From 66037535fd5297ffcec7036caa3e7f8f01b0f429 Mon Sep 17 00:00:00 2001 From: Cristian Date: Tue, 1 Sep 2020 10:16:24 -0500 Subject: [PATCH] feat: Add curl command on readability as default command to debug --- archivebox/extractors/readability.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/archivebox/extractors/readability.py b/archivebox/extractors/readability.py index 52d3b6ae..5508e096 100644 --- a/archivebox/extractors/readability.py +++ b/archivebox/extractors/readability.py @@ -16,6 +16,7 @@ from ..util import ( ) from ..config import ( TIMEOUT, + CURL_BINARY, SAVE_READABILITY, DEPENDENCIES, READABILITY_VERSION, @@ -65,7 +66,10 @@ def save_readability(link: Link, out_dir: Optional[str]=None, timeout: int=TIMEO # Readability Docs: https://github.com/mozilla/readability status = 'succeeded' - cmd = [] + cmd = [ + CURL_BINARY, + link.url + ] timer = TimedProgress(timeout, prefix=' ') try: document = get_html(link, out_dir)