crawler 0.10.3 and main warc2zim

This commit is contained in:
renaud gaudin 2023-08-10 18:51:19 +00:00
parent e590e851be
commit 1224476b41
No known key found for this signature in database
GPG key ID: 447475A4CFBA2E24
2 changed files with 9 additions and 2 deletions

View file

@ -5,6 +5,13 @@ All notable changes to this project are documented in this file.
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html) (as of version 1.2.0).
## [Unreleased]
### Changed
- Using browsertrix-crawler 0.10.3
- Using warc2zim ⚠️⚠️ `main` branch
## [1.4.0] - 2023-08-02
### Added

View file

@ -1,4 +1,4 @@
FROM webrecorder/browsertrix-crawler:0.10.2
FROM webrecorder/browsertrix-crawler:v0.10.3
LABEL org.opencontainers.image.source https://github.com/openzim/zimit
RUN apt-get update \
@ -8,7 +8,7 @@ RUN apt-get update \
&& rm -rf /var/lib/apt/lists/* \
# 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' 'warc2zim==1.5.2' \
&& /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' \
# placeholder (default output location)
&& mkdir -p /output \
# disable chrome upgrade