def test_next_url_new_domain_block(self):
my_example = "https://my.example.com/"
www_example = "https://www.example.com/"
schedule = Scheduler(my_example) # Constructor calls upon schedule_url
schedule.schedule_url(www_example)
self.assertEqual(schedule.next_url(), my_example)
self.assertEqual(schedule.next_url(), www_example)
def test_schedule_multiple_url_different_subdomain(self):
schedule = Scheduler("https://my.example.com/path/to/location") # Constructor calls upon schedule_url
schedule.schedule_url("https://www.example.com/path/to")
www_example = schedule.blocks_to_crawl.pop()
my_example = schedule.blocks_to_crawl.pop()
self.assertNotEqual(www_example, my_example)
self.assertTrue(www_example.next_url())
self.assertTrue(my_example.next_url())
def trade():
logger = get_logger()
loop = asyncio.get_event_loop()
scheduler = Scheduler()
try:
loop.run_until_complete(schedule_trading(scheduler))
except KeyboardInterrupt:
logger.debug('Trading interrupted...')
finally:
# cleanup once again?
pass
async def refresh_data():
logger = get_logger()
logger.info('Refreshing initiated from webapp')
factory = Factory()
await factory.init_cache()
factory.load_resources()
tasks = factory.create()
scheduler = Scheduler(tasks=tasks)
await scheduler.run_tasks()
await scheduler.cleanup()
async def test_daily_tasks():
scheduler = Scheduler()
async def dummy_task():
print('Running dummy task...')
await asyncio.sleep(0.1)
task = ScheduledTask(task=dummy_task, scheduled_time='23:45')
scheduler.add_daily_tasks([task])
task.is_ready = lambda: True
await scheduler.run_daily_tasks()
assert task.done
async def test_run_task_exceptions(resource, caplog):
bad_task = BadGrabber(resource=resource)
scheduler = Scheduler()
scheduler.add_tasks([bad_task])
import logging
with caplog.at_level(logging.INFO):
await scheduler.run_tasks()
print('asdf')
for record in caplog.records:
print(record)
print('asdf')
async def test_working_time():
scheduler = Scheduler()
with mock.patch('crawler.scheduler.get_config', _get_config_mock):
await scheduler.update_config()
assert scheduler.working_time is True
def test_next_url(self):
schedule = Scheduler("https://my.example.com/path/to/location") # Constructor calls upon schedule_url
correct_output = "https://my.example.com/path/to/location"
self.assertEqual(schedule.next_url(), correct_output)
from crawler.domain import Domain
from crawler.scheduler import Scheduler
from urllib.parse import urlparse
from multiprocessing import Process
pages_fetchers = []
pages_fetchers_limit = 60
inicio = datetime.datetime.now()
arr_str_urls_seeds = [
"http://cnn.com/", "https://pt.wikipedia.org/wiki/House,_M.D./",
"https://globoesporte.globo.com/"
]
arr_urls_seeds = [(urlparse(str_url), 0) for str_url in arr_str_urls_seeds]
scheduler = Scheduler(str_usr_agent="bifaroBot",
int_page_limit=1000,
int_depth_limit=6,
arr_urls_seeds=arr_urls_seeds)
for a in range(0, pages_fetchers_limit):
pages_fetchers.append(PageFetcher(scheduler))
proc = []
for pages_fetcher in pages_fetchers:
p = Process(target=pages_fetcher.run())
p.start()
proc.append(p)
for p in proc:
p.join()
fim = datetime.datetime.now()
print(f"Tempo gasto: {(fim-inicio).total_seconds()}")
def test_schedule_multiple_url_same_netloc(self):
schedule = Scheduler("https://www.example.com/path/to/location") # Constructor calls upon schedule_url
schedule.schedule_url("https://www.example.com/path/to")
block = schedule.blocks_to_crawl.pop()
correct_output = deque(["/path/to", "/path/to/location"])
self.assertEqual(sorted(block.extensions_to_crawl), sorted(correct_output))
def test_schedule_url_already_crawled(self):
url = "https://my.example.com/path/to/location"
schedule = Scheduler(url) # Constructor calls upon schedule_url
schedule.next_url()
self.assertFalse(schedule.schedule_url(url))
def test_schedule_same_url_twice(self):
schedule = Scheduler("https://my.example.com/path/to/location") # Constructor calls upon schedule_url
has_been_scheduled = schedule.schedule_url("https://my.example.com/path/to/location")
self.assertFalse(has_been_scheduled)
def test_schedule_url_different_domain(self):
schedule = Scheduler("https://my.example.com/path/to/location") # Constructor calls upon schedule_url
has_been_scheduled = schedule.schedule_url("https://my.example.org/path/to/location")
self.assertFalse(has_been_scheduled)
def test_next_url_extensions(self):
schedule = Scheduler("https://my.example.com/path/to/location") # Constructor calls upon schedule_url
schedule.schedule_url("https://my.example.com/path/to/location?key=val;word=bird#frag")
correct_output = "https://my.example.com/path/to/location?key=val;word=bird#frag"
self.assertEqual(schedule.next_url(), correct_output)
def test_next_url_empty_queue(self):
schedule = Scheduler("https://my.example.com/path/to/location") # Constructor calls upon schedule_url
schedule.next_url()
self.assertFalse(schedule.next_url())
def test_schedule_one_url(self):
schedule = Scheduler("https://www.example.com/path/to/location") # Constructor calls upon schedule_url
block = schedule.blocks_to_crawl.pop()
ext = block.extensions_to_crawl[0]
correct_output = "/path/to/location"
self.assertEqual(ext, correct_output)
def test_schedule_url_variety(self):
schedule = Scheduler("https://my.example.com/path/to/location") # Constructor calls upon schedule_url
has_been_scheduled = schedule.schedule_url("https://my.example.com/path/to/location?key1=val1;key2=val2#frag")
self.assertTrue(has_been_scheduled)
def test_schedule_url_params(self):
schedule = Scheduler("https://my.example.com/path/to/location") # Constructor calls upon schedule_url
has_been_scheduled = schedule.schedule_url("https://my.example.com/path/to/location;key=val")
self.assertTrue(has_been_scheduled)
def test_schedule_url_fragment(self):
schedule = Scheduler("https://my.example.com/path/to/location") # Constructor calls upon schedule_url
has_been_scheduled = schedule.schedule_url("https://my.example.com/path/to/location#maincontent")
self.assertTrue(has_been_scheduled)
