def __init__(self, crawl_infrastructure_plugins, w3af_core, max_discovery_time): """ :param crawl_infrastructure_plugins: Instances of CrawlInfrastructure plugins in a list :param w3af_core: The w3af core that we'll use for status reporting :param max_discovery_time: The max time (in seconds) to use for the discovery phase """ super(CrawlInfrastructure, self).__init__(crawl_infrastructure_plugins, w3af_core, thread_name=self.get_name(), max_pool_queued_tasks=100) self._max_discovery_time = int(max_discovery_time) # For filtering fuzzable requests found by plugins: self._variant_db = VariantDB() self._disabled_plugins = set() self._running = True self._report_max_time = True self._reported_found_urls = ScalableBloomFilter() # Override BaseConsumer.in_queue in order to have an ordered queue for # our crawling process. # # Read OrderedCachedQueue's documentation to understand why order is # important self.in_queue = OrderedCachedQueue(maxsize=10, name=self.get_name() + 'In')
def __init__(self): CrawlPlugin.__init__(self) # Internal variables self._compiled_ignore_re = None self._compiled_follow_re = None self._broken_links = DiskSet() self._first_run = True self._known_variants = VariantDB() self._already_filled_form = ScalableBloomFilter() # User configured variables self._ignore_regex = '' self._follow_regex = '.*' self._only_forward = False self._compile_re()
def __init__(self): CrawlPlugin.__init__(self) # Internal variables self._compiled_ignore_re = None self._compiled_follow_re = None self._broken_links = DiskSet(table_prefix='web_spider') self._first_run = True self._target_urls = [] self._target_domain = None self._already_filled_form = ScalableBloomFilter() self._variant_db = VariantDB() # User configured variables self._ignore_regex = '' self._follow_regex = '.*' self._only_forward = False self._compile_re()
def __init__(self, crawl_infrastructure_plugins, w3af_core, max_discovery_time): """ :param in_queue: The input queue that will feed the crawl_infrastructure plugins :param crawl_infrastructure_plugins: Instances of crawl_infrastructure plugins in a list :param w3af_core: The w3af core that we'll use for status reporting :param max_discovery_time: The max time (in seconds) to use for the discovery phase """ super(crawl_infrastructure, self).__init__(crawl_infrastructure_plugins, w3af_core, thread_name='CrawlInfra') self._max_discovery_time = int(max_discovery_time) # For filtering fuzzable requests found by plugins: self._variant_db = VariantDB() self._already_seen_urls = ScalableBloomFilter() self._disabled_plugins = set() self._running = True self._report_max_time = True
def setUp(self): create_temp_dir() self.vdb = VariantDB()
def setUp(self): MiscSettings().set_default_values() create_temp_dir() self.vdb = VariantDB()