Skip to content

Scrapy, a fast high-level web crawling & scraping framework for Python.

Rename FEED_STORAGE_BATCH_SIZE to FEED_STORAGE_BATCH_ITEM_COUNT

BroodingKangaroo2327ecead085
diff --git a/docs/topics/feed-exports.rst b/docs/topics/feed-exports.rst
index 2106b41f5..917240d4d 100644
--- a/docs/topics/feed-exports.rst
+++ b/docs/topics/feed-exports.rst
@@ -220,7 +220,7 @@ These are the settings used for configuring the feed exports:
* :setting:`FEED_STORAGE_FTP_ACTIVE`
* :setting:`FEED_STORAGE_S3_ACL`
* :setting:`FEED_EXPORTERS`
- * :setting:`FEED_EXPORT_BATCH_SIZE`
+ * :setting:`FEED_STORAGE_BATCH_ITEM_COUNT`
.. currentmodule:: scrapy.extensions.feedexport
@@ -431,9 +431,9 @@ format in :setting:`FEED_EXPORTERS`. E.g., to disable the built-in CSV exporter
.. _botocore: https://github.com/boto/botocore
.. _Canned ACL: https://docs.aws.amazon.com/AmazonS3/latest/dev/acl-overview.html#canned-acl
-.. setting:: FEED_EXPORT_BATCH_SIZE
+.. setting:: FEED_STORAGE_BATCH_ITEM_COUNT
-FEED_EXPORT_BATCH_SIZE
+FEED_STORAGE_BATCH_ITEM_COUNT
----------------------
Default: ``None``
@@ -448,7 +448,7 @@ Therefore you must specify %(batch_time)s or %(batch_id)s or both in FEED_URI.
For instance::
- FEED_EXPORT_BATCH_SIZE=100
+ FEED_STORAGE_BATCH_ITEM_COUNT=100
Your request can be like::
diff --git a/scrapy/extensions/feedexport.py b/scrapy/extensions/feedexport.py
index a262f5d18..5bc946634 100644
--- a/scrapy/extensions/feedexport.py
+++ b/scrapy/extensions/feedexport.py
@@ -242,7 +242,7 @@ class FeedExporter:
self.storages = self._load_components('FEED_STORAGES')
self.exporters = self._load_components('FEED_EXPORTERS')
- self.storage_batch_size = self.settings.get('FEED_STORAGE_BATCH_SIZE', None)
+ self.storage_batch_size = self.settings.get('FEED_STORAGE_BATCH_ITEM_COUNT', None)
for uri, feed in self.feeds.items():
if not self._storage_supported(uri):
raise NotConfigured
@@ -290,7 +290,7 @@ class FeedExporter:
def _start_new_batch(self, batch_id, uri, feed, spider, template_uri):
"""
Redirect the output data stream to a new file.
- Execute multiple times if 'FEED_STORAGE_BATCH' setting is specified.
+ Execute multiple times if 'FEED_STORAGE_BATCH_ITEM_COUNT' setting is specified.
:param batch_id: sequence number of current batch
:param uri: uri of the new batch to start
:param feed: dict with parameters of feed
@@ -326,7 +326,7 @@ class FeedExporter:
slot.start_exporting()
slot.exporter.export_item(item)
slot.itemcount += 1
- # create new slot for each slot with itemcount == FEED_STORAGE_BATCH_SIZE and close the old one
+ # create new slot for each slot with itemcount == FEED_STORAGE_BATCH_ITEM_COUNT and close the old one
if self.storage_batch_size and slot.itemcount == self.storage_batch_size:
uri_params = self._get_uri_params(spider, self.feeds[slot.template_uri]['uri_params'], slot)
self._close_slot(slot, spider)
@@ -358,12 +358,12 @@ class FeedExporter:
def _batch_deliveries_supported(self, uri):
"""
- If FEED_STORAGE_BATCH_SIZE setting is specified uri has to contain %(batch_time)s or %(batch_id)s
+ If FEED_STORAGE_BATCH_ITEM_COUNT setting is specified uri has to contain %(batch_time)s or %(batch_id)s
to distinguish different files of partial output
"""
if self.storage_batch_size is None or '%(batch_time)s' in uri or '%(batch_id)s' in uri:
return True
- logger.warning('%(batch_time)s or %(batch_id)s must be in uri if FEED_STORAGE_BATCH_SIZE setting is specified')
+ logger.warning('%(batch_time)s or %(batch_id)s must be in uri if FEED_STORAGE_BATCH_ITEM_COUNT setting is specified')
return False
def _storage_supported(self, uri):
diff --git a/scrapy/settings/default_settings.py b/scrapy/settings/default_settings.py
index c3463a505..5a7dc533e 100644
--- a/scrapy/settings/default_settings.py
+++ b/scrapy/settings/default_settings.py
@@ -146,7 +146,7 @@ FEED_STORAGES_BASE = {
's3': 'scrapy.extensions.feedexport.S3FeedStorage',
'ftp': 'scrapy.extensions.feedexport.FTPFeedStorage',
}
-FEED_STORAGE_BATCH_SIZE = None
+FEED_STORAGE_BATCH_ITEM_COUNT = None
FEED_EXPORTERS = {}
FEED_EXPORTERS_BASE = {
'json': 'scrapy.exporters.JsonItemExporter',
diff --git a/tests/test_feedexport.py b/tests/test_feedexport.py
index 2217bb4ed..1a21eeba9 100644
--- a/tests/test_feedexport.py
+++ b/tests/test_feedexport.py
@@ -1025,7 +1025,7 @@ class PartialDeliveriesTest(FeedExportTestBase):
os.path.join(self._random_temp_filename(), 'jl', self._file_mark): {'format': 'jl'},
},
})
- batch_size = settings['FEED_STORAGE_BATCH_SIZE']
+ batch_size = settings['FEED_STORAGE_BATCH_ITEM_COUNT']
rows = [{k: v for k, v in row.items() if v} for row in rows]
data = yield self.exported_data(items, settings)
for batch in data['jl']:
@@ -1041,7 +1041,7 @@ class PartialDeliveriesTest(FeedExportTestBase):
os.path.join(self._random_temp_filename(), 'csv', self._file_mark): {'format': 'csv'},
},
})
- batch_size = settings['FEED_STORAGE_BATCH_SIZE']
+ batch_size = settings['FEED_STORAGE_BATCH_ITEM_COUNT']
data = yield self.exported_data(items, settings)
for batch in data['csv']:
got_batch = csv.DictReader(to_unicode(batch).splitlines())
@@ -1057,7 +1057,7 @@ class PartialDeliveriesTest(FeedExportTestBase):
os.path.join(self._random_temp_filename(), 'xml', self._file_mark): {'format': 'xml'},
},
})
- batch_size = settings['FEED_STORAGE_BATCH_SIZE']
+ batch_size = settings['FEED_STORAGE_BATCH_ITEM_COUNT']
rows = [{k: v for k, v in row.items() if v} for row in rows]
data = yield self.exported_data(items, settings)
for batch in data['xml']:
@@ -1075,7 +1075,7 @@ class PartialDeliveriesTest(FeedExportTestBase):
os.path.join(self._random_temp_filename(), 'json', self._file_mark): {'format': 'json'},
},
})
- batch_size = settings['FEED_STORAGE_BATCH_SIZE']
+ batch_size = settings['FEED_STORAGE_BATCH_ITEM_COUNT']
rows = [{k: v for k, v in row.items() if v} for row in rows]
data = yield self.exported_data(items, settings)
# XML
@@ -1100,7 +1100,7 @@ class PartialDeliveriesTest(FeedExportTestBase):
os.path.join(self._random_temp_filename(), 'pickle', self._file_mark): {'format': 'pickle'},
},
})
- batch_size = settings['FEED_STORAGE_BATCH_SIZE']
+ batch_size = settings['FEED_STORAGE_BATCH_ITEM_COUNT']
rows = [{k: v for k, v in row.items() if v} for row in rows]
data = yield self.exported_data(items, settings)
import pickle
@@ -1117,7 +1117,7 @@ class PartialDeliveriesTest(FeedExportTestBase):
os.path.join(self._random_temp_filename(), 'marshal', self._file_mark): {'format': 'marshal'},
},
})
- batch_size = settings['FEED_STORAGE_BATCH_SIZE']
+ batch_size = settings['FEED_STORAGE_BATCH_ITEM_COUNT']
rows = [{k: v for k, v in row.items() if v} for row in rows]
data = yield self.exported_data(items, settings)
import marshal
@@ -1140,7 +1140,7 @@ class PartialDeliveriesTest(FeedExportTestBase):
{'foo': 'bar3', 'baz': 'quux3', 'egg': ''}
]
settings = {
- 'FEED_STORAGE_BATCH_SIZE': 2
+ 'FEED_STORAGE_BATCH_ITEM_COUNT': 2
}
header = self.MyItem.fields.keys()
yield self.assertExported(items, header, rows, settings=settings)
@@ -1151,7 +1151,7 @@ class PartialDeliveriesTest(FeedExportTestBase):
'FEEDS': {
self._random_temp_filename(): {'format': 'xml'},
},
- 'FEED_STORAGE_BATCH_SIZE': 1
+ 'FEED_STORAGE_BATCH_ITEM_COUNT': 1
}
crawler = get_crawler(settings_dict=settings)
self.assertRaises(NotConfigured, FeedExporter, crawler)
@@ -1163,7 +1163,7 @@ class PartialDeliveriesTest(FeedExportTestBase):
'FEEDS': {
os.path.join(self._random_temp_filename(), fmt, self._file_mark): {'format': fmt},
},
- 'FEED_STORAGE_BATCH_SIZE': 1
+ 'FEED_STORAGE_BATCH_ITEM_COUNT': 1
}
data = yield self.exported_no_data(settings)
data = dict(data)
@@ -1185,7 +1185,7 @@ class PartialDeliveriesTest(FeedExportTestBase):
},
'FEED_STORE_EMPTY': True,
'FEED_EXPORT_INDENT': None,
- 'FEED_STORAGE_BATCH_SIZE': 1,
+ 'FEED_STORAGE_BATCH_ITEM_COUNT': 1,
}
data = yield self.exported_no_data(settings)
data = dict(data)
@@ -1225,7 +1225,7 @@ class PartialDeliveriesTest(FeedExportTestBase):
'encoding': 'utf-8',
},
},
- 'FEED_STORAGE_BATCH_SIZE': 1,
+ 'FEED_STORAGE_BATCH_ITEM_COUNT': 1,
}
data = yield self.exported_data(items, settings)
for fmt, expected in formats.items():
@@ -1249,7 +1249,7 @@ class PartialDeliveriesTest(FeedExportTestBase):
'format': 'json',
},
},
- 'FEED_STORAGE_BATCH_SIZE': 1,
+ 'FEED_STORAGE_BATCH_ITEM_COUNT': 1,
}
data = yield self.exported_data(items, settings)
self.assertEqual(len(items) + 1, len(data['json']))
@@ -1291,7 +1291,7 @@ class PartialDeliveriesTest(FeedExportTestBase):
'format': 'json',
},
},
- 'FEED_STORAGE_BATCH_SIZE': 1,
+ 'FEED_STORAGE_BATCH_ITEM_COUNT': 1,
}
items = [
self.MyItem({'foo': 'bar1', 'egg': 'spam1'}),
@@ -1309,7 +1309,7 @@ class PartialDeliveriesTest(FeedExportTestBase):
s3 = boto3.resource('s3')
my_bucket = s3.Bucket(s3_test_bucket_name)
- batch_size = settings['FEED_STORAGE_BATCH_SIZE']
+ batch_size = settings['FEED_STORAGE_BATCH_ITEM_COUNT']
with MockServer() as s:
runner = CrawlerRunner(Settings(settings))