mirrors/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2025-05-15 07:34:27 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: Add curl command on readability as default command to debug

Browse source
This commit is contained in:
Cristian 2020-09-01 10:16:24 -05:00
parent bf3ea42141
commit 66037535fd
1 changed files with 5 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

6
archivebox/extractors/readability.py
View file

@ -16,6 +16,7 @@ from ..util import (
) )
from ..config import ( from ..config import (
TIMEOUT, TIMEOUT,
CURL_BINARY,
SAVE_READABILITY, SAVE_READABILITY,
DEPENDENCIES, DEPENDENCIES,
READABILITY_VERSION, 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 # Readability Docs: https://github.com/mozilla/readability
status = 'succeeded' status = 'succeeded'
cmd = [] cmd = [
CURL_BINARY,
link.url
]
timer = TimedProgress(timeout, prefix=' ') timer = TimedProgress(timeout, prefix=' ')
try: try:
document = get_html(link, out_dir) document = get_html(link, out_dir)