def pull_xml_data_to_dict(self, start_date):
all_files = os.listdir(output_path)
self.change_dict_values()
for files in all_files:
if '.zip' not in files:
extract.ExtractXMLData(files).fix_xml_encoding(output_path)
self.xml_handler = extract.ExtractXMLData(
output_path + files).row_name_entry_handler(header=True)
self.change_handler_values()
def extract_data(self):
print "Unzipping and modifying Analysis Tool results..."
fw.FileHandler().zip_file_open('Ryan Job Rollup Suggestor EAC.zip',
self.temp_out_files)
extract.ExtractXMLData(
'Ryan Job Rollup Suggestor EAC_0.xml').fix_xml_encoding(
self.temp_out_files)
count_dict = extract.ExtractXMLData(self.temp_out_files + 'Ryan Job Rollup Suggestor EAC_0.xml')\
.overall_medians_list_return()
return count_dict
def gather_results(self):
self.DTO = AlumniDTO()
for xml_files in os.listdir(const.anon_out):
if ".xml" in xml_files and 'Gina Alumni Analytics' in xml_files:
my_xml.fix_xml_encoding(const.anon_out, xml_files)
if 'Gina Alumni Analytics Query 1' in xml_files and '.xml' in xml_files:
self.update_string_progress.emit("Pulling from %s... " %
(xml_files))
data_dict = extract.ExtractXMLData(
const.anon_out +
xml_files).table_def_medians_list_handler()
main_key = 'Gina %s Query 01' % self.affiliate_id
self.update_dictionaries(xml_files, main_key, data_dict,
self.DTO.query_01)
elif 'Gina Alumni Analytics Query Large' in xml_files and '.xml' in xml_files:
self.update_string_progress.emit("Pulling from %s... " %
(xml_files))
data_dict = extract.ExtractXMLData(
const.anon_out +
xml_files).table_def_medians_list_handler()
main_key = 'Gina %s Query 02' % self.affiliate_id
self.update_dictionaries(xml_files, main_key, data_dict,
self.DTO.query_02)
elif 'Gina Alumni Analytics Query 2' in xml_files and '.xml' in xml_files:
self.update_string_progress.emit("Pulling from %s... " %
(xml_files))
data_dict = extract.ExtractXMLData(
const.anon_out +
xml_files).table_def_medians_list_handler()
main_key = 'Gina %s Query 03' % self.affiliate_id
self.update_dictionaries(xml_files, main_key, data_dict,
self.DTO.query_03)
elif 'Gina Alumni Analytics Query 3' in xml_files and '.xml' in xml_files:
self.update_string_progress.emit("Pulling from %s... " %
(xml_files))
data_dict = extract.ExtractXMLData(
const.anon_out +
xml_files).table_def_medians_list_handler()
main_key = 'Gina %s Query 04' % self.affiliate_id
self.update_dictionaries(xml_files, main_key, data_dict,
self.DTO.query_04)
elif 'Gina Alumni Analytics Query 4' in xml_files and '.xml' in xml_files:
self.update_string_progress.emit("Pulling from %s... " %
(xml_files))
data_dict = extract.ExtractXMLData(
const.anon_out +
xml_files).table_def_medians_list_handler()
main_key = 'Gina %s Query 05' % self.affiliate_id
self.update_dictionaries(xml_files, main_key, data_dict,
self.DTO.query_05)
elif 'Gina Alumni Analytics Query 5' in xml_files and '.xml' in xml_files:
self.update_string_progress.emit("Pulling from %s... " %
(xml_files))
data_dict = extract.ExtractXMLData(
const.anon_out +
xml_files).sample_def_alumni_analytics_handler()
main_key = 'Gina %s Query 06' % self.affiliate_id
self.update_dictionaries(xml_files, main_key, data_dict,
self.DTO.query_06)
def pull_model_data_from_xml(xml_file):
return extract.ExtractXMLData(xml_file).model_content_handler()
def pull_unconfirmed_data_from_xml(xml_file):
return extract.ExtractXMLData(xml_file).row_name_entry_handler()
def pull_iqr_data_from_xml(xml_file):
return extract.ExtractXMLData(xml_file).iqr_content_handler()
def pull_job_data_from_xml(xml_file):
return extract.ExtractXMLData(xml_file).overall_data_count()
anon_out = "\\\\filer02\\public\\Data_Analytics\\AnonReports\\TempOut\\"
class AlumniDTO:
def __init__(self):
self.query_01 = {}
self.query_02 = {}
self.query_03 = {}
self.query_04 = {}
self.query_05 = {}
self.query_06 = {}
test = AlumniDTO()
for xml_files in os.listdir(anon_out):
if ".xml" in xml_files and 'Gina Alumni Analytics Query 1' in xml_files:
my_xml.fix_xml_encoding(anon_out, xml_files)
if 'Gina Alumni Analytics Query 4' in xml_files and '.xml' in xml_files:
data_dict = extract.ExtractXMLData(
anon_out + xml_files).table_def_medians_list_handler()
main_key = 'Gina %s Query 04' % 1234
if main_key not in test.query_01.keys():
test.query_01[main_key] = data_dict
else:
copy_dict = test.query_01[main_key]
copy_dict.update(data_dict)
test.query_01[main_key] = copy_dict
print test.query_01
def pull_medians_data(self, file_name):
return extract.ExtractXMLData(self.temp_out_files +
file_name).overall_medians_list_return()
def pull_monthly_count_data(self, file_name):
return extract.ExtractXMLData(self.temp_out_files +
file_name).row_name_entry_handler()
def pull_count_data(self, file_name):
return extract.ExtractXMLData(self.temp_out_files +
file_name).overall_data_count()