Mirrors/ArchiveBox
2
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox synced 2024-11-23 04:33:11 +00:00
Code Issues Projects Releases Packages Wiki Activity

use the db exclusively for icons instead of hammering filesystem

Browse source
This commit is contained in:
Nick Sweeting 2021-02-01 02:18:13 -05:00
parent 923f517a8f
commit 534ead2440
1 changed files with 21 additions and 12 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

33
archivebox/index/html.py
View file

@ -150,24 +150,33 @@ def snapshot_icons(snapshot) -> str:
for extractor, _ in EXTRACTORS: for extractor, _ in EXTRACTORS:
if extractor not in exclude: if extractor not in exclude:
outpath = extractor_outputs[extractor] and extractor_outputs[extractor].output existing = extractor_outputs[extractor] and extractor_outputs[extractor].status == 'succeeded' and extractor_outputs[extractor].output
if outpath: # Check filesystsem to see if anything is actually present (too slow, needs optimization/caching)
outpath = (Path(path) / outpath) # if existing:
if outpath.is_file(): # existing = (Path(path) / existing)
exists = True # if existing.is_file():
elif outpath.is_dir(): # existing = True
exists = any(outpath.glob('*.*')) # elif existing.is_dir():
output += format_html(output_template, path, canon[f"{extractor}_path"], str(bool(outpath)), # existing = any(existing.glob('*.*'))
output += format_html(output_template, path, canon[f"{extractor}_path"], str(bool(existing)),
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
exists = list((Path(path) / canon["warc_path"]).glob("*.warc.gz"))
output += format_html(output_template, exists[0] if exists else '#', canon["warc_path"], str(bool(exists)), "warc", icons.get("warc", "?")) # get from db (faster but less thurthful)
exists = extractor_outputs[extractor] and extractor_outputs[extractor].status == 'succeeded' and extractor_outputs[extractor].output
# get from filesystem (slower but more accurate)
# exists = list((Path(path) / canon["warc_path"]).glob("*.warc.gz"))
output += format_html(output_template, 'warc/', canon["warc_path"], str(bool(exists)), "warc", icons.get("warc", "?"))
if extractor == "archive_org": if extractor == "archive_org":
# The check for archive_org is different, so it has to be handled separately # The check for archive_org is different, so it has to be handled separately
target_path = Path(path) / "archive.org.txt"
exists = target_path.exists() # get from db (faster)
exists = extractor_outputs[extractor] and extractor_outputs[extractor].status == 'succeeded' and extractor_outputs[extractor].output
# get from filesystem (slower)
# target_path = Path(path) / "archive.org.txt"
# exists = target_path.exists()
output += '<a href="{}" class="exists-{}" title="{}">{}</a> '.format(canon["archive_org_path"], str(exists), output += '<a href="{}" class="exists-{}" title="{}">{}</a> '.format(canon["archive_org_path"], str(exists),
"archive_org", icons.get("archive_org", "?")) "archive_org", icons.get("archive_org", "?"))