Merge pull request #234 from bellingcat/update_suggestions

Auto Updates

src/auto_archiver/core/orchestrator.py

@@ -15,6 +15,7 @@ from copy import copy
 
 from rich_argparse import RichHelpFormatter
 from loguru import logger
+import requests
 
 from .metadata import Metadata, Media
 from auto_archiver.version import __version__
@@ -349,6 +350,22 @@ class ArchivingOrchestrator:
 
         return self.setup_complete_parser(basic_config, yaml_config, unused_args)
     
+    def check_for_updates(self):
+        response = requests.get("https://pypi.org/pypi/auto-archiver/json").json()
+        latest_version = response['info']['version']
+        # check version compared to current version
+        if latest_version != __version__:
+            if os.environ.get('RUNNING_IN_DOCKER'):
+                update_cmd = "`docker pull bellingcat/auto-archiver:latest`"
+            else:
+                update_cmd = "`pip install --upgrade auto-archiver`"
+            logger.warning("")
+            logger.warning("********* IMPORTANT: UPDATE AVAILABLE ********")
+            logger.warning(f"A new version of auto-archiver is available (v{latest_version}, you have {__version__})")
+            logger.warning(f"Make sure to update to the latest version using: {update_cmd}")
+            logger.warning("")
+
+        
     def setup(self, args: list):
         """
         Function to configure all setup of the orchestrator: setup configs and load modules.
@@ -356,6 +373,8 @@ class ArchivingOrchestrator:
         This method should only ever be called once
         """
 
+        self.check_for_updates()
+
         if self.setup_finished:
             logger.warning("The `setup_config()` function should only ever be run once. \
                            If you need to re-run the setup, please re-instantiate a new instance of the orchestrator. \

src/auto_archiver/modules/console_db/console_db.py

@@ -10,7 +10,7 @@ class ConsoleDb(Database):
     """
 
     def started(self, item: Metadata) -> None:
-        logger.warning(f"STARTED {item}")
+        logger.info(f"STARTED {item}")
 
     def failed(self, item: Metadata, reason:str) -> None:
         logger.error(f"FAILED {item}: {reason}")

src/auto_archiver/modules/generic_extractor/__manifest__.py

@@ -28,6 +28,13 @@ the broader archiving framework.
  metadata objects. Some dropins are included in this generic_archiver by default, but
 custom dropins can be created to handle additional websites and passed to the archiver
 via the command line using the `--dropins` option (TODO!).
+
+### Auto-Updates
+
+The Generic Extractor will also automatically check for updates to `yt-dlp` (every 5 days by default).
+This can be configured using the `ytdlp_update_interval` setting (or disabled by setting it to -1).
+If you are having issues with the extractor, you can review the version of `yt-dlp` being used with `yt-dlp --version`.
+
 """,
     "configs": {
         "subtitles": {"default": True, "help": "download subtitles if available", "type": "bool"},
@@ -64,5 +71,10 @@ via the command line using the `--dropins` option (TODO!).
             "default": "inf",
             "help": "Use to limit the number of videos to download when a channel or long page is being extracted. 'inf' means no limit.",
         },
+        "ytdlp_update_interval": {
+            "default": 5,
+            "help": "How often to check for yt-dlp updates (days). If positive, will check and update yt-dlp every [num] days. Set it to -1 to disable, or 0 to always update on every run.",
+            "type": "int",
+        },
     },
 }

src/auto_archiver/modules/generic_extractor/generic_extractor.py

@@ -1,7 +1,11 @@
-import datetime, os, yt_dlp, pysubs2
+import datetime, os
 import importlib
+import subprocess
 from typing import Generator, Type
+
+import yt_dlp
 from yt_dlp.extractor.common import InfoExtractor
+import pysubs2
 
 from loguru import logger
 
@@ -11,6 +15,44 @@ from auto_archiver.core import Metadata, Media
 class GenericExtractor(Extractor):
     _dropins = {}
 
+    def setup(self):
+        # check for file .ytdlp-update in the secrets folder
+        if self.ytdlp_update_interval < 0:
+            return
+        
+        use_secrets = os.path.exists('secrets')
+        path = os.path.join('secrets' if use_secrets else '', '.ytdlp-update')
+        next_update_check = None
+        if os.path.exists(path):
+            with open(path, "r") as f:
+                next_update_check = datetime.datetime.fromisoformat(f.read())
+        
+        if not next_update_check or next_update_check < datetime.datetime.now():
+            self.update_ytdlp()
+
+            next_update_check = datetime.datetime.now() + datetime.timedelta(days=self.ytdlp_update_interval)
+            with open(path, "w") as f:
+                f.write(next_update_check.isoformat())
+
+    def update_ytdlp(self):
+        logger.info("Checking and updating yt-dlp...")
+        logger.info(f"Tip: change the 'ytdlp_update_interval' setting to control how often yt-dlp is updated. Set to -1 to disable or 0 to enable on every run. Current setting: {self.ytdlp_update_interval}")
+        from importlib.metadata import version as get_version
+        old_version = get_version("yt-dlp")
+        try:
+            # try and update with pip (this works inside poetry environment and in a normal virtualenv)
+            result = subprocess.run(["pip", "install", "--upgrade", "yt-dlp"], check=True, capture_output=True)
+
+            if "Successfully installed yt-dlp" in result.stdout.decode():
+                new_version = importlib.metadata.version("yt-dlp")
+                logger.info(f"yt-dlp successfully (from {old_version} to {new_version})")
+                importlib.reload(yt_dlp)
+            else:
+                logger.info("yt-dlp already up to date")
+
+        except Exception as e:
+            logger.error(f"Error updating yt-dlp: {e}")
+
     def suitable_extractors(self, url: str) -> Generator[str, None, None]:
         """
         Returns a list of valid extractors for the given URL"""