Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Don't assume provenance summary is present. #3419

Merged
merged 1 commit into from
Oct 30, 2023
Merged

Don't assume provenance summary is present. #3419

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
38 changes: 22 additions & 16 deletions perma_web/perma/celery_tasks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -835,15 +835,9 @@ def save_scoop_capture(link, capture_job, data):
description = data['scoop_capture_summary']['pageInfo'].get('description')
if description:
link.submitted_description=description[:300]
software = data['scoop_capture_summary']['provenanceInfo']['software'].lower()
version = data['scoop_capture_summary']['provenanceInfo']['version'].lower()
link.captured_by_software = f"{software}: {version}"
link.captured_by_browser = data['scoop_capture_summary']['provenanceInfo']['userAgent']
link.save(update_fields=[
'submitted_title',
'submitted_description',
'captured_by_software',
'captured_by_browser'
'submitted_description'
])

# Make this link private by policy, if the captured domain is on the list.
Expand Down Expand Up @@ -884,16 +878,28 @@ def save_scoop_capture(link, capture_job, data):
#
# OTHER ATTACHMENTS
#
provenance_filename = data['scoop_capture_summary']['attachments'].get("provenanceSummary")
if provenance_filename:
Capture(
link=link,
role='provenance_summary',
status='success',
record_type='response',
url=f"file:///{provenance_filename}",
content_type='text/html; charset=utf-8',
).save()

provenance_filename = data['scoop_capture_summary']['attachments']["provenanceSummary"]
Capture(
link=link,
role='provenance_summary',
status='success',
record_type='response',
url=f"file:///{provenance_filename}",
content_type='text/html; charset=utf-8',
).save()
software = data['scoop_capture_summary']['provenanceInfo']['software'].lower()
version = data['scoop_capture_summary']['provenanceInfo']['version'].lower()
link.captured_by_software = f"{software}: {version}"
link.captured_by_browser = data['scoop_capture_summary']['provenanceInfo']['userAgent']
link.save(update_fields=[
'captured_by_software',
'captured_by_browser'
])
else:
link.tags.add('scoop-missing-provenance')
logger.warning(f"{capture_job.link_id}: Scoop warc does not contain provenance summary ({data['id_capture']}).")

#
# WARC
Expand Down
Loading