本文整理汇总了Python中scrapy.http.Response.copy方法的典型用法代码示例。如果您正苦于以下问题：Python Response.copy方法的具体用法？Python Response.copy怎么用？Python Response.copy使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类scrapy.http.Response的用法示例。
在下文中一共展示了Response.copy方法的5个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: TestHttpErrorMiddlewareHandleAll
# 需要导入模块: from scrapy.http import Response [as 别名]
# 或者: from scrapy.http.Response import copy [as 别名]
class TestHttpErrorMiddlewareHandleAll(TestCase):
def setUp(self):
self.spider = BaseSpider("foo")
self.mw = HttpErrorMiddleware(Settings({"HTTPERROR_ALLOW_ALL": True}))
self.req = Request("http://scrapytest.org")
self.res200 = Response("http://scrapytest.org", status=200)
self.res200.request = self.req
self.res404 = Response("http://scrapytest.org", status=404)
self.res404.request = self.req
self.res402 = Response("http://scrapytest.org", status=402)
self.res402.request = self.req
def test_process_spider_input(self):
self.assertEquals(None, self.mw.process_spider_input(self.res200, self.spider))
self.assertEquals(None, self.mw.process_spider_input(self.res404, self.spider))
def test_meta_overrides_settings(self):
request = Request("http://scrapytest.org", meta={"handle_httpstatus_list": [404]})
res404 = self.res404.copy()
res404.request = request
res402 = self.res402.copy()
res402.request = request
self.assertEquals(None, self.mw.process_spider_input(res404, self.spider))
self.assertRaises(HttpError, self.mw.process_spider_input, res402, self.spider)示例2: TestHttpErrorMiddleware
# 需要导入模块: from scrapy.http import Response [as 别名]
# 或者: from scrapy.http.Response import copy [as 别名]
class TestHttpErrorMiddleware(TestCase):
def setUp(self):
self.spider = BaseSpider("foo")
self.mw = HttpErrorMiddleware(Settings({}))
self.req = Request("http://scrapytest.org")
self.res200 = Response("http://scrapytest.org", status=200)
self.res200.request = self.req
self.res404 = Response("http://scrapytest.org", status=404)
self.res404.request = self.req
def test_process_spider_input(self):
self.assertEquals(None, self.mw.process_spider_input(self.res200, self.spider))
self.assertRaises(HttpError, self.mw.process_spider_input, self.res404, self.spider)
def test_process_spider_exception(self):
self.assertEquals([], self.mw.process_spider_exception(self.res404, HttpError(self.res404), self.spider))
self.assertEquals(None, self.mw.process_spider_exception(self.res404, Exception(), self.spider))
def test_handle_httpstatus_list(self):
res = self.res404.copy()
res.request = Request("http://scrapytest.org", meta={"handle_httpstatus_list": [404]})
self.assertEquals(None, self.mw.process_spider_input(res, self.spider))
self.spider.handle_httpstatus_list = [404]
self.assertEquals(None, self.mw.process_spider_input(self.res404, self.spider))示例3: TestHttpErrorMiddleware
# 需要导入模块: from scrapy.http import Response [as 别名]
# 或者: from scrapy.http.Response import copy [as 别名]
class TestHttpErrorMiddleware(TestCase):
def setUp(self):
self.spider = BaseSpider()
self.mw = HttpErrorMiddleware()
self.req = Request('http://scrapytest.org')
self.res200 = Response('http://scrapytest.org', status=200)
self.res200.request = self.req
self.res404 = Response('http://scrapytest.org', status=404)
self.res404.request = self.req
def test_process_spider_input(self):
self.assertEquals(self.mw.process_spider_input(self.res200, self.spider),
None)
self.assertEquals(self.mw.process_spider_input(self.res404, self.spider),
[])
def test_handle_httpstatus_list(self):
res = self.res404.copy()
res.request = Request('http://scrapytest.org',
meta={'handle_httpstatus_list': [404]})
self.assertEquals(self.mw.process_spider_input(res, self.spider),
None)
self.spider.handle_httpstatus_list = [404]
self.assertEquals(self.mw.process_spider_input(self.res404, self.spider),
None)示例4: TestHttpErrorMiddlewareSettings
# 需要导入模块: from scrapy.http import Response [as 别名]
# 或者: from scrapy.http.Response import copy [as 别名]
class TestHttpErrorMiddlewareSettings(TestCase):
"""Similar test, but with settings"""
def setUp(self):
self.spider = Spider('foo')
self.mw = HttpErrorMiddleware(Settings({'HTTPERROR_ALLOWED_CODES': (402,)}))
self.req = Request('http://scrapytest.org')
self.res200 = Response('http://scrapytest.org', status=200)
self.res200.request = self.req
self.res404 = Response('http://scrapytest.org', status=404)
self.res404.request = self.req
self.res402 = Response('http://scrapytest.org', status=402)
self.res402.request = self.req
def test_process_spider_input(self):
self.assertEquals(None,
self.mw.process_spider_input(self.res200, self.spider))
self.assertRaises(HttpError,
self.mw.process_spider_input, self.res404, self.spider)
self.assertEquals(None,
self.mw.process_spider_input(self.res402, self.spider))
def test_meta_overrides_settings(self):
request = Request('http://scrapytest.org',
meta={'handle_httpstatus_list': [404]})
res404 = self.res404.copy()
res404.request = request
res402 = self.res402.copy()
res402.request = request
self.assertEquals(None,
self.mw.process_spider_input(res404, self.spider))
self.assertRaises(HttpError,
self.mw.process_spider_input, res402, self.spider)
def test_spider_override_settings(self):
self.spider.handle_httpstatus_list = [404]
self.assertEquals(None,
self.mw.process_spider_input(self.res404, self.spider))
self.assertRaises(HttpError,
self.mw.process_spider_input, self.res402, self.spider)示例5: test_get_cached_beautifulsoup
# 需要导入模块: from scrapy.http import Response [as 别名]
# 或者: from scrapy.http.Response import copy [as 别名]
def test_get_cached_beautifulsoup(self):
r1 = Response('http://www.example.com', body='')
soup1 = get_cached_beautifulsoup(r1)
soup2 = get_cached_beautifulsoup(r1)
assert isinstance(soup1, BeautifulSoup)
assert isinstance(soup2, BeautifulSoup)
# make sure it's cached
assert soup1 is soup2
# when body is None, an empty soup should be returned
r1 = Response('http://www.example.com')
assert r1.body == ""
assert isinstance(get_cached_beautifulsoup(r1), BeautifulSoup)
r1 = Response('http://www.example.com', body='')
soup1 = get_cached_beautifulsoup(r1)
r2 = r1.copy()
soup2 = get_cached_beautifulsoup(r1)
soup3 = get_cached_beautifulsoup(r2)
assert soup1 is soup2
assert soup1 is not soup3