1
0
Fork 0
mirror of synced 2024-06-24 00:50:23 +12:00

fix: Partially restore server command functionality (html still needs some refactoring)

This commit is contained in:
Cristian 2021-01-04 09:14:02 -05:00
parent e95f14d1d0
commit 15d88be229
3 changed files with 66 additions and 29 deletions

View file

@ -3,6 +3,7 @@ __package__ = 'archivebox.core'
import uuid
from pathlib import Path
from typing import Dict, Optional, List
from datetime import datetime
from django.db import models, transaction
from django.utils.functional import cached_property
@ -12,6 +13,7 @@ from django.db.models import Case, When, Value, IntegerField
from ..util import parse_date
from ..index.schema import Link
from ..config import CONFIG
from ..system import get_dir_size
#EXTRACTORS = [(extractor[0], extractor[0]) for extractor in get_default_archive_methods()]
EXTRACTORS = [("title", "title"), ("wget", "wget")]
@ -133,8 +135,36 @@ class Snapshot(models.Model):
return parse_date(self.timestamp)
@cached_property
def is_archived(self):
return self.as_link().is_archived
def is_archived(self) -> bool:
from ..config import ARCHIVE_DIR
from ..util import domain
output_paths = (
domain(self.url),
'output.pdf',
'screenshot.png',
'output.html',
'media',
'singlefile.html'
)
return any(
(Path(ARCHIVE_DIR) / self.timestamp / path).exists()
for path in output_paths
)
@cached_property
def archive_dates(self) -> List[datetime]:
return [
result.start_ts
for result in self.archiveresult_set.all()
]
@cached_property
def oldest_archive_date(self) -> Optional[datetime]:
oldest = self.archiveresult_set.all().order_by("-start_ts")[:1]
if len(oldest) > 0:
return oldest[0].start_ts
@cached_property
def num_outputs(self):
@ -145,8 +175,9 @@ class Snapshot(models.Model):
return self.as_link().url_hash
@cached_property
def base_url(self):
return self.as_link().base_url
def base_url(self) -> str:
from ..util import base_url
return base_url(self.url)
@cached_property
def snapshot_dir(self):
@ -155,11 +186,15 @@ class Snapshot(models.Model):
@cached_property
def archive_path(self):
return self.as_link().archive_path
from ..config import ARCHIVE_DIR_NAME
return '{}/{}'.format(ARCHIVE_DIR_NAME, self.timestamp)
@cached_property
def archive_size(self):
return self.as_link().archive_size
def archive_size(self) -> float:
try:
return get_dir_size(self.archive_path)[0]
except Exception:
return 0
@cached_property
def history(self):
@ -191,7 +226,10 @@ class Snapshot(models.Model):
# TODO: Define what details are, and return them accordingly
return {"history": {}}
@property
def extension(self) -> str:
from ..util import extension
return extension(self.url)
def canonical_outputs(self) -> Dict[str, Optional[str]]:
"""predict the expected output paths that should be present after archiving"""

View file

@ -61,7 +61,7 @@ class LinkDetails(View):
by_ts = {page.timestamp: page for page in all_pages}
try:
# print('SERVING STATICFILE', by_ts[slug].link_dir, request.path, path)
response = static.serve(request, archivefile, document_root=by_ts[slug].link_dir, show_indexes=True)
response = static.serve(request, archivefile, document_root=by_ts[slug].snapshot_dir, show_indexes=True)
response["Link"] = f'<{by_ts[slug].url}>; rel="canonical"'
return response
except KeyError:

View file

@ -61,10 +61,10 @@ def main_index_template(snapshots: List[Model], template: str=MAIN_INDEX_TEMPLAT
return render_django_template(template, {
'version': VERSION,
'git_sha': GIT_SHA,
'num_links': str(len(snapshots)),
'num_snapshots': str(len(snapshots)),
'date_updated': datetime.now().strftime('%Y-%m-%d'),
'time_updated': datetime.now().strftime('%Y-%m-%d %H:%M'),
'links': [snapshot.as_json() for snapshot in snapshots],
'snapshots': snapshots,
'FOOTER_INFO': FOOTER_INFO,
})
@ -80,30 +80,30 @@ def write_html_snapshot_details(snapshot: Model, out_dir: Optional[str]=None) ->
@enforce_types
def link_details_template(link: Link) -> str:
def link_details_template(snapshot: Model) -> str:
from ..extractors.wget import wget_output_path
link_info = link._asdict(extended=True)
snapshot._asdict()
return render_django_template(LINK_DETAILS_TEMPLATE, {
**link_info,
**link_info['canonical'],
**snapshot._asdict(),
**snapshot.canonical_outputs(),
'title': htmlencode(
link.title
or (link.base_url if link.is_archived else TITLE_LOADING_MSG)
snapshot.title
or (snapshot.base_url if snapshot.is_archived else TITLE_LOADING_MSG)
),
'url_str': htmlencode(urldecode(link.base_url)),
'url_str': htmlencode(urldecode(snapshot.base_url)),
'archive_url': urlencode(
wget_output_path(link)
or (link.domain if link.is_archived else '')
wget_output_path(snapshot)
or (snapshot.domain if snapshot.is_archived else '')
) or 'about:blank',
'extension': link.extension or 'html',
'tags': link.tags or 'untagged',
'size': printable_filesize(link.archive_size) if link.archive_size else 'pending',
'status': 'archived' if link.is_archived else 'not yet archived',
'status_color': 'success' if link.is_archived else 'danger',
'oldest_archive_date': ts_to_date(link.oldest_archive_date),
'extension': snapshot.extension or 'html',
'tags': snapshot.tags.all() or 'untagged', #TODO: Return a proper comma separated list. Leaving it like this for now to revisit when fixing tags
'size': printable_filesize(snapshot.archive_size) if snapshot.archive_size else 'pending',
'status': 'archived' if snapshot.is_archived else 'not yet archived',
'status_color': 'success' if snapshot.is_archived else 'danger',
'oldest_archive_date': ts_to_date(snapshot.oldest_archive_date),
})
@enforce_types
@ -118,9 +118,8 @@ def snapshot_icons(snapshot) -> str:
from core.models import EXTRACTORS
archive_results = snapshot.archiveresult_set.filter(status="succeeded")
link = snapshot.as_link()
path = link.archive_path
canon = link.canonical_outputs()
path = snapshot.archive_path
canon = snapshot.canonical_outputs()
output = ""
output_template = '<a href="/{}/{}" class="exists-{}" title="{}">{} </a>'
icons = {