Skip to content

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

Add type hints to test_link.py and test_downloadermiddleware_stats.py (#7785)

SpiliosDmk13be37e4b107
diff --git a/pyproject.toml b/pyproject.toml
index 4220b12ed..5ed07a9ce 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -136,7 +136,6 @@ module = [
"tests.test_downloadermiddleware_redirect_metarefresh",
"tests.test_downloadermiddleware_retry",
"tests.test_downloadermiddleware_robotstxt",
- "tests.test_downloadermiddleware_stats",
"tests.test_downloaderslotssettings",
"tests.test_dupefilters",
"tests.test_engine_loop",
@@ -154,11 +153,9 @@ module = [
"tests.test_http_response",
"tests.test_http_response_text",
"tests.test_item",
- "tests.test_link",
"tests.test_linkextractors",
"tests.test_loader",
"tests.test_logformatter",
- "tests.test_logstats",
"tests.test_mail",
"tests.test_pipeline_crawl",
"tests.test_pipeline_files",
diff --git a/tests/test_downloadermiddleware_stats.py b/tests/test_downloadermiddleware_stats.py
index 5609360a7..b8fda25b4 100644
--- a/tests/test_downloadermiddleware_stats.py
+++ b/tests/test_downloadermiddleware_stats.py
@@ -1,3 +1,5 @@
+from __future__ import annotations
+
import pytest
from scrapy.downloadermiddlewares.stats import DownloaderStats, get_header_size
@@ -12,8 +14,9 @@ class MyException(Exception):
class TestDownloaderStats:
- def setup_method(self):
+ def setup_method(self) -> None:
self.crawler = get_crawler(Spider)
+ assert self.crawler.stats is not None
self.mw = DownloaderStats(self.crawler.stats)
self.crawler.stats.open_spider()
@@ -21,20 +24,21 @@ class TestDownloaderStats:
self.req = Request("http://scrapytest.org")
self.res = Response("http://scrapytest.org", status=400)
- def assertStatsEqual(self, key, value):
+ def assertStatsEqual(self, key: str, value: object) -> None:
+ assert self.crawler.stats is not None
assert self.crawler.stats.get_value(key) == value, str(
self.crawler.stats.get_stats()
)
- def test_process_request(self):
+ def test_process_request(self) -> None:
self.mw.process_request(self.req)
self.assertStatsEqual("downloader/request_count", 1)
- def test_process_response(self):
+ def test_process_response(self) -> None:
self.mw.process_response(self.req, self.res)
self.assertStatsEqual("downloader/response_count", 1)
- def test_process_exception(self):
+ def test_process_exception(self) -> None:
self.mw.process_exception(self.req, MyException())
self.assertStatsEqual("downloader/exception_count", 1)
self.assertStatsEqual(
@@ -42,14 +46,17 @@ class TestDownloaderStats:
1,
)
- def test_from_crawler_not_configured(self):
+ def test_from_crawler_not_configured(self) -> None:
crawler = get_crawler(Spider, {"DOWNLOADER_STATS": False})
with pytest.raises(NotConfigured):
DownloaderStats.from_crawler(crawler)
- def teardown_method(self):
+ def teardown_method(self) -> None:
+ assert self.crawler.stats is not None
self.crawler.stats.close_spider()
-def test_get_header_size_non_list_value():
- assert get_header_size({"Content-Type": "text/html"}) == 0
+def test_get_header_size_non_list_value() -> None:
+ # Deliberately passing a non-list/tuple header value to make sure
+ # get_header_size() degrades gracefully instead of raising.
+ assert get_header_size({"Content-Type": "text/html"}) == 0 # type: ignore[dict-item]
diff --git a/tests/test_link.py b/tests/test_link.py
index 0eeffe12b..40c53edd3 100644
--- a/tests/test_link.py
+++ b/tests/test_link.py
@@ -1,18 +1,20 @@
+from __future__ import annotations
+
import pytest
from scrapy.link import Link
class TestLink:
- def _assert_same_links(self, link1, link2):
+ def _assert_same_links(self, link1: Link, link2: Link) -> None:
assert link1 == link2
assert hash(link1) == hash(link2)
- def _assert_different_links(self, link1, link2):
+ def _assert_different_links(self, link1: Link, link2: Link) -> None:
assert link1 != link2
assert hash(link1) != hash(link2)
- def test_eq_and_hash(self):
+ def test_eq_and_hash(self) -> None:
l1 = Link("http://www.example.com")
l2 = Link("http://www.example.com/other")
l3 = Link("http://www.example.com")
@@ -45,17 +47,17 @@ class TestLink:
self._assert_different_links(l7, l9)
self._assert_different_links(l7, l10)
- def test_repr(self):
+ def test_repr(self) -> None:
l1 = Link(
"http://www.example.com", text="test", fragment="something", nofollow=True
)
l2 = eval(repr(l1))
self._assert_same_links(l1, l2)
- def test_bytes_url(self):
+ def test_bytes_url(self) -> None:
with pytest.raises(TypeError):
- Link(b"http://www.example.com/\xc2\xa3")
+ Link(b"http://www.example.com/\xc2\xa3") # type: ignore[arg-type]
- def test_eq_non_link(self):
+ def test_eq_non_link(self) -> None:
url = "http://example.com"
assert Link(url) != url
diff --git a/tests/test_logstats.py b/tests/test_logstats.py
index 370728e6a..213681ad1 100644
--- a/tests/test_logstats.py
+++ b/tests/test_logstats.py
@@ -1,3 +1,5 @@
+from __future__ import annotations
+
from datetime import datetime
import pytest
@@ -9,16 +11,17 @@ from tests.utils.decorators import coroutine_test
class TestLogStats:
- def setup_method(self):
+ def setup_method(self) -> None:
self.crawler = get_crawler(SimpleSpider)
self.spider = self.crawler._create_spider("spidey")
+ assert self.crawler.stats is not None
self.stats = self.crawler.stats
self.stats.set_value("response_received_count", 4802)
self.stats.set_value("item_scraped_count", 3201)
@coroutine_test
- async def test_stats_calculations(self):
+ async def test_stats_calculations(self) -> None:
logstats = LogStats.from_crawler(self.crawler)
with pytest.raises(AttributeError):
@@ -56,7 +59,7 @@ class TestLogStats:
assert self.stats.get_value("responses_per_minute") == 172.9
assert self.stats.get_value("items_per_minute") == 116.4
- def test_stats_calculations_no_time(self):
+ def test_stats_calculations_no_time(self) -> None:
"""The stat values should be None since the start and finish time are
not available.
"""
@@ -65,7 +68,7 @@ class TestLogStats:
assert self.stats.get_value("responses_per_minute") is None
assert self.stats.get_value("items_per_minute") is None
- def test_stats_calculation_no_elapsed_time(self):
+ def test_stats_calculation_no_elapsed_time(self) -> None:
"""The stat values should be None since the elapsed time is 0."""
logstats = LogStats.from_crawler(self.crawler)
self.stats.set_value("start_time", datetime.fromtimestamp(1655100172))