kiwix/zimit
1
0
Fork 0
mirror of https://github.com/openzim/zimit.git synced 2025-09-22 11:22:23 -04:00
Code Issues Packages Projects Releases Wiki Activity

Adapt to warc2zim2 branch of warc2zim.

Browse Source 
`warc2zim2` branch create zim files without service worker.
This commit is contained in:
Matthieu Gautier 2024-01-14 12:08:54 +01:00 committed by benoit74
parent eab3d1f189
commit 1c58bbe303
No known key found for this signature in database
GPG Key ID: B89606434FC7B530
2 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Dockerfile
View File

@ -9,7 +9,7 @@ RUN apt-get update \
# python setup (in venv not to conflict with browsertrix) # python setup (in venv not to conflict with browsertrix)
&& python3 -m venv /app/zimit \ && 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' \ && /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) # placeholder (default output location)
&& mkdir -p /output \ && mkdir -p /output \
# disable chrome upgrade # disable chrome upgrade

10
test/integration.py
View File

@ -6,9 +6,9 @@ import libzim.reader
from warcio import ArchiveIterator from warcio import ArchiveIterator
def get_zim_article(zimfile, path): def get_zim_main_entry(zimfile):
zim_fh = libzim.reader.Archive(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(): 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 """Main page specified, http://isago.rskg.org/, was a redirect to https
Ensure main page is the redirected page""" Ensure main page is the redirected page"""
assert b'"https://isago.rskg.org/"' in get_zim_article( main_entry = get_zim_main_entry("/output/isago.zim")
"/output/isago.zim", "A/index.html" assert main_entry.is_redirect
) assert main_entry.get_redirect_entry().path == "isago.rskg.org/"
def test_user_agent(): def test_user_agent():