def names_parse(self):
#header_fields = ["Property_Name", "Name", "Source"]
people = []
count = 0
for excel_file in self.excel_files:
print excel_file
count += 1
print count
workbook = xlrd.open_workbook(excel_file)
worksheet = workbook.sheet_by_index(0)
name_index = 0
event_date_index = 0
source_index = 0
status_index = 0
start = False
end = False
prop_name_cell = ""
person = {}
for row_index in range(worksheet.nrows):
cell = worksheet.cell(row_index, 0).value
cell = cell.strip()
cell = cell.replace('\n','')
if 'property:' in cell.lower():
prop_name_cell = worksheet.cell(row_index,0).value
elif cell in self.headers:
start = True
header_row = worksheet.row_values(row_index,0)
#Find the column index of the different header row names
for i, c in enumerate(header_row):
if 'name' in c.lower() and 'agent' not in c.lower():
#print c, i
name_index = i
#start = True
elif 'event' in c.lower() and 'date' in c.lower():
event_date_index = i
elif 'source' in c.lower():
source_index = i
elif 'status' in c.lower():
status_index = i
#The row with cell "Grand Total" is used as the flag to signal the end of name collecting.
elif 'grand' in cell.lower() and 'total' in cell.lower():
end = True
elif end:
continue
#Begin collecting names after getting past the header row
elif start:
#print cell
if cell.replace(" ", "") in [i.replace(" ", "") for i in self.section_titles]:
section_title_cell = cell
name_cell = worksheet.cell(row_index, name_index).value
name_cell = name_cell.encode('utf-8')
event_date_cell = worksheet.cell(row_index, event_date_index).value
source_cell = worksheet.cell(row_index, source_index).value
status_cell = worksheet.cell(row_index, status_index).value
if name_cell != "":
#writer.writerow([prop_name_cell, name_cell, source_cell])
prop_key = re.sub("\(\d*\)?", "", prop_name_cell).strip().lower()
prop_key = " ".join(prop_key.split())
if self.args.raw == True:
person = {'Property ID': self.keys.get(prop_key, ''), 'Property_Name': prop_name_cell, 'Name': name_cell, 'Source': source_cell, 'Status': status_cell, 'Event Date': event_date_cell,'Action': section_title_cell}
else:
#print name_cell
person = {'Property ID': self.keys.get(prop_key, ''), 'Property_Name': prop_name_cell, 'Name': name_cell, 'Source': source_cell, 'Status': status_cell, 'Event Date': event_date_cell,'Action': section_title_cell}
processed_name = eagle.namer(name_cell)
person['First Name'] = processed_name[0].encode('utf-8')
person['Last Name'] = processed_name[1].encode('utf-8')
#person = {'Property_Name': prop_name_cell, 'Name': name_cell, 'Source': source_cell, 'Event Date': event_date_cell,'Action': section_title_cell}
#Add person dict to people list
people.append(person)
with open(self.output, 'wb') as out_file:
if self.args.raw == True:
out_file.write(u'\ufeff'.encode('utf8')) #BOM for Excel to open UTF-8 file properly
writer = csv.DictWriter(out_file, fieldnames=self.header_fields_raw)
writer.writeheader()
for person in people:
#print person
writer.writerow(person)
else:
out_file.write(u'\ufeff'.encode('utf8')) #BOM for Excel to open UTF-8 file properly
writer = csv.DictWriter(out_file, fieldnames=self.header_fields)
writer.writeheader()
for person in people:
if self.args.filter == True:
status = person['Status'].lower()
if 'resident' in status:
writer.writerow(person)
else:
writer.writerow(person)
def names_parse(self):
#header_fields = ["Property_Name", "Name", "Source"]
people = []
for excel_file in self.excel_files:
workbook = xlrd.open_workbook(excel_file)
worksheet = workbook.sheet_by_index(0)
name_index = 0
event_date_index = 0
source_index = 0
status_index = 0
start = False
end = False
prop_name_cell = ""
person = {}
for row_index in range(worksheet.nrows):
cell = worksheet.cell(row_index, 0).value
cell = cell.strip()
cell = cell.replace('\n', '')
if 'property:' in cell.lower():
prop_name_cell = worksheet.cell(row_index, 0).value
elif cell in self.headers:
start = True
header_row = worksheet.row_values(row_index, 0)
#Find the column index of the different header row names
for i, c in enumerate(header_row):
if 'name' in c.lower() and 'agent' not in c.lower():
print c, i
name_index = i
#start = True
elif 'event' in c.lower() and 'date' in c.lower():
event_date_index = i
elif 'source' in c.lower():
source_index = i
elif 'status' in c.lower():
status_index = i
#The row with cell "Grand Total" is used as the flag to signal the end of name collecting.
elif 'grand' in cell.lower() and 'total' in cell.lower():
end = True
elif end:
continue
#Begin collecting names after getting past the header row
elif start:
if cell in self.section_titles:
section_title_cell = cell
name_cell = worksheet.cell(row_index, name_index).value
event_date_cell = worksheet.cell(row_index,
event_date_index).value
source_cell = worksheet.cell(row_index, source_index).value
status_cell = worksheet.cell(row_index, status_index).value
if name_cell != "":
#writer.writerow([prop_name_cell, name_cell, source_cell])
prop_key = re.sub("\(\d*\)?", "",
prop_name_cell).strip().lower()
prop_key = " ".join(prop_key.split())
if self.args.raw == True:
person = {
'Property ID': self.keys.get(prop_key, ''),
'Property_Name': prop_name_cell,
'Name': name_cell,
'Source': source_cell,
'Status': status_cell,
'Event Date': event_date_cell,
'Action': section_title_cell
}
else:
person = {
'Property ID': self.keys.get(prop_key, ''),
'Property_Name': prop_name_cell,
'Name': name_cell,
'Source': source_cell,
'Status': status_cell,
'Event Date': event_date_cell,
'Action': section_title_cell
}
processed_name = eagle.namer(name_cell)
person['First Name'] = processed_name[0]
person['Last Name'] = processed_name[1]
#person = {'Property_Name': prop_name_cell, 'Name': name_cell, 'Source': source_cell, 'Event Date': event_date_cell,'Action': section_title_cell}
#Add person dict to people list
people.append(person)
with open(self.output, 'wb') as out_file:
if self.args.raw == True:
writer = csv.DictWriter(out_file,
fieldnames=self.header_fields_raw)
writer.writeheader()
for person in people:
writer.writerow(person)
else:
writer = csv.DictWriter(out_file,
fieldnames=self.header_fields)
writer.writeheader()
for person in people:
writer.writerow(person)
def names_parse(self):
people = []
count = 0
for excel_file in self.excel_files:
print excel_file
count += 1
print count
workbook = xlrd.open_workbook(excel_file)
worksheet = workbook.sheet_by_index(0)
name_index = 0
event_date_index = 0
source_index = 0
status_index = 0
event_type_index = 0
home_phone_index = 0
office_phone_index = 0
start = False
end = False
prop_name_cell = worksheet.cell(1, 0).value
person = {}
for row_index in range(worksheet.nrows):
cell = worksheet.cell(row_index, 0).value
cell = cell.strip()
cell = cell.replace("\n", "")
if cell in self.headers:
start = True
header_row = worksheet.row_values(row_index, 0)
# Find the column index of the different header row names
for i, c in enumerate(header_row):
if "prospect" and "name" in c.lower():
name_index = i
elif "event" and "date" in c.lower():
event_date_index = i
elif "source" in c.lower():
source_index = i
elif "status" in c.lower():
status_index = i
elif "event" and "type" in c.lower():
event_type_index = i
elif "home" in c.lower() and "phone" in c.lower():
home_phone_index = i
elif "office" in c.lower() and "phone" in c.lower():
office_phone_index = i
elif "event" and "summary" in cell.lower():
end = True
elif end:
continue
elif start:
row = worksheet.row_values(row_index, 0)
name_cell = worksheet.cell(row_index, name_index).value
name_cell = name_cell.encode("utf-8")
event_date_cell = worksheet.cell(row_index, event_date_index).value
source_cell = worksheet.cell(row_index, source_index).value
status_cell = worksheet.cell(row_index, status_index).value
event_type_cell = worksheet.cell(row_index, event_type_index).value
home_phone_cell = worksheet.cell(row_index, home_phone_index).value
office_phone_cell = worksheet.cell(row_index, office_phone_index).value
if name_cell != "" and source_cell != "":
# Need to add prop_name_cell to prop_key conversion
prop_key = prop_name_cell
if self.args.raw == True:
person = {
"Property ID": self.keys.get(prop_key, ""),
"Property_Name": prop_name_cell,
"Name": name_cell,
"Source": source_cell,
"Status": status_cell,
"Event Date": event_date_cell,
"Event Type": event_type_cell,
"Home Phone": home_phone_cell,
"Office Phone": office_phone_cell,
}
else:
person = {
"Property ID": self.keys.get(prop_key, ""),
"Property_Name": prop_name_cell,
"Name": name_cell,
"Source": source_cell,
"Status": status_cell,
"Event Date": event_date_cell,
"Event Type": event_type_cell,
"Home Phone": home_phone_cell,
"Office Phone": office_phone_cell,
}
processed_name = eagle.namer(name_cell)
person["First Name"] = processed_name[0].encode("utf-8")
person["Last Name"] = processed_name[1].encode("utf-8")
# Add person dict to people list
people.append(person)
with open(self.output, "wb") as out_file:
if self.args.raw == True:
out_file.write(u"\ufeff".encode("utf8")) # BOM for Excel to open UTF-8 file properly
writer = csv.DictWriter(out_file, fieldnames=self.header_fields_raw)
writer.writeheader()
for person in people:
# print person
writer.writerow(person)
else:
out_file.write(u"\ufeff".encode("utf8")) # BOM for Excel to open UTF-8 file properly
writer = csv.DictWriter(out_file, fieldnames=self.header_fields)
writer.writeheader()
for person in people:
if self.args.filter == True:
status = person["Status"].lower()
if "resident" in status:
writer.writerow(person)
else:
writer.writerow(person)
def names_parse(self):
# header_fields = ["Property_Name", "Name", "Source"]
people = []
for excel_file in self.excel_files:
workbook = xlrd.open_workbook(excel_file)
worksheet = workbook.sheet_by_index(0)
name_index = 0
event_date_index = 0
source_index = 0
status_index = 0
start = False
end = False
prop_name_cell = ""
person = {}
for row_index in range(worksheet.nrows):
cell = worksheet.cell(row_index, 0).value
cell = cell.strip()
cell = cell.replace("\n", "")
if "property:" in cell.lower():
prop_name_cell = worksheet.cell(row_index, 0).value
elif cell in self.headers:
start = True
header_row = worksheet.row_values(row_index, 0)
# Find the column index of the different header row names
for i, c in enumerate(header_row):
if "name" in c.lower() and "agent" not in c.lower():
print c, i
name_index = i
# start = True
elif "event" in c.lower() and "date" in c.lower():
event_date_index = i
elif "source" in c.lower():
source_index = i
elif "status" in c.lower():
status_index = i
# The row with cell "Grand Total" is used as the flag to signal the end of name collecting.
elif "grand" in cell.lower() and "total" in cell.lower():
end = True
elif end:
continue
# Begin collecting names after getting past the header row
elif start:
if cell in self.section_titles:
section_title_cell = cell
name_cell = worksheet.cell(row_index, name_index).value
event_date_cell = worksheet.cell(row_index, event_date_index).value
source_cell = worksheet.cell(row_index, source_index).value
status_cell = worksheet.cell(row_index, status_index).value
if name_cell != "":
# writer.writerow([prop_name_cell, name_cell, source_cell])
prop_key = re.sub("\(\d*\)?", "", prop_name_cell).strip().lower()
prop_key = " ".join(prop_key.split())
if self.args.raw == True:
person = {
"Property ID": self.keys.get(prop_key, ""),
"Property_Name": prop_name_cell,
"Name": name_cell,
"Source": source_cell,
"Status": status_cell,
"Event Date": event_date_cell,
"Action": section_title_cell,
}
else:
person = {
"Property ID": self.keys.get(prop_key, ""),
"Property_Name": prop_name_cell,
"Name": name_cell,
"Source": source_cell,
"Status": status_cell,
"Event Date": event_date_cell,
"Action": section_title_cell,
}
processed_name = eagle.namer(name_cell)
person["First Name"] = processed_name[0]
person["Last Name"] = processed_name[1]
# person = {'Property_Name': prop_name_cell, 'Name': name_cell, 'Source': source_cell, 'Event Date': event_date_cell,'Action': section_title_cell}
# Add person dict to people list
people.append(person)
with open(self.output, "wb") as out_file:
if self.args.raw == True:
writer = csv.DictWriter(out_file, fieldnames=self.header_fields_raw)
writer.writeheader()
for person in people:
writer.writerow(person)
else:
writer = csv.DictWriter(out_file, fieldnames=self.header_fields)
writer.writeheader()
for person in people:
if self.args.filter == True:
status = person["Status"].lower()
if "resident" in status:
writer.writerow(person)
else:
writer.writerow(person)
def names_parse(self):
#header_fields = ["Property_Name", "Name", "Source"]
people = []
for excel_file in self.excel_files:
workbook = xlrd.open_workbook(excel_file)
worksheet = workbook.sheet_by_index(0)
name_index = 0
event_date_index = 0
source_index = 0
start = False
end = False
prop_name_cell = ""
person = {}
for row_index in range(worksheet.nrows):
cell = worksheet.cell(row_index, 0).value
cell = cell.strip()
cell = cell.replace('\n','')
if 'property:' in cell.lower():
prop_name_cell = worksheet.cell(row_index,0).value
elif cell in self.headers:
start = True
header_row = worksheet.row_values(row_index,0)
#Find the column index of the different header row names
for i, c in enumerate(header_row):
if 'name' in c.lower() and 'agent' not in c.lower():
print c, i
name_index = i
#start = True
elif 'event' in c.lower() and 'date' in c.lower():
event_date_index = i
elif 'source' in c.lower():
source_index = i
#The row with cell "Grand Total" is used as the flag to signal the end of name collecting.
elif 'grand' in cell.lower() and 'total' in cell.lower():
end = True
elif end:
continue
#Begin collecting names after getting past the header row
elif start:
if cell in self.section_titles:
section_title_cell = cell
name_cell = worksheet.cell(row_index, name_index).value
event_date_cell = worksheet.cell(row_index, event_date_index).value
source_cell = worksheet.cell(row_index, source_index).value
if name_cell != "":
#writer.writerow([prop_name_cell, name_cell, source_cell])
if self.args.raw == True:
person = {'Property_Name': prop_name_cell, 'Name': name_cell, 'Source': source_cell, 'Event Date': event_date_cell,'Action': section_title_cell}
else:
person = {'Property_Name': prop_name_cell, 'Name': name_cell, 'Source': source_cell, 'Event Date': event_date_cell,'Action': section_title_cell}
processed_name = eagle.namer(name_cell)
person['First Name'] = processed_name[0]
person['Last Name'] = processed_name[1]
#person = {'Property_Name': prop_name_cell, 'Name': name_cell, 'Source': source_cell, 'Event Date': event_date_cell,'Action': section_title_cell}
#Add person dict to people list
people.append(person)
with open(self.output, 'wb') as out_file:
if self.args.raw == True:
writer = csv.DictWriter(out_file, fieldnames=self.header_fields_raw)
writer.writeheader()
for person in people:
writer.writerow(person)
else:
writer = csv.DictWriter(out_file, fieldnames=self.header_fields)
writer.writeheader()
for person in people:
writer.writerow(person)
def names_parse(self):
people = []
count = 0
for excel_file in self.excel_files:
print excel_file
count += 1
print count
workbook = xlrd.open_workbook(excel_file)
worksheet = workbook.sheet_by_index(0)
name_index = 0
event_date_index = 0
source_index = 0
status_index = 0
event_type_index = 0
home_phone_index = 0
office_phone_index = 0
start = False
end = False
prop_name_cell = worksheet.cell(1, 0).value
person = {}
for row_index in range(worksheet.nrows):
cell = worksheet.cell(row_index, 0).value
cell = cell.strip()
cell = cell.replace('\n', '')
if cell in self.headers:
start = True
header_row = worksheet.row_values(row_index, 0)
#Find the column index of the different header row names
for i, c in enumerate(header_row):
if 'prospect' and 'name' in c.lower():
name_index = i
elif 'event' and 'date' in c.lower():
event_date_index = i
elif 'source' in c.lower():
source_index = i
elif 'status' in c.lower():
status_index = i
elif 'event' and 'type' in c.lower():
event_type_index = i
elif 'home' in c.lower() and 'phone' in c.lower():
home_phone_index = i
elif 'office' in c.lower() and 'phone' in c.lower():
office_phone_index = i
elif 'event' and 'summary' in cell.lower():
end = True
elif end:
continue
elif start:
row = worksheet.row_values(row_index, 0)
name_cell = worksheet.cell(row_index, name_index).value
name_cell = name_cell.encode('utf-8')
event_date_cell = worksheet.cell(row_index,
event_date_index).value
source_cell = worksheet.cell(row_index, source_index).value
status_cell = worksheet.cell(row_index, status_index).value
event_type_cell = worksheet.cell(row_index,
event_type_index).value
home_phone_cell = worksheet.cell(row_index,
home_phone_index).value
office_phone_cell = worksheet.cell(
row_index, office_phone_index).value
if name_cell != "" and source_cell != "":
#Need to add prop_name_cell to prop_key conversion
prop_key = prop_name_cell
if self.args.raw == True:
person = {
'Property ID': self.keys.get(prop_key, ''),
'Property_Name': prop_name_cell,
'Name': name_cell,
'Source': source_cell,
'Status': status_cell,
'Event Date': event_date_cell,
'Event Type': event_type_cell,
'Home Phone': home_phone_cell,
'Office Phone': office_phone_cell
}
else:
person = {
'Property ID': self.keys.get(prop_key, ''),
'Property_Name': prop_name_cell,
'Name': name_cell,
'Source': source_cell,
'Status': status_cell,
'Event Date': event_date_cell,
'Event Type': event_type_cell,
'Home Phone': home_phone_cell,
'Office Phone': office_phone_cell
}
processed_name = eagle.namer(name_cell)
person['First Name'] = processed_name[0].encode(
'utf-8')
person['Last Name'] = processed_name[1].encode(
'utf-8')
#Add person dict to people list
people.append(person)
with open(self.output, 'wb') as out_file:
if self.args.raw == True:
out_file.write(u'\ufeff'.encode(
'utf8')) #BOM for Excel to open UTF-8 file properly
writer = csv.DictWriter(out_file,
fieldnames=self.header_fields_raw)
writer.writeheader()
for person in people:
#print person
writer.writerow(person)
else:
out_file.write(u'\ufeff'.encode(
'utf8')) #BOM for Excel to open UTF-8 file properly
writer = csv.DictWriter(out_file,
fieldnames=self.header_fields)
writer.writeheader()
for person in people:
if self.args.filter == True:
status = person['Status'].lower()
if 'resident' in status:
writer.writerow(person)
else:
writer.writerow(person)
