From 4a19051f4a31cdd15b73e5782c5562780245903a Mon Sep 17 00:00:00 2001
From: Nick Sweeting <github@sweeting.me>
Date: Tue, 1 Oct 2024 21:45:18 -0700
Subject: [PATCH] change BaseExtractor to use new extract hookspec

---
 archivebox/abx/archivebox/base_extractor.py | 105 ++++++++++++++++----
 1 file changed, 84 insertions(+), 21 deletions(-)

diff --git a/archivebox/abx/archivebox/base_extractor.py b/archivebox/abx/archivebox/base_extractor.py
index 4ba47cdd..e3202d96 100644
--- a/archivebox/abx/archivebox/base_extractor.py
+++ b/archivebox/abx/archivebox/base_extractor.py
@@ -1,16 +1,19 @@
 __package__ = 'abx.archivebox'
 
+import json
+import socket
 from typing import Optional, List, Literal, Annotated, Dict, Any
 from typing_extensions import Self
-
 from pathlib import Path
 
 from pydantic import model_validator, AfterValidator
 from pydantic_pkgr import BinName
+from django.utils.functional import cached_property
 
 import abx
 
 from .base_hook import BaseHook, HookType
+from .base_binary import BaseBinary
 
 
 def no_empty_args(args: List[str]) -> List[str]:
@@ -49,37 +52,97 @@ class BaseExtractor(BaseHook):
         return Path(self.id.lower())
 
     def should_extract(self, snapshot) -> bool:
-        output_dir = self.get_output_path(snapshot)
-        if output_dir.glob('*.*'):
+        try:
+            assert self.BIN.version
+        except Exception:
+            # could not load binary
             return False
+        
+        # output_dir = self.get_output_path(snapshot)
+        # if output_dir.glob('*.*'):
+        #     return False
         return True
 
-    # TODO: move this to a hookimpl
-    def extract(self, url: str, **kwargs) -> Dict[str, Any]:
-        output_dir = self.get_output_path(url, **kwargs)
+    @abx.hookimpl
+    def extract(self, snapshot_id: str) -> Dict[str, Any]:
+        from core.models import Snapshot
+        snapshot = Snapshot.objects.get(id=snapshot_id)
+        
+        if not self.should_extract(snapshot):
+            return {}
+        
+        from archivebox import CONSTANTS
+        # output_dir = self.get_output_path(snapshot) or CONSTANTS.TMP_DIR
+        output_dir = CONSTANTS.TMP_DIR / 'test'
+        output_dir.mkdir(parents=True, exist_ok=True)
 
-        cmd = [url, *self.args] if self.args is not None else [url, *self.default_args, *self.extra_args]
-        proc = self.exec(cmd, pwd=output_dir)
+        cmd = [snapshot.url, *self.args] if self.args is not None else [snapshot.url, *self.default_args, *self.extra_args]
+        proc = self.exec(cmd, cwd=output_dir)
+
+        stdout = proc.stdout.strip()
+        stderr = proc.stderr.strip()
+        output_json = None
+        output_text = stdout
+        try:
+            output_json = json.loads(stdout.strip())
+            output_text = None
+        except json.JSONDecodeError:
+            pass
+        
+        errors = []
+        if proc.returncode != 0:
+            errors.append(f'{self.BIN.name} returned non-zero exit code: {proc.returncode}')   
+
+        # pocket@git+https://github.com/tapanpandita/pocket.git@v0.3.7
+        binary_str = f'{self.BIN.abspath}@{self.BIN.binprovider.name}:{self.BIN.binprovider.get_packages(self.BIN.name)}=={self.BIN.version}'
 
         return {
-            'status': 'succeeded' if proc.returncode == 0 else 'failed',
-            'output': proc.stdout.decode().strip().split('\n')[-1],
-            'output_files': list(output_dir.glob('*.*')),
-
-            'stdout': proc.stdout.decode().strip(),
-            'stderr': proc.stderr.decode().strip(),
+            'extractor': self.name,
+            
+            'snapshot_id': snapshot.id,
+            'snapshot_abid': snapshot.abid,
+            'snapshot_url': snapshot.url,
+            'snapshot_created_by_id': snapshot.created_by_id,
+            
+            'hostname': socket.gethostname(),
+            
+            'binary': binary_str,
+            'binary_name': self.BIN.name,
+            'binary_provider': self.BIN.binprovider.name,
+            'binary_version': self.BIN.version,
+            'binary_abspath': self.BIN.abspath,
+            
+            'cmd': cmd,
+            'stdout': stdout,
+            'stderr': stderr,
             'returncode': proc.returncode,
+            
+            'status': 'succeeded' if proc.returncode == 0 else 'failed',
+            'errors': errors,
+            'output_dir': str(output_dir.relative_to(CONSTANTS.DATA_DIR)),
+            'output_files': list(str(path.relative_to(output_dir)) for path in output_dir.glob('**/*.*')),
+            'output_json': output_json or {},
+            'output_text': output_text or '',
         }
 
     # TODO: move this to a hookimpl
-    def exec(self, args: CmdArgsList, pwd: Optional[Path]=None, settings=None):
-        pwd = pwd or Path('.')
-        if settings is None:
-            from django.conf import settings as django_settings
-            settings = django_settings
+    def exec(self, args: CmdArgsList, cwd: Optional[Path]=None, binary=None):
+        cwd = cwd or Path('.')
+        binary = (binary or self.BINARY).load()
         
-        binary = settings.BINARIES[self.binary]
-        return binary.exec(args, pwd=pwd)
+        return binary.exec(cmd=args, cwd=cwd)
+    
+    @cached_property
+    def BINARY(self) -> BaseBinary:
+        from django.conf import settings
+        for binary in settings.BINARIES.values():
+            if binary.name == self.binary:
+                return binary
+        raise ValueError(f'Binary {self.binary} not found')
+    
+    @cached_property
+    def BIN(self) -> BaseBinary:
+        return self.BINARY.load()
 
     @abx.hookimpl
     def get_EXTRACTORS(self):