mirrors/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2025-05-15 23:54:27 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor: headers uses snapshot instead of link

Browse source
This commit is contained in:
Cristian 2020-12-29 14:04:22 -05:00
parent 29ec48a35f
commit b9489c971c
1 changed files with 9 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

16
archivebox/extractors/headers.py
View file

@ -4,6 +4,8 @@ from pathlib import Path
from typing import Optional from typing import Optional
from django.db.models import Model
from ..index.schema import Link, ArchiveResult, ArchiveOutput from ..index.schema import Link, ArchiveResult, ArchiveOutput
from ..system import atomic_write from ..system import atomic_write
from ..util import ( from ..util import (
@ -22,18 +24,18 @@ from ..config import (
from ..logging_util import TimedProgress from ..logging_util import TimedProgress
@enforce_types @enforce_types
def should_save_headers(link: Link, out_dir: Optional[str]=None) -> bool: def should_save_headers(snapshot: Model, out_dir: Optional[str]=None) -> bool:
out_dir = out_dir or link.link_dir out_dir = out_dir or snapshot.snapshot_dir
output = Path(out_dir or link.link_dir) / 'headers.json' output = Path(out_dir or snapshot.snapshot_dir) / 'headers.json'
return not output.exists() and SAVE_HEADERS return not output.exists() and SAVE_HEADERS
@enforce_types @enforce_types
def save_headers(link: Link, out_dir: Optional[str]=None, timeout: int=TIMEOUT) -> ArchiveResult: def save_headers(snapshot: Model, out_dir: Optional[str]=None, timeout: int=TIMEOUT) -> ArchiveResult:
"""Download site headers""" """Download site headers"""
out_dir = Path(out_dir or link.link_dir) out_dir = Path(out_dir or snapshot.snapshot_dir)
output_folder = out_dir.absolute() output_folder = out_dir.absolute()
output: ArchiveOutput = 'headers.json' output: ArchiveOutput = 'headers.json'
@ -47,10 +49,10 @@ def save_headers(link: Link, out_dir: Optional[str]=None, timeout: int=TIMEOUT)
'--max-time', str(timeout), '--max-time', str(timeout),
*(['--user-agent', '{}'.format(CURL_USER_AGENT)] if CURL_USER_AGENT else []), *(['--user-agent', '{}'.format(CURL_USER_AGENT)] if CURL_USER_AGENT else []),
*([] if CHECK_SSL_VALIDITY else ['--insecure']), *([] if CHECK_SSL_VALIDITY else ['--insecure']),
link.url, snapshot.url,
] ]
try: try:
json_headers = get_headers(link.url, timeout=timeout) json_headers = get_headers(snapshot.url, timeout=timeout)
output_folder.mkdir(exist_ok=True) output_folder.mkdir(exist_ok=True)
atomic_write(str(output_folder / "headers.json"), json_headers) atomic_write(str(output_folder / "headers.json"), json_headers)
except (Exception, OSError) as err: except (Exception, OSError) as err: