def get_defaults_spider_mw(self):
crawler = get_crawler()
spider = Spider('foo')
spider.set_crawler(crawler)
defaults = dict([(k, [v]) for k, v in \
six.iteritems(crawler.settings.get('DEFAULT_REQUEST_HEADERS'))])
return defaults, spider, DefaultHeadersMiddleware.from_crawler(crawler)
def get_defaults_spider_mw(self):
crawler = get_crawler()
spider = Spider('foo')
spider.set_crawler(crawler)
defaults = dict([(k, [v]) for k, v in \
crawler.settings.get('DEFAULT_REQUEST_HEADERS').iteritems()])
return defaults, spider, DefaultHeadersMiddleware.from_crawler(crawler)
class ChunkExtensionTest(object):
settings = {}
def tearDown(self):
self.remove_temp_dir()
def start(self, n_items_per_chunk=None, n_items=None, settings=None):
# Reset item generator and remove temporary dir
ItemGenerator.reset()
self.remove_temp_dir()
# Setup settings
settings = settings or self.settings.copy()
if n_items_per_chunk is not None:
settings['CHUNKED_FEED_ITEMS_PER_CHUNK'] = n_items_per_chunk
# Init Scrapy
self.crawler = get_crawler(settings)
self.spider = Spider('chunk_test')
self.spider.set_crawler(self.crawler)
self.extension = ChunkedFeedExporter.from_crawler(self.crawler)
self.extension.open_spider(self.spider)
# Add items if we have to
if n_items:
self.add_items(n_items)
def stop(self):
return self.extension.close_spider(self.spider)
def remove_temp_dir(self):
shutil.rmtree(EXPORT_TEMP_DIR, ignore_errors=True)
def add_items(self, n_items):
for i in range(n_items):
item = ItemGenerator.generate()
self.extension.item_scraped(item, self.spider)
def get_chunk_filename(self, chunk):
return EXPORT_FILE_PATTERN % {'chunk_number':chunk}
def get_chunk_filenames(self):
return [f for f in os.listdir(EXPORT_TEMP_DIR) if f.endswith(".json")]
def get_number_of_chunks(self):
return len(self.get_chunk_filenames())
def get_chunk_content(self, chunk):
with open(self.get_chunk_filename(chunk)) as f:
return json.load(f)
def ensure_number_of_chunks(self, n_chunks):
n = self.get_number_of_chunks()
assert n_chunks == n, "Wrong number of chunks. found %d, expecting %d" % (n, n_chunks)
def ensure_number_of_exported_items_per_chunk(self, chunk, n_items):
n_exported_items = len(self.get_chunk_content(chunk))
assert n_items == n_exported_items, "Wrong number of exported items. found %d, expecting %d" % \
(n_exported_items, n_items)
def _export_streamitem(self, values):
item = load_item_from_values(values)
crawler = get_crawler()
spider = Spider('streamitem_test')
spider.set_crawler(crawler)
storage = StreamItemFileFeedStorage(EXPORT_SC_FILENAME)
exporter = StreamItemExporter(file=storage.open(spider))
exporter.start_exporting()
exporter.export_item(item)
exporter.finish_exporting()
class ManagerTestCase(TestCase):
settings_dict = None
def setUp(self):
self.crawler = get_crawler(self.settings_dict)
self.spider = Spider('foo')
self.spider.set_crawler(self.crawler)
self.mwman = DownloaderMiddlewareManager.from_crawler(self.crawler)
# some mw depends on stats collector
self.crawler.stats.open_spider(self.spider)
return self.mwman.open_spider(self.spider)
def tearDown(self):
self.crawler.stats.close_spider(self.spider, '')
return self.mwman.close_spider(self.spider)
def _download(self, request, response=None):
"""Executes downloader mw manager's download method and returns
the result (Request or Response) or raise exception in case of
failure.
"""
if not response:
response = Response(request.url)
def download_func(**kwargs):
return response
dfd = self.mwman.download(download_func, request, self.spider)
# catch deferred result and return the value
results = []
dfd.addBoth(results.append)
self._wait(dfd)
ret = results[0]
if isinstance(ret, Failure):
ret.raiseException()
return ret
class ManagerTestCase(TestCase):
settings_dict = None
def setUp(self):
self.crawler = get_crawler(self.settings_dict)
self.spider = Spider('foo')
self.spider.set_crawler(self.crawler)
self.mwman = DownloaderMiddlewareManager.from_crawler(self.crawler)
# some mw depends on stats collector
self.crawler.stats.open_spider(self.spider)
return self.mwman.open_spider(self.spider)
def tearDown(self):
self.crawler.stats.close_spider(self.spider, '')
return self.mwman.close_spider(self.spider)
def _download(self, request, response=None):
"""Executes downloader mw manager's download method and returns
the result (Request or Response) or raise exception in case of
failure.
"""
if not response:
response = Response(request.url)
def download_func(**kwargs):
return response
dfd = self.mwman.download(download_func, request, self.spider)
# catch deferred result and return the value
results = []
dfd.addBoth(results.append)
self._wait(dfd)
ret = results[0]
if isinstance(ret, Failure):
ret.raiseException()
return ret
def get_spider_and_mw(self, default_useragent):
crawler = get_crawler({'USER_AGENT': default_useragent})
spider = Spider('foo')
spider.set_crawler(crawler)
return spider, UserAgentMiddleware.from_crawler(crawler)
def get_request_spider_mw(self):
crawler = get_crawler()
spider = Spider('foo')
spider.set_crawler(crawler)
request = Request('http://scrapytest.org/')
return request, spider, DownloadTimeoutMiddleware.from_crawler(crawler)
def get_request_spider_mw(self):
crawler = get_crawler()
spider = Spider("foo")
spider.set_crawler(crawler)
request = Request("http://scrapytest.org/")
return request, spider, DownloadTimeoutMiddleware.from_crawler(crawler)