Allow the parse command to write data to a file (#4377)

docs/topics/commands.rst

@@ -468,7 +468,7 @@ Supported options:
 * ``--callback`` or ``-c``: spider method to use as callback for parsing the
   response
 
-* ``--meta`` or ``-m``: additional request meta that will be passed to the callback 
+* ``--meta`` or ``-m``: additional request meta that will be passed to the callback
   request. This must be a valid json string. Example: --meta='{"foo" : "bar"}'
 
 * ``--cbkwargs``: additional keyword arguments that will be passed to the callback.
@@ -491,6 +491,8 @@ Supported options:
 
 * ``--verbose`` or ``-v``: display information for each depth level
 
+* ``--output`` or ``-o``: dump scraped items to a file
+
 .. skip: start
 
 Usage example::

scrapy/commands/__init__.py

@@ -108,7 +108,7 @@ class ScrapyCommand:
 
 class BaseRunSpiderCommand(ScrapyCommand):
     """
-    Common class used to share functionality between the crawl and runspider commands
+    Common class used to share functionality between the crawl, parse and runspider commands
     """
     def add_options(self, parser):
         ScrapyCommand.add_options(self, parser)

scrapy/commands/parse.py

@@ -4,18 +4,16 @@ import logging
 from itemadapter import is_item, ItemAdapter
 from w3lib.url import is_url
 
-from scrapy.commands import ScrapyCommand
+from scrapy.commands import BaseRunSpiderCommand
 from scrapy.http import Request
 from scrapy.utils import display
-from scrapy.utils.conf import arglist_to_dict
 from scrapy.utils.spider import iterate_spider_output, spidercls_for_request
 from scrapy.exceptions import UsageError
 
 logger = logging.getLogger(__name__)
 
 
-class Command(ScrapyCommand):
-
+class Command(BaseRunSpiderCommand):
     requires_project = True
 
     spider = None
@@ -31,11 +29,9 @@ class Command(ScrapyCommand):
         return "Parse URL (using its spider) and print the results"
 
     def add_options(self, parser):
-        ScrapyCommand.add_options(self, parser)
+        BaseRunSpiderCommand.add_options(self, parser)
         parser.add_option("--spider", dest="spider", default=None,
                           help="use this spider without looking for one")
-        parser.add_option("-a", dest="spargs", action="append", default=[], metavar="NAME=VALUE",
-                          help="set spider argument (may be repeated)")
         parser.add_option("--pipelines", action="store_true",
                           help="process items through pipelines")
         parser.add_option("--nolinks", dest="nolinks", action="store_true",
@@ -200,12 +196,15 @@ class Command(ScrapyCommand):
             self.add_items(depth, items)
             self.add_requests(depth, requests)
 
+            scraped_data = items if opts.output else []
             if depth < opts.depth:
                 for req in requests:
                     req.meta['_depth'] = depth + 1
                     req.meta['_callback'] = req.callback
                     req.callback = callback
-                return requests
+                scraped_data += requests
+
+            return scraped_data
 
         # update request meta if any extra meta was passed through the --meta/-m opts.
         if opts.meta:
@@ -221,18 +220,11 @@ class Command(ScrapyCommand):
         return request
 
     def process_options(self, args, opts):
-        ScrapyCommand.process_options(self, args, opts)
+        BaseRunSpiderCommand.process_options(self, args, opts)
 
-        self.process_spider_arguments(opts)
         self.process_request_meta(opts)
         self.process_request_cb_kwargs(opts)
 
-    def process_spider_arguments(self, opts):
-        try:
-            opts.spargs = arglist_to_dict(opts.spargs)
-        except ValueError:
-            raise UsageError("Invalid -a value, use -a NAME=VALUE", print_help=False)
-
     def process_request_meta(self, opts):
         if opts.meta:
             try:

tests/test_command_parse.py

@@ -1,5 +1,5 @@
 import os
-from os.path import join, abspath
+from os.path import join, abspath, isfile, exists
 from twisted.internet import defer
 from scrapy.utils.testsite import SiteTest
 from scrapy.utils.testproc import ProcessTest
@@ -218,3 +218,24 @@ ITEM_PIPELINES = {'%s.pipelines.MyPipeline': 1}
         )
         self.assertRegex(_textmode(out), r"""# Scraped Items  -+\n\[\]""")
         self.assertIn("""Cannot find a rule that matches""", _textmode(stderr))
+
+    @defer.inlineCallbacks
+    def test_output_flag(self):
+        """Checks if a file was created successfully having
+        correct format containing correct data in it.
+        """
+        file_name = 'data.json'
+        file_path = join(self.proj_path, file_name)
+        yield self.execute([
+            '--spider', self.spider_name,
+            '-c', 'parse',
+            '-o', file_name,
+            self.url('/html')
+        ])
+
+        self.assertTrue(exists(file_path))
+        self.assertTrue(isfile(file_path))
+
+        content = '[\n{},\n{"foo": "bar"}\n]'
+        with open(file_path, 'r') as f:
+            self.assertEqual(f.read(), content)