fix docs build for vendored pkgs
Some checks are pending
CodeQL / Analyze (python) (push) Waiting to run
Build Debian package / build (push) Waiting to run
Build Docker image / buildx (push) Waiting to run
Deploy static content to Pages / deploy (push) Waiting to run
Build Homebrew package / build (push) Waiting to run
Build GitHub Pages website / build (push) Waiting to run
Build GitHub Pages website / deploy (push) Blocked by required conditions
Run linters / lint (push) Waiting to run
Build Pip package / build (push) Waiting to run
Run tests / python_tests (ubuntu-22.04, 3.11) (push) Waiting to run
Run tests / docker_tests (push) Waiting to run

This commit is contained in:
Nick Sweeting 2024-11-12 23:53:34 -08:00
parent f0a7198861
commit ec100bfe29
No known key found for this signature in database
15 changed files with 78 additions and 74 deletions

View file

@ -1,18 +1,19 @@
__package__ = 'archivebox.extractors'
__package__ = 'abx_plugin_archivedotorg'
from pathlib import Path
from typing import Optional, List, Dict, Tuple
from collections import defaultdict
from ..index.schema import Link, ArchiveResult, ArchiveOutput, ArchiveError
from archivebox.logging_util import TimedProgress
from archivebox.index.schema import Link, ArchiveResult, ArchiveOutput, ArchiveError
from archivebox.misc.system import run, chmod_file
from archivebox.misc.util import enforce_types, is_static_file, dedupe
from archivebox.plugins_extractor.archivedotorg.config import ARCHIVEDOTORG_CONFIG
from archivebox.plugins_extractor.curl.config import CURL_CONFIG
from archivebox.plugins_extractor.curl.binaries import CURL_BINARY
from ..logging_util import TimedProgress
from abx_plugin_curl.config import CURL_CONFIG
from abx_plugin_curl.binaries import CURL_BINARY
from .config import ARCHIVEDOTORG_CONFIG
def get_output_path():

View file

@ -1,18 +1,18 @@
__package__ = 'archivebox.extractors'
__package__ = 'abx_plugin_chrome'
from pathlib import Path
from typing import Optional
from ..index.schema import Link, ArchiveResult, ArchiveOutput, ArchiveError
from archivebox.index.schema import Link, ArchiveResult, ArchiveOutput, ArchiveError
from archivebox.misc.system import run, chmod_file, atomic_write
from archivebox.misc.util import (
enforce_types,
is_static_file,
)
from ..logging_util import TimedProgress
from archivebox.logging_util import TimedProgress
from plugins_extractor.chrome.config import CHROME_CONFIG
from plugins_extractor.chrome.binaries import CHROME_BINARY
from .config import CHROME_CONFIG
from .binaries import CHROME_BINARY
def get_output_path():

View file

@ -1,4 +1,4 @@
__package__ = 'archivebox.extractors'
__package__ = 'abx_plugin_chrome'
from pathlib import Path
from typing import Optional
@ -8,11 +8,11 @@ from archivebox.misc.util import (
enforce_types,
is_static_file,
)
from ..index.schema import Link, ArchiveResult, ArchiveOutput, ArchiveError
from ..logging_util import TimedProgress
from archivebox.index.schema import Link, ArchiveResult, ArchiveOutput, ArchiveError
from archivebox.logging_util import TimedProgress
from plugins_extractor.chrome.config import CHROME_CONFIG
from plugins_extractor.chrome.binaries import CHROME_BINARY
from .config import CHROME_CONFIG
from .binaries import CHROME_BINARY
def get_output_path():

View file

@ -1,15 +1,15 @@
__package__ = 'archivebox.extractors'
__package__ = 'abx_plugin_chrome'
from pathlib import Path
from typing import Optional
from archivebox.misc.system import run, chmod_file
from archivebox.misc.util import enforce_types, is_static_file
from ..index.schema import Link, ArchiveResult, ArchiveOutput, ArchiveError
from ..logging_util import TimedProgress
from archivebox.index.schema import Link, ArchiveResult, ArchiveOutput, ArchiveError
from archivebox.logging_util import TimedProgress
from plugins_extractor.chrome.config import CHROME_CONFIG
from plugins_extractor.chrome.binaries import CHROME_BINARY
from .config import CHROME_CONFIG
from .binaries import CHROME_BINARY
def get_output_path():

View file

@ -1,19 +1,21 @@
__package__ = 'archivebox.extractors'
__package__ = 'abx_plugin_curl'
from pathlib import Path
from typing import Optional
from archivebox.logging_util import TimedProgress
from archivebox.index.schema import Link, ArchiveResult, ArchiveOutput
from archivebox.misc.system import atomic_write
from archivebox.misc.util import (
enforce_types,
get_headers,
dedupe,
)
from archivebox.plugins_extractor.curl.config import CURL_CONFIG
from archivebox.plugins_extractor.curl.binaries import CURL_BINARY
from ..index.schema import Link, ArchiveResult, ArchiveOutput
from ..logging_util import TimedProgress
from .binaries import CURL_BINARY
from .config import CURL_CONFIG
def get_output_path():
return 'headers.json'

View file

@ -1,14 +1,16 @@
__package__ = 'archivebox.extractors'
__package__ = 'abx_plugin_favicon'
from pathlib import Path
from archivebox.misc.system import chmod_file, run
from archivebox.misc.util import enforce_types, domain, dedupe
from archivebox.plugins_extractor.favicon.config import FAVICON_CONFIG
from archivebox.plugins_extractor.curl.config import CURL_CONFIG
from archivebox.plugins_extractor.curl.binaries import CURL_BINARY
from ..index.schema import Link, ArchiveResult, ArchiveOutput
from ..logging_util import TimedProgress
from archivebox.index.schema import Link, ArchiveResult, ArchiveOutput
from archivebox.logging_util import TimedProgress
from abx_plugin_curl.config import CURL_CONFIG
from abx_plugin_curl.binaries import CURL_BINARY
from .config import FAVICON_CONFIG
@enforce_types

View file

@ -1,4 +1,4 @@
__package__ = 'archivebox.extractors'
__package__ = 'abx_plugin_git'
from pathlib import Path
@ -13,8 +13,8 @@ from archivebox.misc.util import (
without_query,
without_fragment,
)
from ..logging_util import TimedProgress
from ..index.schema import Link, ArchiveResult, ArchiveOutput, ArchiveError
from archivebox.logging_util import TimedProgress
from archivebox.index.schema import Link, ArchiveResult, ArchiveOutput, ArchiveError
from abx_plugin_git.config import GIT_CONFIG
from abx_plugin_git.binaries import GIT_BINARY

View file

@ -1,4 +1,4 @@
__package__ = 'archivebox.extractors'
__package__ = 'abx_plugin_htmltotext'
from html.parser import HTMLParser
import io
@ -9,13 +9,12 @@ from archivebox.config import VERSION
from archivebox.config.common import ARCHIVING_CONFIG
from archivebox.misc.system import atomic_write
from archivebox.misc.util import enforce_types, is_static_file
from archivebox.logging_util import TimedProgress
from archivebox.index.schema import Link, ArchiveResult, ArchiveError
from archivebox.plugins_extractor.htmltotext.config import HTMLTOTEXT_CONFIG
from ..logging_util import TimedProgress
from ..index.schema import Link, ArchiveResult, ArchiveError
from .title import get_html
from abx_plugin_title.extractor import get_html
from .config import HTMLTOTEXT_CONFIG
def get_output_path():
return "htmltotext.txt"

View file

@ -1,4 +1,4 @@
__package__ = 'archivebox.extractors'
__package__ = 'abx_plugin_mercury'
from pathlib import Path
@ -6,16 +6,16 @@ from subprocess import CompletedProcess
from typing import Optional, List
import json
from ..index.schema import Link, ArchiveResult, ArchiveError
from archivebox.logging_util import TimedProgress
from archivebox.index.schema import Link, ArchiveResult, ArchiveError
from archivebox.misc.system import run, atomic_write
from archivebox.misc.util import (
enforce_types,
is_static_file,
)
from archivebox.plugins_extractor.mercury.config import MERCURY_CONFIG
from archivebox.plugins_extractor.mercury.binaries import MERCURY_BINARY
from .config import MERCURY_CONFIG
from .binaries import MERCURY_BINARY
from ..logging_util import TimedProgress
def get_output_path():

View file

@ -1,4 +1,4 @@
__package__ = 'archivebox.extractors'
__package__ = 'abx_plugin_readability'
from pathlib import Path
from tempfile import NamedTemporaryFile
@ -8,12 +8,12 @@ import json
from archivebox.misc.system import run, atomic_write
from archivebox.misc.util import enforce_types, is_static_file
from ..index.schema import Link, ArchiveResult, ArchiveError
from ..logging_util import TimedProgress
from .title import get_html
from archivebox.index.schema import Link, ArchiveResult, ArchiveError
from archivebox.logging_util import TimedProgress
from abx_plugin_title.extractor import get_html
from plugins_extractor.readability.config import READABILITY_CONFIG
from plugins_extractor.readability.binaries import READABILITY_BINARY
from .config import READABILITY_CONFIG
from .binaries import READABILITY_BINARY
def get_output_path():

View file

@ -1,19 +1,19 @@
__package__ = 'archivebox.extractors'
__package__ = 'abx_plugin_singlefile'
from pathlib import Path
from typing import Optional
import json
from ..index.schema import Link, ArchiveResult, ArchiveError
from archivebox.index.schema import Link, ArchiveResult, ArchiveError
from archivebox.misc.system import run, chmod_file
from archivebox.misc.util import enforce_types, is_static_file, dedupe
from ..logging_util import TimedProgress
from archivebox.logging_util import TimedProgress
from plugins_extractor.chrome.config import CHROME_CONFIG
from plugins_extractor.chrome.binaries import CHROME_BINARY
from plugins_extractor.singlefile.config import SINGLEFILE_CONFIG
from plugins_extractor.singlefile.binaries import SINGLEFILE_BINARY
from abx_plugin_chrome.config import CHROME_CONFIG
from abx_plugin_chrome.binaries import CHROME_BINARY
from .config import SINGLEFILE_CONFIG
from .binaries import SINGLEFILE_BINARY
def get_output_path():

View file

@ -1,21 +1,20 @@
__package__ = 'archivebox.extractors'
__package__ = 'abx_plugin_title'
import re
from html.parser import HTMLParser
from pathlib import Path
from typing import Optional
from archivebox.index.schema import Link, ArchiveResult, ArchiveOutput, ArchiveError
from archivebox.logging_util import TimedProgress
from archivebox.misc.util import (
enforce_types,
download_url,
htmldecode,
dedupe,
)
from abx_plugin_curl_extractor.config import CURL_CONFIG
from abx_plugin_curl_extractor.binaries import CURL_BINARY
from ..index.schema import Link, ArchiveResult, ArchiveOutput, ArchiveError
from ..logging_util import TimedProgress
from abx_plugin_curl.config import CURL_CONFIG
from abx_plugin_curl.binaries import CURL_BINARY

View file

@ -1,4 +1,4 @@
__package__ = 'abx_plugin_wget_extractor'
__package__ = 'abx_plugin_wget'
import re
import os
@ -7,6 +7,8 @@ from pathlib import Path
from typing import Optional
from datetime import datetime, timezone
from archivebox.logging_util import TimedProgress
from archivebox.index.schema import Link, ArchiveResult, ArchiveOutput, ArchiveError
from archivebox.misc.system import run, chmod_file
from archivebox.misc.util import (
enforce_types,
@ -20,8 +22,6 @@ from archivebox.misc.util import (
from .config import WGET_CONFIG
from .binaries import WGET_BINARY
from archivebox.logging_util import TimedProgress
from archivebox.index.schema import Link, ArchiveResult, ArchiveOutput, ArchiveError
def get_output_path():

View file

@ -1,15 +1,16 @@
__package__ = 'archivebox.extractors'
__package__ = 'abx_plugin_ytdlp'
from pathlib import Path
from typing import Optional
from archivebox.misc.system import run, chmod_file
from archivebox.misc.util import enforce_types, is_static_file, dedupe
from ..index.schema import Link, ArchiveResult, ArchiveOutput, ArchiveError
from ..logging_util import TimedProgress
from archivebox.index.schema import Link, ArchiveResult, ArchiveOutput, ArchiveError
from archivebox.logging_util import TimedProgress
from .config import YTDLP_CONFIG
from .binaries import YTDLP_BINARY
from plugins_extractor.ytdlp.config import YTDLP_CONFIG
from plugins_extractor.ytdlp.binaries import YTDLP_BINARY
def get_output_path():
return 'media/'

2
docs

@ -1 +1 @@
Subproject commit 1c69b1544a275938088e7bfd52a9ebd8c21f76fa
Subproject commit 02003ab1d212712075cb2fec2c645a9c4a0843d2