mirrors/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2024-09-19 23:49:07 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

feat: Add initial support for singlefile extractor

Browse source
This commit is contained in:
Cristian 2020-07-30 13:23:10 -05:00
parent e0dba0494f
commit 853685668c
3 changed files with 96 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

13
archivebox/config/__init__.py
View file

@ -74,6 +74,7 @@ CONFIG_DEFAULTS: Dict[str, ConfigDefaultDict] = {
'SAVE_FAVICON': {'type': bool, 'default': True, 'aliases': ('FETCH_FAVICON',)},
'SAVE_WGET': {'type': bool, 'default': True, 'aliases': ('FETCH_WGET',)},
'SAVE_WGET_REQUISITES': {'type': bool, 'default': True, 'aliases': ('FETCH_WGET_REQUISITES',)},
'SAVE_SINGLEFILE': {'type': bool, 'default': True, 'aliases': ('FETCH_SINGLEFILE',)},
'SAVE_PDF': {'type': bool, 'default': True, 'aliases': ('FETCH_PDF',)},
'SAVE_SCREENSHOT': {'type': bool, 'default': True, 'aliases': ('FETCH_SCREENSHOT',)},
'SAVE_DOM': {'type': bool, 'default': True, 'aliases': ('FETCH_DOM',)},
@ -104,6 +105,7 @@ CONFIG_DEFAULTS: Dict[str, ConfigDefaultDict] = {
'DEPENDENCY_CONFIG': {
'USE_CURL': {'type': bool, 'default': True},
'USE_WGET': {'type': bool, 'default': True},
'USE_SINGLEFILE': {'type': bool, 'default': True},
'USE_GIT': {'type': bool, 'default': True},
'USE_CHROME': {'type': bool, 'default': True},
'USE_YOUTUBEDL': {'type': bool, 'default': True},
@ -111,6 +113,7 @@ CONFIG_DEFAULTS: Dict[str, ConfigDefaultDict] = {
'CURL_BINARY': {'type': str, 'default': 'curl'},
'GIT_BINARY': {'type': str, 'default': 'git'},
'WGET_BINARY': {'type': str, 'default': 'wget'},
'SINGLEFILE_BINARY': {'type': str, 'default': 'single-file'},
'YOUTUBEDL_BINARY': {'type': str, 'default': 'youtube-dl'},
'CHROME_BINARY': {'type': str, 'default': None},
},
@ -249,6 +252,9 @@ DERIVED_CONFIG_DEFAULTS: ConfigDefaultDict = {
'SAVE_WGET': {'default': lambda c: c['USE_WGET'] and c['SAVE_WGET']},
'SAVE_WARC': {'default': lambda c: c['USE_WGET'] and c['SAVE_WARC']},
'USE_SINGLEFILE': {'default': lambda c: c['USE_SINGLEFILE'] and (c['SAVE_SINGLEFILE'])},
'SINGLEFILE_VERSION': {'default': lambda c: bin_version(c['SINGLEFILE_BINARY']) if c['USE_SINGLEFILE'] else None},
'USE_GIT': {'default': lambda c: c['USE_GIT'] and c['SAVE_GIT']},
'GIT_VERSION': {'default': lambda c: bin_version(c['GIT_BINARY']) if c['USE_GIT'] else None},
'SAVE_GIT': {'default': lambda c: c['USE_GIT'] and c['SAVE_GIT']},
@ -674,6 +680,13 @@ def get_dependency_info(config: ConfigDict) -> ConfigValue:
'enabled': config['USE_WGET'],
'is_valid': bool(config['WGET_VERSION']),
},
'SINGLEFILE_BINARY': {
'path': bin_path(config['SINGLEFILE_BINARY']),
'version': config['SINGLEFILE_VERSION'],
'hash': bin_hash(config['SINGLEFILE_BINARY']),
'enabled': config['USE_SINGLEFILE'],
'is_valid': bool(config['SINGLEFILE_VERSION']),
},
'GIT_BINARY': {
'path': bin_path(config['GIT_BINARY']),
'version': config['GIT_VERSION'],

2
archivebox/extractors/__init__.py
View file

@ -25,6 +25,7 @@ from ..logging_util import (
from .title import should_save_title, save_title
from .favicon import should_save_favicon, save_favicon
from .wget import should_save_wget, save_wget
from .singlefile import should_save_singlefile, save_singlefile
from .pdf import should_save_pdf, save_pdf
from .screenshot import should_save_screenshot, save_screenshot
from .dom import should_save_dom, save_dom
@ -37,6 +38,7 @@ def get_default_archive_methods():
('title', should_save_title, save_title),
('favicon', should_save_favicon, save_favicon),
('wget', should_save_wget, save_wget),
('singlefile', should_save_singlefile, save_singlefile),
('pdf', should_save_pdf, save_pdf),
('screenshot', should_save_screenshot, save_screenshot),
('dom', should_save_dom, save_dom),

81
archivebox/extractors/singlefile.py Normal file
View file

@ -0,0 +1,81 @@
__package__ = 'archivebox.extractors'
import os
from pathlib import Path
from typing import Optional
from ..index.schema import Link, ArchiveResult, ArchiveError
from ..system import run, chmod_file
from ..util import (
enforce_types,
)
from ..config import (
TIMEOUT,
SAVE_SINGLEFILE,
SINGLEFILE_BINARY,
SINGLEFILE_VERSION,
CHROME_BINARY,
)
from ..logging_util import TimedProgress
@enforce_types
def should_save_singlefile(link: Link, out_dir: Optional[str]=None) -> bool:
out_dir = out_dir or link.link_dir
if not os.path.exists(out_dir):
return False
return SAVE_SINGLEFILE
@enforce_types
def save_singlefile(link: Link, out_dir: Optional[str]=None, timeout: int=TIMEOUT) -> ArchiveResult:
"""download full site using single-file"""
out_dir = out_dir or link.link_dir
output = str(Path(out_dir).absolute() / "single-file.html")
# WGET CLI Docs: https://www.gnu.org/software/wget/manual/wget.html
cmd = [
SINGLEFILE_BINARY,
'--browser-executable-path={}'.format(CHROME_BINARY),
link.url,
output
]
status = 'succeeded'
timer = TimedProgress(timeout, prefix=' ')
try:
result = run(cmd, cwd=out_dir, timeout=timeout)
# parse out number of files downloaded from last line of stderr:
# "Downloaded: 76 files, 4.0M in 1.6s (2.52 MB/s)"
output_tail = [
line.strip()
for line in (result.stdout + result.stderr).decode().rsplit('\n', 3)[-3:]
if line.strip()
]
hints = (
'Got single-file response code: {}.'.format(result.returncode),
*output_tail,
)
# Check for common failure cases
if (result.returncode > 0):
raise ArchiveError('SingleFile was not able to archive the page', hints)
chmod_file(output)
except Exception as err:
status = 'failed'
output = err
finally:
timer.end()
return ArchiveResult(
cmd=cmd,
pwd=out_dir,
cmd_version=SINGLEFILE_VERSION,
output=output,
status=status,
**timer.stats,
)