├── LICENSE
├── README.md
├── archive_page.html
└── html_from_archive.py
/LICENSE:
--------------------------------------------------------------------------------
1 | MIT License
2 |
3 | Copyright (c) 2018 Dizzy
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 | # Mastodon Archive Viewer (modified by slshyn 11/09/2020)
2 | A html script to take a mastodon archive and convert it into a human-readable webpage for viewing. Currently available as a hacky html file with some inline JS.
3 |
4 | # Features:
5 | ## original
6 | * organizes your old posts into a conveniently readable timeline
7 | * includes media attachments in posts
8 | * Preserves content warnings/summaries
9 | * Tries to use the header from the archive as the background
10 | * Tries to use the avatar from the archive as the avatar next to your old posts
11 | ## modified by slshyn 11/07/2020
12 | * fixed a few link problems
13 | * prettier interface, more similar to mastodon dark theme
14 | * more details from the toots and user profile added
15 | ## modified by slshyn 11/08/2020
16 | * separate page on only toots & media
17 | * archive column on months and year, stick on the screen when scroll down
18 | * back to top button when scroll down
19 | ## modified by slshyn 11/09/2020
20 | * added click to open image
21 | * fixed a few visual problems
22 | * added scroll on archive column
23 | * added open link on a new tab when click
24 | ## fixed by slshyn 11/10/2020
25 | * fixed picture display problem
26 | * modified .sticky column
27 |
28 | # Usage
29 | With Python (unchanged, can still work as the original viewer):
30 | * To make a webpage to view your archive, just place the `html_from_archive.py` script in the root of the archive (the folder that has `outbox.json` and `media_attachments` in it) and run it using python3
31 | * From the command line: `python3 html_from_archive.py`
32 | * You can also set it as executable and run it directly or, on Windows, right click and open it with python 3.
33 | * Open the resulting `processed_archive.html` file in your web browser.
34 |
35 | Without Python (modified by slshyn):
36 |
37 | * Download the `archive_page.html` file. Place it in the root of the archive (the folder that has `outbox.json` and `media_attachments/` in it).
38 | * Open `archive_page.html` in your web browser. Open the `actor.json` and `outbox.json` file from within the page and it will load it.
39 |
40 |
41 | # Next steps:
42 |
43 | - [x] separate page on only toots & media
44 | - [x] make medias easier to view
45 | - [x] click to open pictures (why `addEventListener click` didn't work...)
46 | - [ ] prettier interface
47 |
48 | Open to suggestions. Chinese and English ok.
49 |
--------------------------------------------------------------------------------
/archive_page.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 | Mastodon Archive
6 |
7 |
8 |
489 |
490 |
491 |
526 | Select actor.json and outbox.json in the archive folder.
527 |
528 |
529 |
533 |
537 |
538 |
539 |
540 |
541 |
542 |
543 |
544 |
545 |
546 |
547 |
548 |
549 |
550 |
551 |
552 |
553 |
554 |
555 |
556 |
557 |
558 |
559 |
560 |
561 |
562 |
563 |
564 |
565 |
566 |
567 |
568 |
569 |
570 |
571 |
572 |
573 |
574 |
575 |
576 |
577 |
578 | ×
579 |
580 |
581 |
582 |
583 |
584 |
850 |
851 |
852 |
853 |
--------------------------------------------------------------------------------
/html_from_archive.py:
--------------------------------------------------------------------------------
1 | import json
2 | from os import path
3 | with open("outbox.json", "r") as outbox_file:
4 | outbox = json.loads(outbox_file.read())
5 | with open("actor.json", "r") as actor_file:
6 | actor = json.loads(actor_file.read())
7 | #map the outbox down to the actual objects
8 | statuses = [status.get("object") for status in outbox.get("orderedItems")]
9 |
10 | articles = []
11 | #attachment urls may begin with "/media/" or something else we dont want
12 | # start with an offset of 1 to avoid checking root for /media or something else wrong
13 | pathOffset = 1
14 |
15 | for status in statuses:
16 | #need to ignore objects that arent status dicts
17 | if type(status) == type({}):
18 | date = status.get("published")
19 | summary = status.get("summary")
20 | htmlContent = status.get("content")
21 | attachments = [attachment.get("url") for attachment in status.get("attachment")]
22 | images = ""
23 | for imageURL in attachments:
24 | # only runs the loop for the first media url in the archive
25 | if pathOffset == 1:
26 | while not path.exists(imageURL[pathOffset:]) and pathOffset < len(imageURL):
27 | pathOffset +=1
28 |
29 | if imageURL[-4:] == ".mp4" or imageURL[-5:] == ".webm":
30 | images += "".format(imageURL[pathOffset:])
31 | else:
32 | images += "".format(imageURL[pathOffset:])
33 | if summary:
34 | article = "\
35 |
\
73 |