From 8ec053ed1bddf6c09ffc9146335d5e91d25fe259 Mon Sep 17 00:00:00 2001 From: Patrick Robertson Date: Tue, 18 Mar 2025 08:56:22 +0000 Subject: [PATCH] Refactor the dropin 'is_suitable' method + fix tikwm implementation Makes it easier to maintain/understand. --- .../modules/generic_extractor/dropin.py | 17 +++++++++++++---- .../modules/generic_extractor/facebook.py | 2 +- .../generic_extractor/generic_extractor.py | 12 ++++-------- .../modules/generic_extractor/tiktok.py | 8 ++++++++ 4 files changed, 26 insertions(+), 13 deletions(-) diff --git a/src/auto_archiver/modules/generic_extractor/dropin.py b/src/auto_archiver/modules/generic_extractor/dropin.py index 8395f09..eb8cc71 100644 --- a/src/auto_archiver/modules/generic_extractor/dropin.py +++ b/src/auto_archiver/modules/generic_extractor/dropin.py @@ -59,9 +59,18 @@ class GenericDropin: """ return metadata - def is_suitable(self, url, info_extractor: InfoExtractor): + def suitable(self, url, info_extractor: InfoExtractor): """ - Used to override the InfoExtractor's 'is_suitable' method. Dropins should override this method to return True if the url is suitable for the extractor - (based on being able to parse other URLs) + A method to allow dropins to override their InfoExtractor's 'suitable' method. + Dropins should override this method and return True if the url is suitable for the extractor + (based on being able to parse other URLs). See the `suitable_extractors` method in the + `GenericExtractor` class for how this is implemented. + + The default behaviour of this method is to return the result of the InfoExtractor's 'suitable' method. + + ### Example: An example of where this is useful is for the FacebookIE extractor in yt-dlp. By default, + it's 'suitable' method only returns True for video URLs. However, we can override this method in the + Facebook dropin to return True for all Facebook URLs (photo/post types). This way, the Facebook dropin + can be used for all Facebook URLs. """ - return False + return info_extractor.suitable(url) diff --git a/src/auto_archiver/modules/generic_extractor/facebook.py b/src/auto_archiver/modules/generic_extractor/facebook.py index e04a862..5b264c6 100644 --- a/src/auto_archiver/modules/generic_extractor/facebook.py +++ b/src/auto_archiver/modules/generic_extractor/facebook.py @@ -142,7 +142,7 @@ class Facebook(GenericDropin): result.set_url(url) return result - def is_suitable(self, url, info_extractor: FacebookIE): + def suitable(self, url, info_extractor: FacebookIE): regex = r"(?:https?://(?:[\w-]+\.)?(?:facebook\.com||facebookwkhpilnemxj7asaniu7vnjjbiltxjqhye3mhbshg7kx5tfyd\.onion)/)" return re.match(regex, url) diff --git a/src/auto_archiver/modules/generic_extractor/generic_extractor.py b/src/auto_archiver/modules/generic_extractor/generic_extractor.py index 2f44ba8..e7d6be0 100644 --- a/src/auto_archiver/modules/generic_extractor/generic_extractor.py +++ b/src/auto_archiver/modules/generic_extractor/generic_extractor.py @@ -13,6 +13,7 @@ from loguru import logger from auto_archiver.core.extractor import Extractor from auto_archiver.core import Metadata, Media +from .dropin import GenericDropin class SkipYtdlp(Exception): @@ -71,14 +72,9 @@ class GenericExtractor(Extractor): continue # check if there's a dropin and see if that declares whether it's suitable - dropin = self.dropin_for_name(info_extractor.ie_key()) - if dropin and dropin.is_suitable(url, info_extractor): + dropin: GenericDropin = self.dropin_for_name(info_extractor.ie_key()) + if dropin and dropin.suitable(url, info_extractor): yield info_extractor - continue - - if info_extractor.suitable(url): - yield info_extractor - continue def suitable(self, url: str) -> bool: """ @@ -300,7 +296,7 @@ class GenericExtractor(Extractor): return self.add_metadata(data, info_extractor, url, result) - def dropin_for_name(self, dropin_name: str, additional_paths=[], package=__package__) -> Type[InfoExtractor]: + def dropin_for_name(self, dropin_name: str, additional_paths=[], package=__package__) -> GenericDropin: dropin_name = dropin_name.lower() if dropin_name == "generic": diff --git a/src/auto_archiver/modules/generic_extractor/tiktok.py b/src/auto_archiver/modules/generic_extractor/tiktok.py index b25abca..e545ba9 100644 --- a/src/auto_archiver/modules/generic_extractor/tiktok.py +++ b/src/auto_archiver/modules/generic_extractor/tiktok.py @@ -1,5 +1,8 @@ import requests from loguru import logger + +from yt_dlp.extractor.tiktok import TikTokIE, TikTokLiveIE, TikTokVMIE, TikTokUserIE + from auto_archiver.core import Metadata, Media from datetime import datetime, timezone from .dropin import GenericDropin @@ -13,6 +16,11 @@ class Tiktok(GenericDropin): TIKWM_ENDPOINT = "https://www.tikwm.com/api/?url={url}" + def suitable(self, url, info_extractor): + """This dropin (which uses Tikvm) is suitable for *all* Tiktok type URLs - videos, lives, VMs, and users. + Return the 'suitable' method from the TikTokIE class.""" + return any(extractor().suitable(url) for extractor in (TikTokIE, TikTokLiveIE, TikTokVMIE, TikTokUserIE)) + def extract_post(self, url: str, ie_instance): logger.debug(f"Using Tikwm API to attempt to download tiktok video from {url=}")