add extractors files to favicon and title plugins

archivebox/pkgs/abx-plugin-chrome/abx_plugin_chrome/extractors.py

@@ -0,0 +1,26 @@
+__package__ = 'abx_plugin_chrome'
+
+from abx_pkg import BinName
+
+from abx_spec_extractor import BaseExtractor, ExtractorName
+
+from .binaries import CHROME_BINARY
+
+
+class PDFExtractor(BaseExtractor):
+    name: ExtractorName = 'pdf'
+    binary: BinName = CHROME_BINARY.name
+
+PDF_EXTRACTOR = PDFExtractor()
+
+
+class ScreenshotExtractor(BaseExtractor):
+    name: ExtractorName = 'screenshot'
+    binary: BinName = CHROME_BINARY.name
+
+SCREENSHOT_EXTRACTOR = ScreenshotExtractor()
+
+class DOMExtractor(BaseExtractor):
+    name: ExtractorName = 'dom'
+    binary: BinName = CHROME_BINARY.name
+DOM_EXTRACTOR = DOMExtractor()

archivebox/pkgs/abx-plugin-favicon/abx_plugin_favicon/actors.py

@@ -0,0 +1,32 @@
+__package__ = 'abx_plugin_favicon'
+
+from typing import ClassVar
+
+from core.actors import ActorType
+from core.statemachines import ArchiveResultMachine
+
+from statemachine import State
+
+from .models import FaviconResult
+
+
+class FaviconResultActor(ActorType[FaviconResult]):
+    """
+    The primary actor for progressing ArchiveResult objects
+    through their lifecycle using the ArchiveResultMachine.
+    """
+    Model = FaviconResult
+    StateMachineClass = ArchiveResultMachine
+    
+    ACTIVE_STATE: ClassVar[State] = ArchiveResultMachine.started                # 'started'
+    FINAL_STATES: ClassVar[list[State]] = ArchiveResultMachine.final_states     # ['succeeded', 'failed', 'skipped']
+    STATE_FIELD_NAME: ClassVar[str] = ArchiveResultMachine.state_field_name     # status
+    
+    MAX_CONCURRENT_ACTORS: ClassVar[int] = 6
+    MAX_TICK_TIME: ClassVar[int] = 60
+    CLAIM_FROM_TOP_N: ClassVar[int] = MAX_CONCURRENT_ACTORS * 10
+
+    # @classproperty
+    # def qs(cls) -> QuerySet[ModelType]:
+    #     """Get the unfiltered and unsorted QuerySet of all objects that this Actor might care about."""
+    #     return cls.Model.objects.filter(extractor='favicon')

archivebox/pkgs/abx-plugin-favicon/abx_plugin_favicon/extractors.py

@@ -0,0 +1,19 @@
+__package__ = 'abx_plugin_favicon'
+
+from pathlib import Path
+
+from abx_pkg import BinName
+
+from abx_spec_extractor import BaseExtractor, ExtractorName
+
+from abx_plugin_curl.binaries import CURL_BINARY
+
+
+class FaviconExtractor(BaseExtractor):
+    name: ExtractorName = 'favicon'
+    binary: BinName = CURL_BINARY.name
+
+    def get_output_path(self, snapshot) -> Path | None:
+        return Path(snapshot.link_dir) / 'favicon.png'
+
+FAVICON_EXTRACTOR = FaviconExtractor()

archivebox/pkgs/abx-plugin-favicon/abx_plugin_favicon/models.py

@@ -0,0 +1,14 @@
+# from django.db import models
+
+# from core.models import ArchiveResult
+
+# class FaviconResultManager(models.Manager):
+#     def get_queryset(self):
+#         return super().get_queryset().filter(extractor='favicon')
+
+
+# class FaviconResult(ArchiveResult):
+#     objects = FaviconResultManager()
+
+#     class Meta:
+#         proxy = True

archivebox/pkgs/abx-plugin-title/abx_plugin_title/extractors.py

@@ -0,0 +1,10 @@
+__package__ = 'abx_plugin_title'
+
+from abx_spec_extractor import BaseExtractor, ExtractorName
+
+
+
+class TitleExtractor(BaseExtractor):
+    name: ExtractorName = 'title'
+
+TITLE_EXTRACTOR = TitleExtractor()