Stowage/browsertrix-crawler
2
0
Fork 0
mirror of https://github.com/webrecorder/browsertrix-crawler.git synced 2025-10-19 14:33:17 +00:00
Code Issues Projects Releases Packages Wiki Activity

Adblock support (#534)

Browse source 
Now that RWP 2.0.0 with adblock support has been released
(webrecorder/replayweb.page#307), this enables adblock on the QA mode
RWP embed, to get more accurate screenshots.
Fetches the adblock.gz directly from RWP (though could also fetch it
separately from Easylist)
Updates to 1.1.0-beta.5
This commit is contained in:
Ilya Kreymer 2024-04-12 09:47:32 -07:00 • committed by GitHub
parent b5f3238c29
commit e15f0c95d9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 14 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

3
Dockerfile
View file

@ -48,9 +48,10 @@ ADD config/ /app/
ADD html/ /app/html/ ADD html/ /app/html/
ARG RWP_VERSION=1.8.15 ARG RWP_VERSION=2.0.0
ADD https://cdn.jsdelivr.net/npm/replaywebpage@${RWP_VERSION}/ui.js /app/html/rwp/ ADD https://cdn.jsdelivr.net/npm/replaywebpage@${RWP_VERSION}/ui.js /app/html/rwp/
ADD https://cdn.jsdelivr.net/npm/replaywebpage@${RWP_VERSION}/sw.js /app/html/rwp/ ADD https://cdn.jsdelivr.net/npm/replaywebpage@${RWP_VERSION}/sw.js /app/html/rwp/
ADD https://cdn.jsdelivr.net/npm/replaywebpage@${RWP_VERSION}/adblock/adblock.gz /app/html/rwp/adblock.gz
RUN chmod a+x /app/dist/main.js /app/dist/create-login-profile.js && chmod a+r /app/html/rwp/* RUN chmod a+x /app/dist/main.js /app/dist/create-login-profile.js && chmod a+r /app/html/rwp/*

1
html/replay.html
View file

@ -33,6 +33,7 @@
url="about:blank" url="about:blank"
ts="" ts=""
coll="replay" coll="replay"
useAdblock
> >
</replay-web-page> </replay-web-page>
</body> </body>

2
package.json
View file

@ -1,6 +1,6 @@
{ {
"name": "browsertrix-crawler", "name": "browsertrix-crawler",
"version": "1.1.0-beta.4", "version": "1.1.0-beta.5",
"main": "browsertrix-crawler", "main": "browsertrix-crawler",
"type": "module", "type": "module",
"repository": "https://github.com/webrecorder/browsertrix-crawler", "repository": "https://github.com/webrecorder/browsertrix-crawler",

12
src/util/replayserver.ts
View file

@ -16,6 +16,11 @@ const uiJS = fs.readFileSync(new URL("../../html/rwp/ui.js", import.meta.url), {
encoding: "utf8", encoding: "utf8",
}); });
const adblockGZ = fs.readFileSync(
new URL("../../html/rwp/adblock.gz", import.meta.url),
{},
);
// ============================================================================ // ============================================================================
const PORT = 9990; const PORT = 9990;
@ -76,9 +81,7 @@ export class ReplayServer {
return; return;
case "/sw.js": case "/sw.js":
case "/sw.js?serveIndex=1":
case "/replay/sw.js": case "/replay/sw.js":
case "/replay/sw.js?serveIndex=1":
response.writeHead(200, { "Content-Type": "application/javascript" }); response.writeHead(200, { "Content-Type": "application/javascript" });
response.end(swJS); response.end(swJS);
return; return;
@ -88,6 +91,11 @@ export class ReplayServer {
response.end(uiJS); response.end(uiJS);
return; return;
case "/replay/adblock/adblock.gz":
response.writeHead(200, { "Content-Type": "application/gzip" });
response.end(adblockGZ);
return;
case this.sourceUrl: case this.sourceUrl:
if (this.sourceContentType && this.origFileSource) { if (this.sourceContentType && this.origFileSource) {
if (!this.sourceSize) { if (!this.sourceSize) {