Add backward-compatibility tests for Spider.start_requests

This commit is contained in:
Adrián Chaves 2025-03-12 03:58:35 +01:00
parent 2ec86ffb42
commit 6ce483125f
1 changed files with 109 additions and 21 deletions

View File

@ -1,12 +1,13 @@
from asyncio import sleep
import pytest
from twisted.internet.defer import Deferred, inlineCallbacks
from twisted.internet.defer import Deferred
from twisted.trial.unittest import TestCase
from scrapy import Spider, signals
from scrapy.core.engine import ExecutionEngine
from scrapy.utils.defer import maybe_deferred_to_future
from scrapy.exceptions import ScrapyDeprecationWarning
from scrapy.utils.defer import deferred_f_from_coro_f, maybe_deferred_to_future
from scrapy.utils.test import get_crawler
# These are the minimum seconds necessary to wait to reproduce the issue that
@ -16,6 +17,9 @@ from scrapy.utils.test import get_crawler
# much delay.
ASYNC_GEN_ERROR_MINIMUM_SECONDS = ExecutionEngine._SLOT_HEARTBEAT_INTERVAL + 0.01
ITEM_A = {"id": "a"}
ITEM_B = {"id": "b"}
def twisted_sleep(seconds):
from twisted.internet import reactor
@ -26,40 +30,124 @@ def twisted_sleep(seconds):
class MainTestCase(TestCase):
item = {"a": "b"}
@inlineCallbacks
def _test(self, yield_seeds_):
class TestSpider(Spider):
name = "test"
yield_seeds = yield_seeds_
async def _test_spider(self, spider, expected_items=None):
actual_items = []
expected_items = [] if expected_items is None else expected_items
def track_item(item, response, spider):
actual_items.append(item)
crawler = get_crawler(TestSpider)
crawler = get_crawler(spider)
crawler.signals.connect(track_item, signals.item_scraped)
yield crawler.crawl()
await maybe_deferred_to_future(crawler.crawl())
assert crawler.stats.get_value("finish_reason") == "finished"
assert actual_items == [self.item]
assert actual_items == expected_items
async def _test_yield_seeds(self, yield_seeds_, expected_items=None):
class TestSpider(Spider):
name = "test"
yield_seeds = yield_seeds_
await self._test_spider(TestSpider, expected_items)
@pytest.mark.only_asyncio
@inlineCallbacks
def test_asyncio_delayed(self):
@deferred_f_from_coro_f
async def test_asyncio_delayed(self):
async def yield_seeds(spider):
await sleep(ASYNC_GEN_ERROR_MINIMUM_SECONDS)
yield self.item
yield ITEM_A
yield self._test(yield_seeds)
await self._test_yield_seeds(yield_seeds, [ITEM_A])
@inlineCallbacks
def test_twisted_delayed(self):
@deferred_f_from_coro_f
async def test_twisted_delayed(self):
async def yield_seeds(spider):
await maybe_deferred_to_future(
twisted_sleep(ASYNC_GEN_ERROR_MINIMUM_SECONDS)
)
yield self.item
yield ITEM_A
yield self._test(yield_seeds)
await self._test_yield_seeds(yield_seeds, [ITEM_A])
@deferred_f_from_coro_f
async def test_start_urls(self):
class TestSpider(Spider):
name = "test"
start_urls = ["data:,"]
async def parse(self, response):
yield ITEM_A
await self._test_spider(TestSpider, [ITEM_A])
@deferred_f_from_coro_f
async def test_yield_seeds(self):
class TestSpider(Spider):
name = "test"
async def yield_seeds(self):
yield ITEM_A
await self._test_spider(TestSpider, [ITEM_A])
@deferred_f_from_coro_f
async def test_yield_seeds_subclass(self):
class BaseSpider(Spider):
async def yield_seeds(self):
yield ITEM_A
class TestSpider(BaseSpider):
name = "test"
await self._test_spider(TestSpider, [ITEM_A])
@deferred_f_from_coro_f
async def test_start_requests(self):
class TestSpider(Spider):
name = "test"
def start_requests(self):
yield ITEM_A
with pytest.warns(ScrapyDeprecationWarning):
await self._test_spider(TestSpider, [ITEM_A])
@deferred_f_from_coro_f
async def test_start_requests_subclass(self):
class BaseSpider(Spider):
def start_requests(self):
yield ITEM_A
class TestSpider(BaseSpider):
name = "test"
# The warning must be about the base class and not the subclass.
with pytest.warns(ScrapyDeprecationWarning, match="BaseSpider"):
await self._test_spider(TestSpider, [ITEM_A])
@deferred_f_from_coro_f
async def test_universal(self):
class TestSpider(Spider):
name = "test"
async def yield_seeds(self):
yield ITEM_A
def start_requests(self):
yield ITEM_B
await self._test_spider(TestSpider, [ITEM_A])
@deferred_f_from_coro_f
async def test_universal_subclass(self):
class BaseSpider(Spider):
async def yield_seeds(self):
yield ITEM_A
def start_requests(self):
yield ITEM_B
class TestSpider(BaseSpider):
name = "test"
await self._test_spider(TestSpider, [ITEM_A])