docs: add jekyll just-the-docs docs, initial pass
This commit is contained in:
Ilya Kreymer
@@ -6,4 +6,7 @@ dist/sw.js
|
|||||||
**/node_modules
|
**/node_modules
|
||||||
yarn-error.log
|
yarn-error.log
|
||||||
coverage/
|
coverage/
|
||||||
|
local-examples/
|
||||||
.DS_Store
|
.DS_Store
|
||||||
|
.sass-cache/
|
||||||
|
_site/
|
||||||
|
|||||||
@@ -0,0 +1,67 @@
|
|||||||
|
GEM
|
||||||
|
specs:
|
||||||
|
addressable (2.7.0)
|
||||||
|
public_suffix (>= 2.0.2, < 5.0)
|
||||||
|
colorator (1.1.0)
|
||||||
|
concurrent-ruby (1.1.6)
|
||||||
|
em-websocket (0.5.1)
|
||||||
|
eventmachine (>= 0.12.9)
|
||||||
|
http_parser.rb (~> 0.6.0)
|
||||||
|
eventmachine (1.2.7)
|
||||||
|
ffi (1.12.2)
|
||||||
|
forwardable-extended (2.6.0)
|
||||||
|
http_parser.rb (0.6.0)
|
||||||
|
i18n (0.9.5)
|
||||||
|
concurrent-ruby (~> 1.0)
|
||||||
|
jekyll (3.8.6)
|
||||||
|
addressable (~> 2.4)
|
||||||
|
colorator (~> 1.0)
|
||||||
|
em-websocket (~> 0.5)
|
||||||
|
i18n (~> 0.7)
|
||||||
|
jekyll-sass-converter (~> 1.0)
|
||||||
|
jekyll-watch (~> 2.0)
|
||||||
|
kramdown (~> 1.14)
|
||||||
|
liquid (~> 4.0)
|
||||||
|
mercenary (~> 0.3.3)
|
||||||
|
pathutil (~> 0.9)
|
||||||
|
rouge (>= 1.7, < 4)
|
||||||
|
safe_yaml (~> 1.0)
|
||||||
|
jekyll-sass-converter (1.5.2)
|
||||||
|
sass (~> 3.4)
|
||||||
|
jekyll-seo-tag (2.6.1)
|
||||||
|
jekyll (>= 3.3, < 5.0)
|
||||||
|
jekyll-watch (2.2.1)
|
||||||
|
listen (~> 3.0)
|
||||||
|
just-the-docs (0.2.7)
|
||||||
|
jekyll (~> 3.8.5)
|
||||||
|
jekyll-seo-tag (~> 2.0)
|
||||||
|
rake (~> 12.3.1)
|
||||||
|
kramdown (1.17.0)
|
||||||
|
liquid (4.0.3)
|
||||||
|
listen (3.2.1)
|
||||||
|
rb-fsevent (~> 0.10, >= 0.10.3)
|
||||||
|
rb-inotify (~> 0.9, >= 0.9.10)
|
||||||
|
mercenary (0.3.6)
|
||||||
|
pathutil (0.16.2)
|
||||||
|
forwardable-extended (~> 2.6)
|
||||||
|
public_suffix (4.0.3)
|
||||||
|
rake (12.3.3)
|
||||||
|
rb-fsevent (0.10.3)
|
||||||
|
rb-inotify (0.10.1)
|
||||||
|
ffi (~> 1.0)
|
||||||
|
rouge (3.17.0)
|
||||||
|
safe_yaml (1.0.5)
|
||||||
|
sass (3.7.4)
|
||||||
|
sass-listen (~> 4.0.0)
|
||||||
|
sass-listen (4.0.0)
|
||||||
|
rb-fsevent (~> 0.9, >= 0.9.4)
|
||||||
|
rb-inotify (~> 0.9, >= 0.9.7)
|
||||||
|
|
||||||
|
PLATFORMS
|
||||||
|
ruby
|
||||||
|
|
||||||
|
DEPENDENCIES
|
||||||
|
just-the-docs
|
||||||
|
|
||||||
|
BUNDLED WITH
|
||||||
|
2.1.4
|
||||||
+22
@@ -0,0 +1,22 @@
|
|||||||
|
remote_theme: pmarsceill/just-the-docs
|
||||||
|
theme: "just-the-docs"
|
||||||
|
|
||||||
|
title: ReplayWeb.Page
|
||||||
|
|
||||||
|
# Enable or disable the site search
|
||||||
|
search_enabled: false
|
||||||
|
|
||||||
|
# Set the search token separator for hyphenated-word search:
|
||||||
|
search_tokenizer_separator: /[\s/]+/
|
||||||
|
|
||||||
|
# Enable or disable heading anchors
|
||||||
|
heading_anchors: true
|
||||||
|
|
||||||
|
# Aux links for the upper right navigation
|
||||||
|
aux_links:
|
||||||
|
"View replayweb.page on GitHub":
|
||||||
|
- "//github.com/ikreymer/replayweb.page"
|
||||||
|
|
||||||
|
|
||||||
|
logo: "/static/logo.svg"
|
||||||
|
|
||||||
@@ -0,0 +1,5 @@
|
|||||||
|
{% if site.logo %}
|
||||||
|
<div class="site-logo"></div>
|
||||||
|
{% endif %}
|
||||||
|
<span class="rwp-logo-font rwp-green">replay</span>
|
||||||
|
<span class="rwp-logo-font rwp-yellow">web.page</span>
|
||||||
@@ -0,0 +1,33 @@
|
|||||||
|
$rwp-green: #64e986;
|
||||||
|
$rwp-yellow: #f5c71a;
|
||||||
|
//$link-color: #27a0ff;
|
||||||
|
$link-color: #4876ff;
|
||||||
|
|
||||||
|
//$content-width: 960px;
|
||||||
|
$nav-width-md: $nav-width;
|
||||||
|
|
||||||
|
.side-bar {
|
||||||
|
@include mq(md) {
|
||||||
|
//max-width: calc(0.5rem + #{$nav-width});
|
||||||
|
max-width: $nav-width;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
.site-title {
|
||||||
|
padding-right: 1.5rem !important;
|
||||||
|
}
|
||||||
|
|
||||||
|
.rwp-logo-font {
|
||||||
|
font-variant-caps: all-small-caps;
|
||||||
|
font-size: 20px;
|
||||||
|
font-weight: bold;
|
||||||
|
}
|
||||||
|
|
||||||
|
.rwp-green {
|
||||||
|
color: $rwp-green;
|
||||||
|
}
|
||||||
|
|
||||||
|
.rwp-yellow {
|
||||||
|
color: $rwp-yellow;
|
||||||
|
}
|
||||||
|
|
||||||
@@ -0,0 +1,79 @@
|
|||||||
|
---
|
||||||
|
layout: default
|
||||||
|
title: Browsing Web Archives
|
||||||
|
nav_order: 1
|
||||||
|
parent: Usage
|
||||||
|
permalink: /docs/browsing
|
||||||
|
---
|
||||||
|
|
||||||
|
# Browsing Web Archives via the ReplayWeb.page
|
||||||
|
{: .no_toc }
|
||||||
|
|
||||||
|
## Table of contents
|
||||||
|
{: .no_toc .text-delta }
|
||||||
|
|
||||||
|
1. TOC
|
||||||
|
{:toc}
|
||||||
|
|
||||||
|
|
||||||
|
## Loading Web Archives
|
||||||
|
|
||||||
|
Using [https://replayweb.page](https://replayweb.page), you can select a web archive file from a local
|
||||||
|
file or remote URL to load into the site.
|
||||||
|
|
||||||
|
Archives loaded by ReplayWeb.page are identified by their unique URL, which can be entered directly or selected from a local file browser.
|
||||||
|
|
||||||
|
|
||||||
|
### Remote Archives
|
||||||
|
|
||||||
|
To load a remote archive, simply enter the URL of the archive and click `Replay!`.
|
||||||
|
(See: [Supported Locations](locations.md) for details on where archives can be loaded from).
|
||||||
|
|
||||||
|
The archive will be downloaded, either fully or [only as needed (if possible)](streaming-archives.md) and presented on the archive page.
|
||||||
|
|
||||||
|
The system supports WARC files, as well as several other formats (See: [Supported Formats](formats.md) for more details on supported formats)
|
||||||
|
|
||||||
|
Once loaded, the page is redirected to the archive collection page.
|
||||||
|
|
||||||
|
|
||||||
|
### Local Archives
|
||||||
|
|
||||||
|
Using the `Choose File` button, you can pick any local archive file to load for replay.
|
||||||
|
The click `Replay` to load the file.
|
||||||
|
|
||||||
|
The archive is laoded in the browser directly and *not* uploaded anywhere -- it never leaves your computer!
|
||||||
|
|
||||||
|
(This process is similar to how [Webrecorder Player](https://github.com/webrecorder/webrecorder-player) works, but happens entirely in the browser.
|
||||||
|
|
||||||
|
|
||||||
|
It will be identified by a `file://` URL and is not accessible outside your browser.
|
||||||
|
|
||||||
|
|
||||||
|
## Archive View
|
||||||
|
|
||||||
|
Once an archive is loaded, you are taken to the archive view, and you are ready to explore and replay the web archive!
|
||||||
|
|
||||||
|
This view has several tabs:
|
||||||
|
|
||||||
|
- **Curated Pages** - This tab exists if the archive has curated lists of pages. Currently this is available only for Webrecorder WARCs, but may be possible
|
||||||
|
with other formats (see: [Web Archive Zip Format](webarchive-zip-format.md)
|
||||||
|
|
||||||
|
- **URL Resources** - This tab allows searching the archive by URLs, as well as by MIME type. For many archives with no page or curatorial metadata, this is
|
||||||
|
a way to explore the archive data in more detail.
|
||||||
|
|
||||||
|
Once a URL is selected, you will be taken to the Replay tab which renders the archived page directly in your browser.
|
||||||
|
|
||||||
|
|
||||||
|
## Index of Archives
|
||||||
|
|
||||||
|
The ReplayWeb.page homepage lists an index of all archives loaded in your browser.
|
||||||
|
Once loaded, the archive remains cached in the browser for quick access. This view will be unique to your browser.
|
||||||
|
To remove the archive from your browser, click on the 'X'. (Of course, this does not delete the archive from its original location, only your local copy of it)
|
||||||
|
|
||||||
|
|
||||||
|
<hr>
|
||||||
|
Next: [Sharing Links to Archived Pages](linking.md)
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
@@ -0,0 +1,8 @@
|
|||||||
|
---
|
||||||
|
layout: default
|
||||||
|
title: Linking to Web Archives
|
||||||
|
nav_order: 2
|
||||||
|
parent: Usage
|
||||||
|
permalink: /docs/linking
|
||||||
|
---
|
||||||
|
|
||||||
@@ -0,0 +1,11 @@
|
|||||||
|
---
|
||||||
|
layout: default
|
||||||
|
title: Reference
|
||||||
|
nav_order: 2
|
||||||
|
has_children: true
|
||||||
|
permalink: /docs/reference
|
||||||
|
---
|
||||||
|
|
||||||
|
## Reference
|
||||||
|
|
||||||
|
A guide to the file formats, source locations and query arguments supported by ReplayWeb.Page
|
||||||
@@ -0,0 +1,26 @@
|
|||||||
|
---
|
||||||
|
layout: default
|
||||||
|
title: 'Supported Formats'
|
||||||
|
nav_order: 2
|
||||||
|
description: 'Supported Formats'
|
||||||
|
permalink: /docs/formats
|
||||||
|
parent: Reference
|
||||||
|
---
|
||||||
|
|
||||||
|
## Supported Formats
|
||||||
|
|
||||||
|
ReplayWeb.Page supports the following archive formats.
|
||||||
|
Format is currently determined based on the extension, though more extensive detection may be added later.
|
||||||
|
|
||||||
|
|
||||||
|
| Format | Extensions | Status |
|
||||||
|
|:--------|:--------------------|:--------------|
|
||||||
|
| WARC | `.warc`, `.warc.gz` | <span class="d-inline-block p-2 mr-1 v-align-middle bg-green-000"> Supported |
|
||||||
|
| HAR | `.har` | <span class="d-inline-block p-2 mr-1 v-align-middle bg-green-000"> Supported |
|
||||||
|
| WBN | `.wbn` | <span class="d-inline-block p-2 mr-1 v-align-middle bg-yellow-000"> Experimental |
|
||||||
|
| ARC | `.arc` | <span class="d-inline-block p-2 mr-1 v-align-middle bg-red-000"> Not Supported |
|
||||||
|
| CDX | `.cdx`, `.cdxj` | <span class="d-inline-block p-2 mr-1 v-align-middle bg-green-000"> Supported |
|
||||||
|
| ZIP | `.zip`, `.waz` | <span class="d-inline-block p-2 mr-1 v-align-middle bg-yellow-000"> In Progress |
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
@@ -0,0 +1,77 @@
|
|||||||
|
---
|
||||||
|
layout: default
|
||||||
|
title: 'Supported Locations'
|
||||||
|
nav_order: 1
|
||||||
|
description: 'Supported Locations'
|
||||||
|
parent: Reference
|
||||||
|
permalink: /docs/locations
|
||||||
|
---
|
||||||
|
|
||||||
|
## Supported Location URLs
|
||||||
|
|
||||||
|
ReplayWeb.Page uses URLs to uniquely indentify web archives.
|
||||||
|
|
||||||
|
In addition HTTP/S, the system supports loading from additional cloud providers
|
||||||
|
and via peer-to-peer decentralized services. The goal is to support loading
|
||||||
|
web archives from any source a web browser can connect to.
|
||||||
|
|
||||||
|
The following is a list of currently supported URL schemes and details below:
|
||||||
|
|
||||||
|
|
||||||
|
| Scheme | Status |
|
||||||
|
|:-----------------|:------------|
|
||||||
|
| `https://` | <span class="d-inline-block p-2 mr-1 v-align-middle bg-green-000"> Supported |
|
||||||
|
| `http://` | <span class="d-inline-block p-2 mr-1 v-align-middle bg-green-000"> Supported |
|
||||||
|
| `file://` | <span class="d-inline-block p-2 mr-1 v-align-middle bg-green-000"> Supported |
|
||||||
|
| `s3://` | <span class="d-inline-block p-2 mr-1 v-align-middle bg-green-000"> Supported |
|
||||||
|
| `googledrive://` | <span class="d-inline-block p-2 mr-1 v-align-middle bg-yellow-000"> In progress |
|
||||||
|
| `ipfs://` | <span class="d-inline-block p-2 mr-1 v-align-middle bg-yellow-000"> Partial |
|
||||||
|
| `dat://` | <span class="d-inline-block p-2 mr-1 v-align-middle text-grey-lt-000 bg-purple-000"> Planned |
|
||||||
|
|
||||||
|
|
||||||
|
### HTTP and HTTPS
|
||||||
|
|
||||||
|
While `https://replayweb.page` can load from any url, a site must allow access by enabling [CORS](https://developer.mozilla.org/en-US/docs/Web/HTTP/CORS)
|
||||||
|
for the web archive. HTTP URLs may not be accessible from `https://replayweb.page` since it requires HTTPS.
|
||||||
|
|
||||||
|
If you need to provide access to web archives stored on your own domain or over HTTP, consider
|
||||||
|
deploying a copy on your server. See: Running your Own.
|
||||||
|
|
||||||
|
### Local Files
|
||||||
|
|
||||||
|
Local files selected via the UI file chooser, and will be given a `file://` URL.
|
||||||
|
Unlike other web archive URLs, file URLs can not be shared with others.
|
||||||
|
|
||||||
|
|
||||||
|
### Amazon S3
|
||||||
|
|
||||||
|
The `s3://` url scheme is provided as a convenience to reference S3 URLs. The URL is converted to an HTTPS URL for access.
|
||||||
|
The S3 Bucket must be public and also provide access to `https://replayweb.page` via CORS.
|
||||||
|
Downloading via S3 credentials is not currently supported.
|
||||||
|
|
||||||
|
|
||||||
|
### Google Drive
|
||||||
|
|
||||||
|
The `googledrive://` url scheme is used when accessing a web archive shared over google drive. It provides a unique identifier
|
||||||
|
provided via Google Drive. When accessing a google drive URL, the user will be asked to authenticate to be able to access the file.
|
||||||
|
|
||||||
|
|
||||||
|
### IPFS
|
||||||
|
{: .d-inline-block }
|
||||||
|
|
||||||
|
Help Wanted
|
||||||
|
{: .label .label-yellow }
|
||||||
|
|
||||||
|
|
||||||
|
The `ipfs://` url scheme is provide as a convenience and resolves to using the Cloudflare IPFS Gateway to download archives from IPFS.
|
||||||
|
A better implementation with IPFS directly is also possible.
|
||||||
|
|
||||||
|
|
||||||
|
### DAT
|
||||||
|
{: .d-inline-block }
|
||||||
|
|
||||||
|
Help Wanted
|
||||||
|
{: .label .label-yellow }
|
||||||
|
|
||||||
|
Support for `dat://` is planned to allow true peer-to-peer transfer of web archives.
|
||||||
|
|
||||||
@@ -0,0 +1,20 @@
|
|||||||
|
---
|
||||||
|
layout: default
|
||||||
|
title: Usage
|
||||||
|
nav_order: 1
|
||||||
|
description: 'Usage'
|
||||||
|
has_children: true
|
||||||
|
permalink: /docs
|
||||||
|
---
|
||||||
|
|
||||||
|
# ReplayWeb.Page
|
||||||
|
## Serverless / Client-Side Web Archive Replay
|
||||||
|
|
||||||
|
A browser-based system to replay archived web pages as accurately as possible, with all interactive elements preserved.
|
||||||
|
{: .fs-6 .fw-300 }
|
||||||
|
|
||||||
|
No server necessary. Archives can be loaded as static files from anywhere a browser can connect to.
|
||||||
|
{: .fs-6 .fw-300 }
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
Reference in New Issue
Block a user