def aggregateData(self):
# Create new directory for storing aggregated data
# download_folder = path.abspath(path.join(self.download_dir, pardir))
aggregateFolder = DirManager(['aggregated_data'])
aggregateFolder.createFolder()
new_folder = aggregateFolder.getDirectory()
new_csv_file = '{}/data.csv'.format(new_folder)
insertColumsFolder = self.insertCandidateFolder.getDirectory()
filenames = sorted([
insertColumsFolder + "/" + f for f in listdir(insertColumsFolder)
],
key=path.getmtime)
with open(new_csv_file, 'w') as new_aggregate_csv:
new_worksheet = csv.writer(new_aggregate_csv,
quoting=csv.QUOTE_ALL)
# Loop through all workbooks (EXCEL)
header = False
for filename in filenames:
# Open worksheet
wb = xlrd.open_workbook(filename)
sheet = wb.sheet_by_index(0)
# Only pull excel header from the first file to reduce duplicates
if header:
for rownum in range(1, sheet.nrows):
new_worksheet.writerow(sheet.row_values(rownum))
else:
for rownum in range(sheet.nrows):
new_worksheet.writerow(sheet.row_values(rownum))
header = True
def test_empty_dir(self):
dirManager = DirManager()
tmpdir = tempfile.mkdtemp()
open(os.path.join(tmpdir, "test"), "w").close()
open(os.path.join(tmpdir, "other"), "w").close()
dirManager.add_directory(tmpdir)
self.assertTrue(isinstance(dirManager.list_available(), dict))
def insertCandidates(self, numDownloads, CandidateName):
print('Processing {} for {}'.format(numDownloads, CandidateName))
insertCandidateFolder = DirManager(['insertCandidateControlled'])
insertCandidateFolder.createFolder()
new_folder = insertCandidateFolder.getDirectory()
filenames = sorted(
[self.download_dir + "/" + f for f in listdir(self.download_dir)],
key=path.getmtime)
candidateHeader = "CandidateControlledName"
for fullfilepathname in filenames[-numDownloads:]:
filename = path.basename(fullfilepathname)
wb = xlrd.open_workbook(fullfilepathname,
logfile=open(devnull, 'w'))
errordTypes = [
'Cmte_ID', 'Intr_Nam L', 'Intr_City', 'Intr_ST', 'Off_S_H_Cd',
'XRef_Match'
]
data = pd.read_excel(
wb, dtype={datatype: str
for datatype in errordTypes})
if CandidateName == " ":
data.insert(0, candidateHeader, "Independent")
else:
data.insert(0, candidateHeader, CandidateName)
data.to_excel('{}/{}'.format(new_folder, filename), index=False)
def __init__(self,
path,
prefix,
cauldronAddr,
ignore=[
r'^\.', r'\.x?swp$', r'~', r'^__', r'__$', r'\.jar$',
r'\.db$'
]):
syslog.openlog(ident="X3Coven", facility=syslog.LOG_DAEMON)
self.path = path
self.prefix = prefix
self.cauldronAddr = cauldronAddr
self.plugins = {}
self.plugins_lock = Lock()
self.confRE = re.compile('^#\\s*x3\.([a-z0-9.]+)\\s*=\\s*(.*)\\s*$')
self.dirManager = DirManager(self.path, self, ignore=ignore)
self.cauldron = CauldronSender(self.cauldronAddr)
def __init__(self):
self.DEFAULT_SLEEP_TIME = 5
self.SEARCH_FORM_ADDRESS = "https://www.southtechhosting.com/SanJoseCity/CampaignDocsWebRetrieval/Search/SearchByElection.aspx"
# create data folder in current directory to store files
self.website = SjcWebsite()
self.new_dir = DirManager(["data"])
self.new_dir.createFolder()
self.download_dir = self.new_dir.getDirectory()
self.website.preprocessing = PreProcessing(self.download_dir)
options = webdriver.ChromeOptions()
# Uncomment block BELOW for headless data-retrieval
# --> Currently not working 100%, only downloads first link on form table
isHeadless = os.environ.get('HEADLESS', False)
if isHeadless:
options.add_argument("--headless")
# options.add_argument("--disable-gpu")
# options.add_argument("--window-size=1280,800")
# Uncomment block ABOVE for headless data-retrieval
options.add_argument("--ignore-certificate-errors")
options.add_argument("--test_type")
options.add_argument("--no-sandbox")
options.add_argument("start-maximized")
options.add_argument("disable-infobars")
options.add_argument("--disable-extensions")
plugs = {"enabled": False, "name": "Chrome PDF Viewer"}
prefs = {
"download.default_directory": self.download_dir,
"download.prompt_for_download": False,
"download.directory_upgrade": True,
"safebrowsing.enabled": False,
"safebrowsing.disable_download_protection": True,
"plugins.plugins_list": [plugs],
}
options.add_experimental_option("prefs", prefs)
self.driver = webdriver.Chrome(ChromeDriverManager().install(),
options=options)
def insertColumns(self, numDownloads, CandidateName, ElectionDate,
BallotItem):
print('Processing {} for {}'.format(numDownloads, CandidateName))
if numDownloads == 0:
return
self.insertCandidateFolder = DirManager(['insertedData'])
self.insertCandidateFolder.createFolder()
new_folder = self.insertCandidateFolder.getDirectory()
filenames = self.insertColumnsHelper()
candidateHeader = "CandidateControlledName"
electionDateHeader = "Election Date"
ballotItemHeader = "Ballot Item"
print(filenames)
for fullfilepathname in filenames[-numDownloads:]:
filename = path.basename(fullfilepathname)
print(filename)
wb = xlrd.open_workbook(fullfilepathname,
logfile=open(devnull, 'w'))
errordTypes = [
'Cmte_ID', 'Intr_Nam L', 'Intr_City', 'Intr_ST', 'Off_S_H_Cd',
'XRef_Match'
]
data = pd.read_excel(
wb, dtype={datatype: str
for datatype in errordTypes})
if CandidateName == " ":
data.insert(0, candidateHeader, "Independent")
else:
data.insert(0, candidateHeader, CandidateName)
data.insert(0, electionDateHeader, ElectionDate)
data.insert(0, ballotItemHeader, BallotItem)
data.to_excel('{}/{}'.format(new_folder, filename), index=False)
def test_found_entry(self):
dirManager = DirManager()
dirManager.add_directory(test_dir)
ans = dirManager.found_entry(dot)
self.assertTrue(ans == "../test_files/DOt_-_05_-_IMF.mp3")
def test_random_list(self):
dirManager = DirManager()
dirManager.add_directory("../test_files/")
x = dirManager.random_list()
self.assertTrue(True)
def test_available_dict(self):
dirManager = DirManager()
json = dict(dirManager.list_available_nested_dict())
self.assertTrue(isinstance(json, dict))
def test_available(self):
dirManager = DirManager()
self.assertTrue(isinstance(dirManager.list_available(), dict))
def test_get_directory(self):
dirManager = DirManager()
dirManager.add_directory("./teste/")
self.assertTrue("./teste/" in dirManager.get_directory())
self.assertTrue("./teste/" == dirManager.get_directory("./teste/"))
def setUp(self):
self.dm = DirManager()
self.dm.add_directory(test_dir)
def setUpClass(cls):
global dirmanager
config.base_dir = tempfile.mkdtemp()
config.__reload__()
dirmanager = DirManager()
