def test_url_plugin(self):
conf_urls = {'this_wont_be_crawled': True}
c = Crawler('/', conf_urls=conf_urls)
c.run()
logs = open('crawler_log')
output = logs.read()
self.assertTrue(output.find('These patterns were not matched during the crawl: this_wont_be_crawled') != -1)
def test_time_plugin(self):
#This isn't testing much, but I can't know how long the time will take
c = Crawler('/')
c.run()
logs = open('crawler_log')
output = logs.read()
self.assertTrue(output.find('Time taken:') != -1)
def test_time_plugin(self):
#This isn't testing much, but I can't know how long the time will take
c = Crawler('/')
c.run()
logs = open('crawler_log')
output = logs.read()
self.assertTrue(output.find('Time taken:') != -1)
def test_memory_plugin(self):
from test_utils.crawler.plugins.memory_plugin import Memory
Memory.active = True
c = Crawler('/')
c.run()
logs = open('crawler_log')
output = logs.read()
self.assertTrue(output.find('Memory consumed:') != -1)
def test_memory_plugin(self):
from test_utils.crawler.plugins.memory_plugin import Memory
Memory.active = True
c = Crawler('/')
c.run()
logs = open('crawler_log')
output = logs.read()
self.assertTrue(output.find('Memory consumed:') != -1)
def test_url_plugin(self):
conf_urls = {'this_wont_be_crawled': True}
c = Crawler('/', conf_urls=conf_urls)
c.run()
logs = open('crawler_log')
output = logs.read()
self.assertTrue(
output.find(
'These patterns were not matched during the crawl: this_wont_be_crawled'
) != -1)
def test_relative_crawling(self):
conf_urls = {}
verbosity = 1
c = Crawler('/1', conf_urls=conf_urls, verbosity=verbosity)
c.run()
self.assertEqual(c.crawled, {u'/1': True})
def test_basic_crawling(self):
conf_urls = {}
verbosity = 1
c = Crawler('/', conf_urls=conf_urls, verbosity=verbosity)
c.run()
self.assertEqual(c.crawled, {'/': True, u'/1': True, u'/2': True})
def test_relative_crawling(self):
c = Crawler('/1')
c.run()
self.assertEqual(c.crawled, {u'/1': True})
def test_basic_crawling(self):
c = Crawler('/')
c.run()
self.assertEqual(c.crawled, {'/': True, u'/1': True, u'/2': True})
def test_relative_crawling(self):
c = Crawler('/1')
c.run()
self.assertEqual(c.crawled, {u'/1': True})
def test_basic_crawling(self):
c = Crawler('/')
c.run()
self.assertEqual(c.crawled, {'/': True, u'/1': True, u'/2': True})
def handle(self, *args, **options):
verbosity = int(options.get('verbosity', 1))
depth = int(options.get('depth', 3))
auth = _parse_auth(options.get('auth'))
if verbosity > 1:
log_level = logging.DEBUG
elif verbosity:
log_level = logging.INFO
else:
log_level = logging.WARN
crawl_logger = logging.getLogger('crawler')
crawl_logger.setLevel(logging.DEBUG)
crawl_logger.propagate = 0
log_stats = LogStatsHandler()
crawl_logger.addHandler(log_stats)
console = logging.StreamHandler()
console.setLevel(log_level)
console.setFormatter(
logging.Formatter(
"%(name)s [%(levelname)s] %(module)s: %(message)s"))
crawl_logger.addHandler(console)
if len(args) > 1:
raise CommandError('Only one start url is currently supported.')
else:
start_url = args[0] if args else '/'
if getattr(settings, 'ADMIN_FOR', None):
settings_modules = [
__import__(m, {}, {}, ['']) for m in settings.ADMIN_FOR
]
else:
settings_modules = [settings]
conf_urls = {}
# Build the list URLs to test from urlpatterns:
for settings_mod in settings_modules:
try:
urlconf = __import__(settings_mod.ROOT_URLCONF, {}, {}, [''])
except Exception as e:
logging.exception("Error occurred while trying to load %s: %s",
settings_mod.ROOT_URLCONF, str(e))
continue
view_functions = extract_views_from_urlpatterns(
urlconf.urlpatterns)
for (func, regex, namespace, name) in view_functions:
# Get function name and add it to the hash of URLConf urls
func_name = hasattr(func,
'__name__') and func.__name__ or repr(func)
conf_urls[regex] = ['func.__module__', func_name]
c = Crawler(
start_url,
conf_urls=conf_urls,
verbosity=verbosity,
output_dir=options.get("output_dir"),
ascend=not options.get("no_parent"),
auth=auth,
)
# Load plugins:
for p in options['plugins']:
# This nested try is somewhat unsightly but allows easy Pythonic
# usage ("--enable-plugin=tidy") instead of Java-esque
# "--enable-plugin=test_utils.crawler.plugins.tidy"
try:
try:
plugin_module = __import__(p)
except ImportError:
if not "." in p:
plugin_module = __import__(
"test_utils.crawler.plugins.%s" % p,
fromlist=["test_utils.crawler.plugins"])
else:
raise
c.plugins.append(plugin_module.PLUGIN())
except (ImportError, AttributeError) as e:
crawl_logger.critical("Unable to load plugin %s: %s", p, e)
sys.exit(3)
c.run(max_depth=depth)
# We'll exit with a non-zero status if we had any errors
max_log_level = max(log_stats.stats.keys())
if max_log_level >= logging.ERROR:
sys.exit(2)
elif max_log_level >= logging.WARNING:
sys.exit(1)
else:
sys.exit(0)
# Load plugins:
for p in options['plugins']:
# This nested try is somewhat unsightly but allows easy Pythonic
# usage ("--enable-plugin=tidy") instead of Java-esque
# "--enable-plugin=test_utils.crawler.plugins.tidy"
try:
try:
plugin_module = __import__(p)
except ImportError:
if not "." in p:
plugin_module = __import__("test_utils.crawler.plugins.%s" % p)
else:
raise
plugin_module.active = True
except ImportError, e:
crawl_logger.critical("Unable to load plugin %s: %s", p, e)
sys.exit(3)
c = Crawler(start_url, conf_urls=conf_urls, verbosity=verbosity)
c.run(max_depth=depth)
# We'll exit with a non-zero status if we had any errors
max_log_level = max(log_stats.stats.keys())
if max_log_level >= logging.ERROR:
sys.exit(2)
elif max_log_level >= logging.WARNING:
sys.exit(1)
else:
sys.exit(0)
