add warning for FeedExporter

Author: vishesh10

Diff for: scrapy/commands/__init__.py

@@ -4,6 +4,7 @@
 
 import argparse
 import builtins
+import logging
 import os
 from pathlib import Path
 from typing import Any, Dict, Iterable, List, Optional
@@ -12,7 +13,13 @@
 
 from scrapy.crawler import Crawler, CrawlerProcess
 from scrapy.exceptions import UsageError
-from scrapy.utils.conf import arglist_to_dict, feed_process_params_from_cli
+from scrapy.utils.conf import (
+    arglist_to_dict,
+    build_component_list,
+    feed_process_params_from_cli,
+)
+
+logger = logging.getLogger(__name__)
 
 
 class ScrapyCommand:
@@ -178,6 +185,16 @@ def process_options(self, args: List[str], opts: argparse.Namespace) -> None:
             )
             self.settings.set("FEEDS", feeds, priority="cmdline")
 
+    def validate_feed_exporter(self, opts):
+        feed_eport_key = "scrapy.extensions.feedexport.FeedExporter"
+
+        if opts.output:
+            extensions = build_component_list(self.settings.getwithbase("EXTENSIONS"))
+            if feed_eport_key not in extensions:
+                logger.warning(
+                    "'FeedExporter' extension must be enabled for Feed Exports to work."
+                )
+
 
 class ScrapyHelpFormatter(argparse.HelpFormatter):
     """

Diff for: scrapy/commands/crawl.py

@@ -23,6 +23,7 @@ def run(self, args: List[str], opts: argparse.Namespace) -> None:
             raise UsageError(
                 "running 'scrapy crawl' with more than one spider is not supported"
             )
+        self.validate_feed_exporter(opts)
         spname = args[0]
 
         assert self.crawler_process

Diff for: scrapy/commands/parse.py

@@ -403,6 +403,7 @@ def run(self, args: List[str], opts: argparse.Namespace) -> None:
             raise UsageError()
         else:
             url = args[0]
+        self.validate_feed_exporter(opts)
 
         # prepare spidercls
         self.set_spidercls(url, opts)

Diff for: scrapy/commands/runspider.py

@@ -40,6 +40,7 @@ def long_desc(self) -> str:
     def run(self, args: List[str], opts: argparse.Namespace) -> None:
         if len(args) != 1:
             raise UsageError()
+        self.validate_feed_exporter(opts)
         filename = Path(args[0])
         if not filename.exists():
             raise UsageError(f"File not found: {filename}\n")

Diff for: tests/test_command_parse.py

@@ -449,3 +449,26 @@ def test_parse_add_options(self):
         self.assertEqual(namespace.depth, 2)
         self.assertEqual(namespace.spider, self.spider_name)
         self.assertTrue(namespace.verbose)
+
+    def test_exporter_disabled(self):
+        with self.assertLogs() as cm:
+            command = parse.Command()
+            settings = Settings()
+            settings.setdict(
+                {"EXTENSIONS": {"scrapy.extensions.feedexport.FeedExporter": None}},
+                priority="project",
+            )
+            command.settings = settings
+            parser = argparse.ArgumentParser(
+                formatter_class=argparse.HelpFormatter, conflict_handler="resolve"
+            )
+            command.add_options(parser)
+            opts, _ = parser.parse_known_args(args=[])
+
+            opts.output = ["example.json"]
+
+            command.validate_feed_exporter(opts)
+            expected = (
+                "'FeedExporter' extension must be enabled for Feed Exports to work."
+            )
+            self.assertTrue(any(expected in str for str in cm.output))

Diff for: tests/test_commands.py

@@ -20,8 +20,9 @@
 from twisted.trial import unittest
 
 import scrapy
-from scrapy.commands import ScrapyCommand, ScrapyHelpFormatter, view
+from scrapy.commands import ScrapyCommand, ScrapyHelpFormatter, crawl, runspider, view
 from scrapy.commands.startproject import IGNORE
+from scrapy.crawler import CrawlerProcess
 from scrapy.settings import Settings
 from scrapy.utils.python import to_unicode
 from scrapy.utils.test import get_testenv
@@ -986,6 +987,29 @@ def start_requests(self):
         self.assertIn("Spider closed (finished)", log)
         self.assertIn("The value of FOO is 42", log)
 
+    def test_exporter_disabled(self):
+        with self.assertLogs() as cm:
+            command = runspider.Command()
+            settings = Settings()
+            settings.setdict(
+                {"EXTENSIONS": {"scrapy.extensions.feedexport.FeedExporter": None}},
+                priority="project",
+            )
+            command.settings = settings
+            parser = argparse.ArgumentParser(
+                formatter_class=ScrapyHelpFormatter, conflict_handler="resolve"
+            )
+            command.add_options(parser)
+            opts, _ = parser.parse_known_args(args=[])
+
+            opts.output = ["example.json"]
+
+            command.validate_feed_exporter(opts)
+            expected = (
+                "'FeedExporter' extension must be enabled for Feed Exports to work."
+            )
+            self.assertTrue(any(expected in str for str in cm.output))
+
 
 class WindowsRunSpiderCommandTest(RunSpiderCommandTest):
     spider_filename = "myspider.pyw"
@@ -1055,6 +1079,30 @@ def start_requests(self):
         log = self.get_log(spider_code)
         self.assertIn("[myspider] DEBUG: It works!", log)
 
+    def test_exporter_disabled(self):
+        with self.assertLogs() as cm:
+            command = crawl.Command()
+            settings = Settings()
+            settings.setdict(
+                {"EXTENSIONS": {"scrapy.extensions.feedexport.FeedExporter": None}},
+                priority="project",
+            )
+            command.settings = settings
+            parser = argparse.ArgumentParser(
+                formatter_class=ScrapyHelpFormatter, conflict_handler="resolve"
+            )
+            command.add_options(parser)
+            opts, _ = parser.parse_known_args(args=[])
+            command.crawler_process = CrawlerProcess(settings)
+
+            opts.output = ["example.json"]
+
+            command.validate_feed_exporter(opts)
+            expected = (
+                "'FeedExporter' extension must be enabled for Feed Exports to work."
+            )
+            self.assertTrue(any(expected in str for str in cm.output))
+
     def test_output(self):
         spider_code = """
 import scrapy