, made available under the License, as indicated by a
38 | copyright notice that is included in or attached to the work
39 | (an example is provided in the Appendix below).
40 |
41 | "Derivative Works" shall mean any work, whether in Source or Object
42 | form, that is based on (or derived from) the Work and for which the
43 | editorial revisions, annotations, elaborations, or other modifications
44 | represent, as a whole, an original work of authorship. For the purposes
45 | of this License, Derivative Works shall not include works that remain
46 | separable from, or merely link (or bind by name) to the interfaces of,
47 | the Work and Derivative Works thereof.
48 |
49 | "Contribution" shall mean any work of authorship, including
50 | the original version of the Work and any modifications or additions
51 | to that Work or Derivative Works thereof, that is intentionally
52 | submitted to Licensor for inclusion in the Work by the copyright owner
53 | or by an individual or Legal Entity authorized to submit on behalf of
54 | the copyright owner. For the purposes of this definition, "submitted"
55 | means any form of electronic, verbal, or written communication sent
56 | to the Licensor or its representatives, including but not limited to
57 | communication on electronic mailing lists, source code control systems,
58 | and issue tracking systems that are managed by, or on behalf of, the
59 | Licensor for the purpose of discussing and improving the Work, but
60 | excluding communication that is conspicuously marked or otherwise
61 | designated in writing by the copyright owner as "Not a Contribution."
62 |
63 | "Contributor" shall mean Licensor and any individual or Legal Entity
64 | on behalf of whom a Contribution has been received by Licensor and
65 | subsequently incorporated within the Work.
66 |
67 | 2. Grant of Copyright License. Subject to the terms and conditions of
68 | this License, each Contributor hereby grants to You a perpetual,
69 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable
70 | copyright license to reproduce, prepare Derivative Works of,
71 | publicly display, publicly perform, sublicense, and distribute the
72 | Work and such Derivative Works in Source or Object form.
73 |
74 | 3. Grant of Patent License. Subject to the terms and conditions of
75 | this License, each Contributor hereby grants to You a perpetual,
76 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable
77 | (except as stated in this section) patent license to make, have made,
78 | use, offer to sell, sell, import, and otherwise transfer the Work,
79 | where such license applies only to those patent claims licensable
80 | by such Contributor that are necessarily infringed by their
81 | Contribution(s) alone or by combination of their Contribution(s)
82 | with the Work to which such Contribution(s) was submitted. If You
83 | institute patent litigation against any entity (including a
84 | cross-claim or counterclaim in a lawsuit) alleging that the Work
85 | or a Contribution incorporated within the Work constitutes direct
86 | or contributory patent infringement, then any patent licenses
87 | granted to You under this License for that Work shall terminate
88 | as of the date such litigation is filed.
89 |
90 | 4. Redistribution. You may reproduce and distribute copies of the
91 | Work or Derivative Works thereof in any medium, with or without
92 | modifications, and in Source or Object form, provided that You
93 | meet the following conditions:
94 |
95 | (a) You must give any other recipients of the Work or
96 | Derivative Works a copy of this License; and
97 |
98 | (b) You must cause any modified files to carry prominent notices
99 | stating that You changed the files; and
100 |
101 | (c) You must retain, in the Source form of any Derivative Works
102 | that You distribute, all copyright, patent, trademark, and
103 | attribution notices from the Source form of the Work,
104 | excluding those notices that do not pertain to any part of
105 | the Derivative Works; and
106 |
107 | (d) If the Work includes a "NOTICE" text file as part of its
108 | distribution, then any Derivative Works that You distribute must
109 | include a readable copy of the attribution notices contained
110 | within such NOTICE file, excluding those notices that do not
111 | pertain to any part of the Derivative Works, in at least one
112 | of the following places: within a NOTICE text file distributed
113 | as part of the Derivative Works; within the Source form or
114 | documentation, if provided along with the Derivative Works; or,
115 | within a display generated by the Derivative Works, if and
116 | wherever such third-party notices normally appear. The contents
117 | of the NOTICE file are for informational purposes only and
118 | do not modify the License. You may add Your own attribution
119 | notices within Derivative Works that You distribute, alongside
120 | or as an addendum to the NOTICE text from the Work, provided
121 | that such additional attribution notices cannot be construed
122 | as modifying the License.
123 |
124 | You may add Your own copyright statement to Your modifications and
125 | may provide additional or different license terms and conditions
126 | for use, reproduction, or distribution of Your modifications, or
127 | for any such Derivative Works as a whole, provided Your use,
128 | reproduction, and distribution of the Work otherwise complies with
129 | the conditions stated in this License.
130 |
131 | 5. Submission of Contributions. Unless You explicitly state otherwise,
132 | any Contribution intentionally submitted for inclusion in the Work
133 | by You to the Licensor shall be under the terms and conditions of
134 | this License, without any additional terms or conditions.
135 | Notwithstanding the above, nothing herein shall supersede or modify
136 | the terms of any separate license agreement you may have executed
137 | with Licensor regarding such Contributions.
138 |
139 | 6. Trademarks. This License does not grant permission to use the trade
140 | names, trademarks, service marks, or product names of the Licensor,
141 | except as required for reasonable and customary use in describing the
142 | origin of the Work and reproducing the content of the NOTICE file.
143 |
144 | 7. Disclaimer of Warranty. Unless required by applicable law or
145 | agreed to in writing, Licensor provides the Work (and each
146 | Contributor provides its Contributions) on an "AS IS" BASIS,
147 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
148 | implied, including, without limitation, any warranties or conditions
149 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
150 | PARTICULAR PURPOSE. You are solely responsible for determining the
151 | appropriateness of using or redistributing the Work and assume any
152 | risks associated with Your exercise of permissions under this License.
153 |
154 | 8. Limitation of Liability. In no event and under no legal theory,
155 | whether in tort (including negligence), contract, or otherwise,
156 | unless required by applicable law (such as deliberate and grossly
157 | negligent acts) or agreed to in writing, shall any Contributor be
158 | liable to You for damages, including any direct, indirect, special,
159 | incidental, or consequential damages of any character arising as a
160 | result of this License or out of the use or inability to use the
161 | Work (including but not limited to damages for loss of goodwill,
162 | work stoppage, computer failure or malfunction, or any and all
163 | other commercial damages or losses), even if such Contributor
164 | has been advised of the possibility of such damages.
165 |
166 | 9. Accepting Warranty or Additional Liability. While redistributing
167 | the Work or Derivative Works thereof, You may choose to offer,
168 | and charge a fee for, acceptance of support, warranty, indemnity,
169 | or other liability obligations and/or rights consistent with this
170 | License. However, in accepting such obligations, You may act only
171 | on Your own behalf and on Your sole responsibility, not on behalf
172 | of any other Contributor, and only if You agree to indemnify,
173 | defend, and hold each Contributor harmless for any liability
174 | incurred by, or claims asserted against, such Contributor by reason
175 | of your accepting any such warranty or additional liability.
176 |
177 | END OF TERMS AND CONDITIONS
178 |
179 | APPENDIX: How to apply the Apache License to your work.
180 |
181 | To apply the Apache License to your work, attach the following
182 | boilerplate notice, with the fields enclosed by brackets "[]"
183 | replaced with your own identifying information. (Don't include
184 | the brackets!) The text should be enclosed in the appropriate
185 | comment syntax for the file format. We also recommend that a
186 | file or class name and description of purpose be included on the
187 | same "printed page" as the copyright notice for easier
188 | identification within third-party archives.
189 |
190 | Copyright 2019 Google LLC
191 |
192 | Licensed under the Apache License, Version 2.0 (the "License");
193 | you may not use this file except in compliance with the License.
194 | You may obtain a copy of the License at
195 |
196 | http://www.apache.org/licenses/LICENSE-2.0
197 |
198 | Unless required by applicable law or agreed to in writing, software
199 | distributed under the License is distributed on an "AS IS" BASIS,
200 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
201 | See the License for the specific language governing permissions and
202 | limitations under the License.
--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | # dom2html
2 | Serializes a dom-like JSON tree into HTML.
3 | This is helpful if you end up with a DOM-like JSON object and need to serialize it to HTML.
4 | An example use case is using [puppeteer](https://pptr.dev/) to get the DOM tree from a page
5 | and wanting to recreate the flattened HTML including shadow roots, and by default, the contents of iframes.
6 |
7 | ## Usage
8 |
9 | ```javascript
10 | const serialize = require('dom2html');
11 | const jsonDOM = require('./dom.json');
12 |
13 | console.log(serialize(jsonDOM, true, 'all'));
14 | ```
15 |
16 | ## Parameters
17 | serialize accepts three inputs
18 | ```javascript
19 | serialize(jsonDOM, includeIframes, domErrorOutput)
20 | ```
21 | *jsonDom* is the nodelke JSON tree
22 | *includeIframes* is a boolean flag to define if you want to serialize iframe content, **optional, defaults to true**
23 | *domErrorOutput* is a string that defines where dom2html outputs errors if it cannot serialzie a node, 'all' outputs to console & inserts a html comment in the outputted html, 'console' only outputs to console.log(), 'comments' only outputs to html comments and silent outputs to neither. **optional, defaults to all**
24 |
25 | ## An example
26 |
27 | Let's say we have this JSON representation of a webpage:
28 |
29 | ```json
30 | {
31 | "nodeId": 1,
32 | "backendNodeId": 3,
33 | "nodeType": 9,
34 | "nodeName": "#document",
35 | "localName": "",
36 | "nodeValue": "",
37 | "childNodeCount": 2,
38 | "children": [{
39 | "nodeId": 2,
40 | "parentId": 1,
41 | "backendNodeId": 8,
42 | "nodeType": 10,
43 | "nodeName": "html",
44 | "localName": "",
45 | "nodeValue": "",
46 | "publicId": "",
47 | "systemId": ""
48 | }, {
49 | "nodeId": 3,
50 | "parentId": 1,
51 | "backendNodeId": 9,
52 | "nodeType": 1,
53 | "nodeName": "HTML",
54 | "localName": "html",
55 | "nodeValue": "",
56 | "childNodeCount": 2,
57 | "children": [{
58 | "nodeId": 4,
59 | "parentId": 3,
60 | "backendNodeId": 10,
61 | "nodeType": 1,
62 | "nodeName": "HEAD",
63 | "localName": "head",
64 | "nodeValue": "",
65 | "childNodeCount": 1,
66 | "children": [{
67 | "nodeId": 5,
68 | "parentId": 4,
69 | "backendNodeId": 11,
70 | "nodeType": 1,
71 | "nodeName": "STYLE",
72 | "localName": "style",
73 | "nodeValue": "",
74 | "childNodeCount": 1,
75 | "children": [{
76 | "nodeId": 6,
77 | "parentId": 5,
78 | "backendNodeId": 12,
79 | "nodeType": 3,
80 | "nodeName": "#text",
81 | "localName": "",
82 | "nodeValue": "\n h1 { color: red; }\n "
83 | }],
84 | "attributes": []
85 | }],
86 | "attributes": []
87 | }, {
88 | "nodeId": 7,
89 | "parentId": 3,
90 | "backendNodeId": 13,
91 | "nodeType": 1,
92 | "nodeName": "BODY",
93 | "localName": "body",
94 | "nodeValue": "",
95 | "childNodeCount": 5,
96 | "children": [{
97 | "nodeId": 8,
98 | "parentId": 7,
99 | "backendNodeId": 4,
100 | "nodeType": 1,
101 | "nodeName": "H1",
102 | "localName": "h1",
103 | "nodeValue": "",
104 | "childNodeCount": 1,
105 | "children": [{
106 | "nodeId": 9,
107 | "parentId": 8,
108 | "backendNodeId": 14,
109 | "nodeType": 3,
110 | "nodeName": "#text",
111 | "localName": "",
112 | "nodeValue": "Hello World!"
113 | }],
114 | "attributes": []
115 | }, {
116 | "nodeId": 10,
117 | "parentId": 7,
118 | "backendNodeId": 5,
119 | "nodeType": 1,
120 | "nodeName": "P",
121 | "localName": "p",
122 | "nodeValue": "",
123 | "childNodeCount": 1,
124 | "children": [{
125 | "nodeId": 11,
126 | "parentId": 10,
127 | "backendNodeId": 15,
128 | "nodeType": 3,
129 | "nodeName": "#text",
130 | "localName": "",
131 | "nodeValue": "This is some content."
132 | }],
133 | "attributes": []
134 | }, {
135 | "nodeId": 12,
136 | "parentId": 7,
137 | "backendNodeId": 16,
138 | "nodeType": 1,
139 | "nodeName": "P",
140 | "localName": "p",
141 | "nodeValue": "",
142 | "childNodeCount": 1,
143 | "children": [{
144 | "nodeId": 13,
145 | "parentId": 12,
146 | "backendNodeId": 6,
147 | "nodeType": 1,
148 | "nodeName": "IMG",
149 | "localName": "img",
150 | "nodeValue": "",
151 | "childNodeCount": 0,
152 | "children": [],
153 | "attributes": ["src", "http://placekitten.com/200/300", "alt", "Some image"]
154 | }],
155 | "attributes": []
156 | }, {
157 | "nodeId": 14,
158 | "parentId": 7,
159 | "backendNodeId": 7,
160 | "nodeType": 1,
161 | "nodeName": "P",
162 | "localName": "p",
163 | "nodeValue": "",
164 | "childNodeCount": 1,
165 | "children": [{
166 | "nodeId": 15,
167 | "parentId": 14,
168 | "backendNodeId": 17,
169 | "nodeType": 3,
170 | "nodeName": "#text",
171 | "localName": "",
172 | "nodeValue": "Data-Attributes!"
173 | }],
174 | "attributes": ["data-test", "works"]
175 | }, {
176 | "nodeId": 16,
177 | "parentId": 7,
178 | "backendNodeId": 18,
179 | "nodeType": 1,
180 | "nodeName": "SCRIPT",
181 | "localName": "script",
182 | "nodeValue": "",
183 | "childNodeCount": 1,
184 | "children": [{
185 | "nodeId": 17,
186 | "parentId": 16,
187 | "backendNodeId": 19,
188 | "nodeType": 3,
189 | "nodeName": "#text",
190 | "localName": "",
191 | "nodeValue": " window.title = 'Hello world!' "
192 | }],
193 | "attributes": []
194 | }],
195 | "attributes": []
196 | }],
197 | "attributes": ["lang", "en"],
198 | "frameId": "D46CBAE99B5CABE7F1FF6DDEE269E6A6"
199 | }],
200 | "documentURL": "http://test.local/test-simple.html",
201 | "baseURL": "http://test.local/test-simple.html",
202 | "xmlVersion": ""
203 | }
204 | ```
205 |
206 | and we want to get the HTML representation:
207 |
208 | ```html
209 |
210 |
211 |
214 |
215 |
216 | Hello World!
217 | This is some content.
218 | 
219 | Data-Attributes!
220 |
221 |
222 |
223 | ```
224 |
225 | For this we can use the following code:
226 |
227 | ```javascript
228 | const serialize = require('dom2html');
229 | const jsonDOM = require('./dom.json');
230 |
231 | console.log(serialize(jsonDOM));
232 | ```
233 |
234 | ## Prevent