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

cleanup dockerfile + fix test (#595)

Browse source 
- remove obsolete line from Dockerfile
- fix pdf test to webrecorder-hosted pdf
This commit is contained in:
Ilya Kreymer 2024-06-06 12:14:44 -07:00 • committed by GitHub
parent 068ee79288
commit 1bd94d93a1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 1 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

3
Dockerfile
View file

@ -28,9 +28,6 @@ ADD package.json /app/
# to allow forcing rebuilds from this stage
ARG REBUILD
# Prefetch tldextract so pywb is able to boot in environments with limited internet access
RUN tldextract --update
# Download and format ad host blocklist as JSON
RUN mkdir -p /tmp/ads && cd /tmp/ads && \
curl -vs -o ad-hosts.txt https://raw.githubusercontent.com/StevenBlack/hosts/master/hosts && \

2
tests/pdf-crawl.test.js
View file

@ -3,7 +3,7 @@ import fs from "fs";
import path from "path";
import { WARCParser } from "warcio";
const PDF = "http://bibnum.bnf.fr/WARC/WARC_ISO_28500_version1_latestdraft.pdf";
const PDF = "https://specs.webrecorder.net/wacz/1.1.1/wacz-2021.pdf";
test("ensure pdf is crawled", async () => {
child_process.execSync(