Mirrors/ArchiveBox
2
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox synced 2024-11-10 14:44:18 +00:00
Code Issues Projects Releases Packages Wiki Activity

Merge pull request #426 from cdvv7788/readability-extractor

Browse source
This commit is contained in:
Nick Sweeting 2020-08-14 12:56:30 -04:00 committed by GitHub
commit e835afcf70
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
9 changed files with 182 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
Dockerfile
View file

@ -90,7 +90,9 @@ WORKDIR "$DATA_DIR"
ENV IN_DOCKER=True \
CHROME_SANDBOX=False \
CHROME_BINARY="chromium" \
USE_SINGLEFILE=True \
SINGLEFILE_BINARY="$NODE_DIR/node_modules/.bin/single-file" \
USE_READABILITY=True \
READABILITY_BINARY="$NODE_DIR/node_modules/.bin/readability-extractor"
# Print version for nice docker finish summary

16
archivebox/config/__init__.py
View file

@ -77,6 +77,7 @@ CONFIG_DEFAULTS: Dict[str, ConfigDefaultDict] = {
'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_READABILITY': {'type': bool, 'default': True, 'aliases': ('FETCH_READABILITY',)},
'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',)},
@ -106,7 +107,8 @@ 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_SINGLEFILE': {'type': bool, 'default': False},
'USE_READABILITY': {'type': bool, 'default': False},
'USE_GIT': {'type': bool, 'default': True},
'USE_CHROME': {'type': bool, 'default': True},
'USE_YOUTUBEDL': {'type': bool, 'default': True},
@ -115,6 +117,7 @@ CONFIG_DEFAULTS: Dict[str, ConfigDefaultDict] = {
'GIT_BINARY': {'type': str, 'default': 'git'},
'WGET_BINARY': {'type': str, 'default': 'wget'},
'SINGLEFILE_BINARY': {'type': str, 'default': 'single-file'},
'READABILITY_BINARY': {'type': str, 'default': 'readability-extractor'},
'YOUTUBEDL_BINARY': {'type': str, 'default': 'youtube-dl'},
'CHROME_BINARY': {'type': str, 'default': None},
},
@ -256,6 +259,9 @@ DERIVED_CONFIG_DEFAULTS: ConfigDefaultDict = {
'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_READABILITY': {'default': lambda c: c['USE_READABILITY'] and c['SAVE_READABILITY']},
'READABILITY_VERSION': {'default': lambda c: bin_version(c['READABILITY_BINARY']) if c['USE_READABILITY'] 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']},
@ -272,6 +278,7 @@ DERIVED_CONFIG_DEFAULTS: ConfigDefaultDict = {
'SAVE_SCREENSHOT': {'default': lambda c: c['USE_CHROME'] and c['SAVE_SCREENSHOT']},
'SAVE_DOM': {'default': lambda c: c['USE_CHROME'] and c['SAVE_DOM']},
'SAVE_SINGLEFILE': {'default': lambda c: c['USE_CHROME'] and c['USE_SINGLEFILE']},
'SAVE_READABILITY': {'default': lambda c: c['USE_READABILITY']},
'DEPENDENCIES': {'default': lambda c: get_dependency_info(c)},
'CODE_LOCATIONS': {'default': lambda c: get_code_locations(c)},
@ -689,6 +696,13 @@ def get_dependency_info(config: ConfigDict) -> ConfigValue:
'enabled': config['USE_SINGLEFILE'],
'is_valid': bool(config['SINGLEFILE_VERSION']),
},
'READABILITY_BINARY': {
'path': bin_path(config['READABILITY_BINARY']),
'version': config['READABILITY_VERSION'],
'hash': bin_hash(config['READABILITY_BINARY']),
'enabled': config['USE_READABILITY'],
'is_valid': bool(config['READABILITY_VERSION']),
},
'GIT_BINARY': {
'path': bin_path(config['GIT_BINARY']),
'version': config['GIT_VERSION'],

3
archivebox/extractors/__init__.py
View file

@ -26,6 +26,7 @@ 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 .readability import should_save_readability, save_readability
from .pdf import should_save_pdf, save_pdf
from .screenshot import should_save_screenshot, save_screenshot
from .dom import should_save_dom, save_dom
@ -42,6 +43,7 @@ def get_default_archive_methods():
('pdf', should_save_pdf, save_pdf),
('screenshot', should_save_screenshot, save_screenshot),
('dom', should_save_dom, save_dom),
('readability', should_save_readability, save_readability), #keep readability below wget and singlefile, as it depends on them
('git', should_save_git, save_git),
('media', should_save_media, save_media),
('archive_org', should_save_archive_dot_org, save_archive_dot_org),
@ -93,6 +95,7 @@ def archive_link(link: Link, overwrite: bool=False, methods: Optional[Iterable[s
stats[result.status] += 1
log_archive_method_finished(result)
else:
print(' > Skipping extractor: {}'.format(method_name))
stats['skipped'] += 1
except Exception as e:
raise Exception('Exception in archive_methods.save_{}(Link(url={}))'.format(

113
archivebox/extractors/readability.py Normal file
View file

@ -0,0 +1,113 @@
__package__ = 'archivebox.extractors'
from pathlib import Path
from tempfile import NamedTemporaryFile
from typing import Optional
import json
from ..index.schema import Link, ArchiveResult, ArchiveError
from ..system import run, atomic_write
from ..util import (
enforce_types,
download_url,
is_static_file,
)
from ..config import (
TIMEOUT,
SAVE_READABILITY,
READABILITY_BINARY,
READABILITY_VERSION,
)
from ..logging_util import TimedProgress
@enforce_types
def get_html(link: Link, path: Path) -> str:
"""
Try to find wget, singlefile and then dom files.
If none is found, download the url again.
"""
canonical = link.canonical_outputs()
abs_path = path.absolute()
sources = [canonical["singlefile_path"], canonical["wget_path"], canonical["dom_path"]]
document = None
for source in sources:
try:
with open(abs_path / source, "r") as f:
document = f.read()
break
except (FileNotFoundError, TypeError):
continue
if document is None:
return download_url(link.url)
else:
return document
@enforce_types
def should_save_readability(link: Link, out_dir: Optional[str]=None) -> bool:
out_dir = out_dir or link.link_dir
if is_static_file(link.url):
return False
output = Path(out_dir or link.link_dir) / 'readability'
return SAVE_READABILITY and (not output.exists())
@enforce_types
def save_readability(link: Link, out_dir: Optional[str]=None, timeout: int=TIMEOUT) -> ArchiveResult:
"""download reader friendly version using @mozilla/readability"""
out_dir = Path(out_dir or link.link_dir)
output_folder = out_dir.absolute() / "readability"
output = str(output_folder)
document = get_html(link, out_dir)
temp_doc = NamedTemporaryFile(delete=False)
temp_doc.write(document.encode("utf-8"))
temp_doc.close()
# Readability Docs: https://github.com/mozilla/readability
cmd = [
READABILITY_BINARY,
temp_doc.name
]
status = 'succeeded'
timer = TimedProgress(timeout, prefix=' ')
try:
result = run(cmd, cwd=out_dir, timeout=timeout)
result_json = json.loads(result.stdout)
output_folder.mkdir(exist_ok=True)
atomic_write(str(output_folder / "content.html"), result_json.pop("content"))
atomic_write(str(output_folder / "content.txt"), result_json.pop("textContent"))
atomic_write(str(output_folder / "article.json"), result_json)
# 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 readability response code: {}.'.format(result.returncode),
*output_tail,
)
# Check for common failure cases
if (result.returncode > 0):
raise ArchiveError('Readability was not able to archive the page', hints)
except Exception as err:
status = 'failed'
output = err
finally:
timer.end()
return ArchiveResult(
cmd=cmd,
pwd=str(out_dir),
cmd_version=READABILITY_VERSION,
output=output,
status=status,
**timer.stats,
)

2
archivebox/index/schema.py
View file

@ -407,6 +407,7 @@ class Link:
'wget_path': wget_output_path(self),
'warc_path': 'warc',
'singlefile_path': 'singlefile.html',
'readability_path': 'readability/content.html',
'pdf_path': 'output.pdf',
'screenshot_path': 'screenshot.png',
'dom_path': 'output.html',
@ -427,6 +428,7 @@ class Link:
'screenshot_path': static_path,
'dom_path': static_path,
'singlefile_path': static_path,
'readability_path': static_path,
})
return canonical

12
archivebox/themes/legacy/link_details.html
View file

@ -348,6 +348,18 @@
</div>
</div>
</div>
<div class="col-lg-2">
<div class="card">
<iframe class="card-img-top" src="$readability_path" sandbox="allow-same-origin allow-scripts allow-forms" scrolling="no"></iframe>
<div class="card-body">
<a href="$readability_path" style="float:right" title="Open in new tab..." target="_blank" rel="noopener">
<img src="../../static/external.png" class="external"/>
</a>
<a href="$readability_path" target="preview"><h4 class="card-title">Readability</h4></a>
<p class="card-text">archive/readability/...</p>
</div>
</div>
</div>
<div class="col-lg-2">
<div class="card">
<iframe class="card-img-top pdf-frame" src="$pdf_path" scrolling="no"></iframe>

1
tests/fixtures.py
View file

@ -15,6 +15,7 @@ def disable_extractors_dict():
env.update({
"USE_WGET": "false",
"USE_SINGLEFILE": "false",
"USE_READABILITY": "false",
"SAVE_PDF": "false",
"SAVE_SCREENSHOT": "false",
"SAVE_DOM": "false",

32
tests/test_extractors.py
View file

@ -21,3 +21,35 @@ def test_singlefile_works(tmp_path, process, disable_extractors_dict):
archived_item_path = list(tmp_path.glob('archive/**/*'))[0]
output_file = archived_item_path / "singlefile.html"
assert output_file.exists()
def test_readability_works(tmp_path, process, disable_extractors_dict):
disable_extractors_dict.update({"USE_READABILITY": "true"})
add_process = subprocess.run(['archivebox', 'add', 'http://127.0.0.1:8080/static/example.com.html'],
capture_output=True, env=disable_extractors_dict)
archived_item_path = list(tmp_path.glob("archive/**/*"))[0]
output_file = archived_item_path / "readability" / "content.html"
assert output_file.exists()
def test_readability_works_with_wget(tmp_path, process, disable_extractors_dict):
disable_extractors_dict.update({"USE_READABILITY": "true", "USE_WGET": "true"})
add_process = subprocess.run(['archivebox', 'add', 'http://127.0.0.1:8080/static/example.com.html'],
capture_output=True, env=disable_extractors_dict)
archived_item_path = list(tmp_path.glob("archive/**/*"))[0]
output_file = archived_item_path / "readability" / "content.html"
assert output_file.exists()
def test_readability_works_with_singlefile(tmp_path, process, disable_extractors_dict):
disable_extractors_dict.update({"USE_READABILITY": "true", "USE_SINGLEFILE": "true"})
add_process = subprocess.run(['archivebox', 'add', 'http://127.0.0.1:8080/static/example.com.html'],
capture_output=True, env=disable_extractors_dict)
archived_item_path = list(tmp_path.glob("archive/**/*"))[0]
output_file = archived_item_path / "readability" / "content.html"
assert output_file.exists()
def test_readability_works_with_dom(tmp_path, process, disable_extractors_dict):
disable_extractors_dict.update({"USE_READABILITY": "true", "SAVE_DOM": "true"})
add_process = subprocess.run(['archivebox', 'add', 'http://127.0.0.1:8080/static/example.com.html'],
capture_output=True, env=disable_extractors_dict)
archived_item_path = list(tmp_path.glob("archive/**/*"))[0]
output_file = archived_item_path / "readability" / "content.html"
assert output_file.exists()

2
tests/test_init.py
View file

@ -19,6 +19,7 @@ def test_update(tmp_path, process):
assert "Updating existing ArchiveBox collection in this folder" in update_process.stdout.decode("utf-8")
def test_add_link(tmp_path, process, disable_extractors_dict):
disable_extractors_dict.update({"USE_WGET": "true"})
os.chdir(tmp_path)
add_process = subprocess.run(['archivebox', 'add', 'http://127.0.0.1:8080/static/example.com.html'],
capture_output=True, env=disable_extractors_dict)
@ -35,6 +36,7 @@ def test_add_link(tmp_path, process, disable_extractors_dict):
assert "Example Domain" in output_html
def test_add_link_support_stdin(tmp_path, process, disable_extractors_dict):
disable_extractors_dict.update({"USE_WGET": "true"})
os.chdir(tmp_path)
stdin_process = subprocess.Popen(["archivebox", "add"], stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.STDOUT,
env=disable_extractors_dict)