def test_scrape_correct_request(self):
item = ItemFactory(created_at_i=42)
httpretty.register_uri(httpretty.GET,
AlgoliaEndpoint.URL,
responses=self._createPages(pages=2,
hits=[item]),
content_type="application/json")
gen = Scraper().scrape(tag="test", since=42, until=43)
gen.next()
self.assertDictEqual(
httpretty.last_request().querystring, {
"numericFilters": ["created_at_i>42,created_at_i<43"],
"tags": ["test"],
"page": ["0"]
})
gen.next()
self.assertDictEqual(
httpretty.last_request().querystring, {
"numericFilters": ["created_at_i>42,created_at_i<43"],
"tags": ["test"],
"page": ["1"]
})
def test_scrape(self):
hits = [ItemFactory(created_at_i=42) for _ in range(2)]
httpretty.register_uri(httpretty.GET,
AlgoliaEndpoint.URL,
responses=self._createPages(hits=hits),
content_type="application/json")
resp = list(Scraper().scrape(tag="test", since=42))
self.assertListEqual(hits, resp)
def test_scrape_all_fields_are_returned(self):
item = ItemFactory(created_at_i=42)
httpretty.register_uri(httpretty.GET,
AlgoliaEndpoint.URL,
responses=self._createPages(hits=[item]),
content_type="application/json")
resp = list(Scraper().scrape(tag="test", since=42))
self.assertItemsEqual(resp[0].keys(),
["objectID", "created_at_i", "title"])
def test_scrape_no_items(self):
lastPage = ResponseFactory()
lastPage["nbHits"] = 0
lastPage["hits"] = []
httpretty.register_uri(httpretty.GET,
AlgoliaEndpoint.URL,
body=json.dumps(lastPage),
content_type="application/json")
resp = list(Scraper().scrape(tag="test", since=42))
self.assertListEqual(resp, [])
def test_scrape_translate_fields(self):
item = ItemFactory(created_at_i=42)
httpretty.register_uri(httpretty.GET,
AlgoliaEndpoint.URL,
responses=self._createPages(hits=[item]),
content_type="application/json")
fields = {"test": "created_at_i"}
resp = list(Scraper().scrape(tag="test", since=42, fields=fields))
self.assertItemsEqual(resp[0].keys(), ["test"])
def test_scrape_generator(self):
hits = [ItemFactory(created_at_i=42) for _ in range(2)]
httpretty.register_uri(httpretty.GET,
AlgoliaEndpoint.URL,
responses=self._createPages(pages=2, hits=hits),
content_type="application/json")
gen = Scraper().scrape(tag="test", since=42)
resp = gen.next()
self.assertEqual(resp, hits[0])
resp = gen.next()
self.assertEqual(resp, hits[1])
def test_scrape_page_limit(self):
hits = [ItemFactory(created_at_i=42) for _ in range(2)]
pages = [
httpretty.Response(body=json.dumps(ResponseFactory(hits=hits)))
]
lastPage = ResponseFactory()
# Trick the scraper in thinking it reached the last page but there are more
# items available.
lastPage["nbHits"] = 3
lastPage["hits"] = [] # this needs to be empty
pages.append(httpretty.Response(body=json.dumps(lastPage)))
httpretty.register_uri(httpretty.GET,
AlgoliaEndpoint.URL,
responses=pages,
content_type="application/json")
with self.assertRaises(TooManyItemsException):
list(Scraper().scrape(tag="test", since=42))
