From 6d82655cc40e2a817be73b1725ec2b31dd6ed872 Mon Sep 17 00:00:00 2001 From: msramalho <19508417+msramalho@users.noreply.github.com> Date: Tue, 10 Jun 2025 16:14:34 +0100 Subject: [PATCH] manifest improvement for antibot --- .../modules/antibot_extractor_enricher/__manifest__.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/src/auto_archiver/modules/antibot_extractor_enricher/__manifest__.py b/src/auto_archiver/modules/antibot_extractor_enricher/__manifest__.py index d2e9d66..d93c072 100644 --- a/src/auto_archiver/modules/antibot_extractor_enricher/__manifest__.py +++ b/src/auto_archiver/modules/antibot_extractor_enricher/__manifest__.py @@ -31,7 +31,9 @@ }, }, "description": """ - Uses a browser controlled by SeleniumBase to capture HTML, media, and screenshots/PDFs of a web page, by bypassing anti-bot measures like Cloudflare's Turnstile. + Uses a browser controlled by SeleniumBase to capture HTML, media, and screenshots/PDFs of a web page, by bypassing anti-bot measures like Cloudflare's Turnstile or Google Recaptcha. + + Still in trial development, please report any issues or suggestions via GitHub Issues. ### Features - Extracts the HTML source code of the page. @@ -40,7 +42,6 @@ - Downloads images and videos from the page, excluding specified file extensions. ### Notes - - Requires a WebDriver (e.g., ChromeDriver) installed and accessible via the system's PATH. - Using a proxy affects Cloudflare Turnstile captcha handling, so it is recommended to use a proxy only if necessary. """, }