From 1c58bbe3038f582dbec7006d573ed5bd50e73227 Mon Sep 17 00:00:00 2001 From: Matthieu Gautier Date: Sun, 14 Jan 2024 12:08:54 +0100 Subject: [PATCH] Adapt to `warc2zim2` branch of warc2zim. `warc2zim2` branch create zim files without service worker. --- Dockerfile | 2 +- test/integration.py | 10 +++++----- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/Dockerfile b/Dockerfile index 298f7ec..d471fb6 100644 --- a/Dockerfile +++ b/Dockerfile @@ -9,7 +9,7 @@ RUN apt-get update \ # python setup (in venv not to conflict with browsertrix) && python3 -m venv /app/zimit \ && /app/zimit/bin/python -m pip install --no-cache-dir 'requests==2.31.0' 'inotify==0.2.10' 'tld==0.13' \ - 'git+https://github.com/openzim/warc2zim@main#egg_name=warc2zim' \ + 'git+https://github.com/openzim/warc2zim@warc2zim2#egg_name=warc2zim' \ # placeholder (default output location) && mkdir -p /output \ # disable chrome upgrade diff --git a/test/integration.py b/test/integration.py index 1782b34..95f7924 100644 --- a/test/integration.py +++ b/test/integration.py @@ -6,9 +6,9 @@ import libzim.reader from warcio import ArchiveIterator -def get_zim_article(zimfile, path): +def get_zim_main_entry(zimfile): zim_fh = libzim.reader.Archive(zimfile) - return zim_fh.get_entry_by_path(path).get_item().content.tobytes() + return zim_fh.main_entry def test_is_file(): @@ -20,9 +20,9 @@ def test_zim_main_page(): """Main page specified, http://isago.rskg.org/, was a redirect to https Ensure main page is the redirected page""" - assert b'"https://isago.rskg.org/"' in get_zim_article( - "/output/isago.zim", "A/index.html" - ) + main_entry = get_zim_main_entry("/output/isago.zim") + assert main_entry.is_redirect + assert main_entry.get_redirect_entry().path == "isago.rskg.org/" def test_user_agent():