mirrors/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2025-05-14 07:04:27 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions

check for output existance when rendering files icons

Browse source
This commit is contained in:
Nick Sweeting 2021-01-30 22:04:14 -05:00
parent 15e87353bd
commit 54c5331693
1 changed files with 10 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

20
archivebox/index/html.py
View file

@ -140,22 +140,22 @@ def snapshot_icons(snapshot) -> str:
exclude = ["favicon", "title", "headers", "archive_org"] exclude = ["favicon", "title", "headers", "archive_org"]
# Missing specific entry for WARC # Missing specific entry for WARC
extractor_items = defaultdict(lambda: None) extractor_outputs = defaultdict(lambda: None)
for extractor, _ in EXTRACTORS: for extractor, _ in EXTRACTORS:
for result in archive_results: for result in archive_results:
if result.extractor == extractor: if result.extractor == extractor and result:
extractor_items[extractor] = result extractor_outputs[extractor] = result
for extractor, _ in EXTRACTORS: for extractor, _ in EXTRACTORS:
if extractor not in exclude: if extractor not in exclude:
exists = False outpath = extractor_outputs[extractor] and extractor_outputs[extractor].output
if extractor_items[extractor] is not None: if outpath:
outpath = (Path(path) / canon[f"{extractor}_path"]) outpath = (Path(path) / outpath)
if outpath.is_dir(): if outpath.is_file():
exists = True
elif outpath.is_dir():
exists = any(outpath.glob('*.*')) exists = any(outpath.glob('*.*'))
elif outpath.is_file(): output += format_html(output_template, path, canon[f"{extractor}_path"], str(bool(outpath)),
exists = outpath.stat().st_size > 100
output += format_html(output_template, path, canon[f"{extractor}_path"], str(exists),
extractor, icons.get(extractor, "?")) extractor, icons.get(extractor, "?"))
if extractor == "wget": if extractor == "wget":
# warc isn't technically it's own extractor, so we have to add it after wget # warc isn't technically it's own extractor, so we have to add it after wget