def seed_loader_setup(self, seeds_content=None):
seed_path = os.path.join(self.tmp_path, 'seeds.txt')
default_content = """
https://www.example.com
https://www.scrapy.org
"""
seeds_content = seeds_content or default_content
with open(seed_path, 'wb') as tmpl_file:
tmpl_file.write(seeds_content.encode('utf-8'))
assert os.path.isfile(seed_path) # Failure of test itself
settings = Settings()
settings.SEEDS_SOURCE = seed_path
crawler = type('crawler', (object, ), {})
crawler.settings = settings
return FileSeedLoader(crawler)
def seed_loader_setup(self, seeds_content=None):
seed_path = os.path.join(self.tmp_path, 'seeds.txt')
default_content = """
https://www.example.com
https://www.scrapy.org
"""
seeds_content = seeds_content or default_content
with open(seed_path, 'wb') as tmpl_file:
tmpl_file.write(seeds_content.encode('utf-8'))
assert os.path.isfile(seed_path) # Failure of test itself
settings = Settings()
settings.SEEDS_SOURCE = seed_path
crawler = type('crawler', (object,), {})
crawler.settings = settings
return FileSeedLoader(crawler)
def setUp(self):
self.tmp_path = mkdtemp()
settings = Settings()
settings.SEEDS_SOURCE = 's3://some-bucket/seeds-folder'
settings.SEEDS_AWS_ACCESS_KEY = 'access_key'
settings.SEEDS_AWS_SECRET_ACCESS_KEY = 'secret_key'
crawler = type('crawler', (object, ), {})
crawler.settings = settings
self.seed_path_1 = os.path.join(self.tmp_path, 'seeds1.txt')
self.seed_path_2 = os.path.join(self.tmp_path, 'seeds2.txt')
s1_content = """
https://www.example.com
https://www.scrapy.org
"""
s2_content = """
https://www.dmoz.org
https://www.test.com
"""
with open(self.seed_path_1, 'wb') as tmpl_file:
tmpl_file.write(s1_content.encode('utf-8'))
with open(self.seed_path_2, 'wb') as tmpl_file:
tmpl_file.write(s2_content.encode('utf-8'))
self.seed_loader = S3SeedLoader(crawler)
def setUp(self):
self.tmp_path = mkdtemp()
settings = Settings()
settings.SEEDS_SOURCE = 's3://some-bucket/seeds-folder'
settings.SEEDS_AWS_ACCESS_KEY = 'access_key'
settings.SEEDS_AWS_SECRET_ACCESS_KEY = 'secret_key'
crawler = type('crawler', (object,), {})
crawler.settings = settings
self.seed_path_1 = os.path.join(self.tmp_path, 'seeds1.txt')
self.seed_path_2 = os.path.join(self.tmp_path, 'seeds2.txt')
s1_content = """
https://www.example.com
https://www.scrapy.org
"""
s2_content = """
https://www.dmoz.org
https://www.test.com
"""
with open(self.seed_path_1, 'wb') as tmpl_file:
tmpl_file.write(s1_content.encode('utf-8'))
with open(self.seed_path_2, 'wb') as tmpl_file:
tmpl_file.write(s2_content.encode('utf-8'))
self.seed_loader = S3SeedLoader(crawler)
def test_invalid_s3_seed_source(self):
crawler = type('crawler', (object, ), {})
settings = Settings()
settings.SEEDS_SOURCE = 'invalid_url'
crawler.settings = settings
self.assertRaises(NotConfigured, S3SeedLoader, crawler)
def test_invalid_s3_seed_source(self):
crawler = type('crawler', (object,), {})
settings = Settings()
settings.SEEDS_SOURCE = 'invalid_url'
crawler.settings = settings
self.assertRaises(NotConfigured, S3SeedLoader, crawler)
