Merge branch 'more_mainifests' into load_modules

src/auto_archiver/modules/generic_extractor/bluesky.py

@@ -1,17 +1,12 @@
-import os
-import mimetypes
-
-import requests
 from loguru import logger
 
-from auto_archiver.core.context import ArchivingContext
-from auto_archiver.archivers.archiver import Archiver
+from auto_archiver.base_processors.extractor import Extractor
 from auto_archiver.core.metadata import Metadata, Media
 from .dropin import GenericDropin, InfoExtractor
 
 class Bluesky(GenericDropin):
 
-    def create_metadata(self, post: dict, ie_instance: InfoExtractor, archiver: Archiver, url: str) -> Metadata:
+    def create_metadata(self, post: dict, ie_instance: InfoExtractor, archiver: Extractor, url: str) -> Metadata:
         result = Metadata()
         result.set_url(url)
         result.set_title(post["record"]["text"])
@@ -42,7 +37,7 @@ class Bluesky(GenericDropin):
 
 
 
-    def _download_bsky_embeds(self, post: dict, archiver: Archiver) -> list[Media]:
+    def _download_bsky_embeds(self, post: dict, archiver: Extractor) -> list[Media]:
         """
         Iterates over image(s) or video in a Bluesky post and downloads them        
         """

src/auto_archiver/modules/generic_extractor/dropin.py

@@ -1,6 +1,6 @@
 from yt_dlp.extractor.common import InfoExtractor
 from auto_archiver.core.metadata import Metadata
-from auto_archiver.archivers.archiver import Archiver
+from auto_archiver.base_processors.extractor import Extractor
 
 class GenericDropin:
     """Base class for dropins for the generic extractor.
@@ -30,7 +30,7 @@ class GenericDropin:
         raise NotImplementedError("This method should be implemented in the subclass")
     
 
-    def create_metadata(self, post: dict, ie_instance: InfoExtractor, archiver: Archiver, url: str) -> Metadata:
+    def create_metadata(self, post: dict, ie_instance: InfoExtractor, archiver: Extractor, url: str) -> Metadata:
         """
         This method should create a Metadata object from the post data.
         """

src/auto_archiver/modules/generic_extractor/generic_extractor.py

@@ -5,10 +5,10 @@ from yt_dlp.extractor.common import InfoExtractor
 
 from loguru import logger
 
-from auto_archiver.archivers.archiver import Archiver
+from auto_archiver.base_processors.extractor import Extractor
 from ...core import Metadata, Media, ArchivingContext
 
-class GenericExtractor(Archiver):
+class GenericExtractor(Extractor):
     name = "youtubedl_archiver" #left as is for backwards compat
     _dropins = {}
 

src/auto_archiver/modules/generic_extractor/truth.py

@@ -2,7 +2,7 @@ from typing import Type
 
 from auto_archiver.utils import traverse_obj
 from auto_archiver.core.metadata import Metadata, Media
-from auto_archiver.archivers.archiver import Archiver
+from auto_archiver.base_processors.extractor import Extractor
 from yt_dlp.extractor.common import InfoExtractor
 
 from dateutil.parser import parse as parse_dt
@@ -19,7 +19,7 @@ class Truth(GenericDropin):
     def skip_ytdlp_download(self, url, ie_instance: Type[InfoExtractor]) -> bool:
         return True
 
-    def create_metadata(self, post: dict, ie_instance: InfoExtractor, archiver: Archiver, url: str) -> Metadata:
+    def create_metadata(self, post: dict, ie_instance: InfoExtractor, archiver: Extractor, url: str) -> Metadata:
         """
         Creates metadata from a truth social post
         

src/auto_archiver/modules/generic_extractor/twitter.py

@@ -6,7 +6,7 @@ from slugify import slugify
 
 from auto_archiver.core.metadata import Metadata, Media
 from auto_archiver.utils import UrlUtil
-from auto_archiver.archivers.archiver import Archiver
+from auto_archiver.base_processors.extractor import Extractor
 
 from .dropin import GenericDropin, InfoExtractor
 
@@ -32,7 +32,7 @@ class Twitter(GenericDropin):
         twid = ie_instance._match_valid_url(url).group('id')
         return ie_instance._extract_status(twid=twid)
 
-    def create_metadata(self, tweet: dict, ie_instance: InfoExtractor, archiver: Archiver, url: str) -> Metadata:
+    def create_metadata(self, tweet: dict, ie_instance: InfoExtractor, archiver: Extractor, url: str) -> Metadata:
         result = Metadata()
         try:
             if not tweet.get("user") or not tweet.get("created_at"):