From e24479945f79113694cb76e14a62e4ddf2c2020e Mon Sep 17 00:00:00 2001 From: benoit74 Date: Wed, 27 Mar 2024 13:18:04 +0000 Subject: [PATCH] Remove trailing characters when retrieving Browsertrix Crawler version --- CHANGELOG.md | 7 +++++++ src/zimit/zimit.py | 2 +- 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index ac640f3..a4d077b 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -12,6 +12,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 - New `--version` flag to display Zimit version - New `--logging` flag to adjust Browsertrix Crawler logging (#273) - Use new `--scraper-suffix` flag of warc2zim to enhance ZIM "Scraper" metadata (#275) +- New `--noMobileDevice` CLI argument ### Changed @@ -21,6 +22,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 - Adopt Python bootstrap conventions - Removed handling of redirects by zimit, they are handled by browsertrix crawler and detected properly by warc2zim - Upgrade to Python 3.12 + upgrade dependencies +- `--userAgent` CLI argument overrides again the `--userAgentSuffix` and `--adminEmail` values +- `--userAgent` CLI arguement is not mandatory anymore + +### Fixed + +- Fix support for Youtube videos (#291) ## [1.6.3] - 2024-01-18 diff --git a/src/zimit/zimit.py b/src/zimit/zimit.py index a1d45d8..7c2764a 100755 --- a/src/zimit/zimit.py +++ b/src/zimit/zimit.py @@ -370,7 +370,7 @@ def run(raw_args): except Exception: logger.error("Failed to get Browsertrix crawler version") raise - crawler_version = crawl.stdout + crawler_version = crawl.stdout.strip() logger.info(f"Browsertrix crawler: version {crawler_version}") # pass a scraper suffix to warc2zim so that both zimit, warc2zim and crawler