def process_data(self, data: FilteredDomainData, **kwargs):
account = kwargs.get("Account")
# is_domain_good = False
is_spammed = False
try:
if isinstance(data, FilteredDomainData) and isinstance(account, SiteAccount):
majestic = MajesticCom(account)
if self._en_spam_check:
self._filter_domain_name(domain=data.domain)
# self._filter_anchor_text(majestic, data.domain)
# self._filter_ref_domains(majestic, data.domain)
if self._en_tf_check:
data = self._filter_tf_cf_backlink_ratio(majestic, data)
if not (data.tf >= self._min_tf and data.ref_domains >= self._min_ref_domains):
raise ValueError("tf or cf doesn't match. tf:" + str(data.tf) + " cf: " + str(data.cf) + " ref domain: " + str(data.ref_domains))
# if data.backlinks / data.ref_domains > self._max_backlink_to_ref_domain_ratio:
# raise MajesticSpamException("backlink to ref domain ratio is greater than {0:.1f}".format(self._max_backlink_to_ref_domain_ratio,))
if self._en_spam_check:
self._filter_anchor_text(majestic, data.domain)
self._filter_ref_domains(majestic, data.domain)
# is_domain_good = True
else:
raise ValueError("account is none in process_data")
except MajesticSpamException as mjx_ex:
is_spammed = True
data.exception = str(mjx_ex)
except Exception as ex:
data.exception = str(ex)
# ErrorLogger.log_error("MajesticFilter.process_data()", ex, str(data))
finally:
PrintLogger.print("Majestic processed: '" + str(data) + "' with: " + account.userID)
if isinstance(data, FilteredDomainData):
with self._sync_lock:
self._job_done += 1
if account is not None:
account.Available = True
# if data.cf >= self._min_cf and data.tf >= self._min_tf:
if data.tf >= self._min_tf and data.cf >= self._min_cf and data.ref_domains >= self._min_ref_domains:
# if data.tf >= self._min_tf and data.ref_domains >= self._min_ref_domains:
#print("Majatic output:", data)
# PrintLogger.print("domain: " + data.domain + " is good.")
if not self._is_throughput_debug:
if is_spammed:
CsvLogger.log_to_file(self._bad_log_file, [data.to_tuple()], dir_path=FilePath.get_temp_db_dir())
else:
CsvLogger.log_to_file(self._log_file, [data.to_tuple()], dir_path=FilePath.get_temp_db_dir()) # log this to file
self._output_queue.put(data)
return data
# elif is_spammed:
# if not self._is_throughput_debug:
# CsvLogger.log_to_file(self._bad_log_file, [data.to_tuple()], dir_path=FilePath.get_temp_db_dir())
# self._output_queue.put(data)
# return data
else:
if self._is_throughput_debug:
self._output_queue.put(data)
# return None
# print("domain: " + data.domain + " has exception:" + data.exception)
else:
pass
def process_data(self, data: FilteredDomainData, **kwargs):
#print("MozFilter processing: ", data)
account = kwargs.get("Account")
try:
if isinstance(data, FilteredDomainData) and isinstance(account, SiteAccount):
if TldUtility.is_top_tld(data.domain):
sleep_time =random.randint(self._min_sleep_time, self._max_wait)
time.sleep(sleep_time)
moz = MozCom(account)
if not self._is_throughput_debug:
ranking = moz.get_ranking_data(data.domain)
else:
ranking = 100
data.da = ranking
else:
pass
else:
raise ValueError("account is none in process_data")
except Exception as ex:
ErrorLogger.log_error("MozFilter", ex, "process_data() " + str(data) + " account: " + account.userID)
finally:
PrintLogger.print("Moz processed: " + str(data) + " with: " + account.userID)
if isinstance(data, FilteredDomainData):
with self._sync_lock:
self._job_done += 1
if account is not None:
account.Available = True
if data.da >= self._min_DA_value:
if not self._is_throughput_debug:
CsvLogger.log_to_file(self._log_file, [(data.domain, data.da)]) # log this to file
self._output_queue.put(data)
def process_data_batch(self, data: collections.Iterable, **kwargs):
#print("MozFilter processing: ", data)
account = kwargs.get("Account")
temp = []
try:
if isinstance(data, collections.Iterable) and isinstance(account, SiteAccount):
temp = [x for x in data if isinstance(x, FilteredDomainData) and TldUtility.is_top_tld(x.domain)]
check_list = [y.domain for y in temp]
sleep_time =random.randint(self._min_sleep_time, self._max_wait)
time.sleep(sleep_time)
moz = MozCom(account)
if not self._is_throughput_debug:
rankings = moz.get_ranking_data_batch(check_list, limit=len(check_list))
else:
rankings = [100] * len(temp)
for i in range(len(temp)):
temp[i].da = rankings[i]
else:
raise ValueError("account is none in process_data_batch()")
except Exception as ex:
ErrorLogger.log_error("MozFilter", ex, "process_data_batch() " + str(data) + " account: " + account.userID)
finally:
PrintLogger.print("Moz processed: " + str(data) + " with: " + account.userID)
with self._sync_lock:
job_done = [x for x in data if x is not None]
self._job_done += len(job_done)
if account is not None:
account.Available = True
for item in temp:
if isinstance(item, FilteredDomainData):
# print("moz processed:", item.domain)
if item.da >= self._min_DA_value:
if not self._is_throughput_debug:
CsvLogger.log_to_file(self._log_file, [(item.domain, item.da)]) # log this to file
self._output_queue.put(item)
def process_data(self, data: FilteredDomainData, **kwargs):
result_ok = False
if isinstance(data, FilteredDomainData):
try:
if len(data.domain_var) == 0:
data.domain_var = data.domain
links = ArchiveOrg.get_url_info(data.domain_var, min_size=self._min_page_size, limit=-100)
count = len(links)
data.archive = count
if count < self._min_profile:
pass
# raise ValueError("profile count is less than:" + str(self._min_profile))
result_ok = True
except Exception as ex:
if not self._is_throughput_debug:
pass
# ErrorLogger.log_error("ArchiveOrgFilter.process_data()", ex, data.domain_var)
finally:
with self._sync_lock:
self._job_done += 1
#with self._process_queue_lock:
if result_ok:
if not self._is_throughput_debug:
CsvLogger.log_to_file(self._log_file, [(data.domain, data.da, data.archive)]) # log this to file
self._output_queue.put(data)
# return data
else:
if self._is_throughput_debug:
self._output_queue.put(data)
# return None
else:
return None
