def parseFile(writer, file):
print("Reading file " + file)
handler = pyUtils.readLocalFile(file)
year = pyUtils.getFileNameWithoutExtension(file)[pyUtils.getLastIndexOf(file, '-') + 1:]
# print(handler)
soup = Soup(handler)
rows = soup.findAll('row')
i = 0
headers_row_num = -1
found_headers = False
for row in rows:
print(row)
csv_row = []
styleId = row.get('ss:styleid', '')
if found_headers is False:
if styleId == 's5':
found_headers = True
headers_row_num = i
cells = row.findAll('data')
for cell in cells:
csv_row.append(pyUtils.returnNormalText(cell.contents[0]))
writer.writerow(csv_row)
else:
autofitheight = row.get('ss:AutoFitHeight'.lower(), '')
# print("autofitheight: " + autofitheight)
if autofitheight == "0":
print("autoheight is 0")
cells = row.findAll('cell')
for column in cells:
dataType = column.data['ss:Type'.lower()]
if len(column.data.contents) == 0:
if dataType.lower() == 'number':
csv_row.append(-100)
else:
csv_row.append('')
else:
if dataType.lower() == 'number':
csv_row.append(column.data.contents[0].replace(',', '.'))
else:
content = column.data.contents[0]
csv_row.append(pyUtils.returnNormalText(content))
writer.writerow(csv_row)
# print("Row: " + str(i+1) + " " + '.'.join(csv_row))
i = i + 1
def parseFile(file):
print("Reading file " + file)
handler = pyUtils.readLocalFile(file)
year = pyUtils.getFileNameWithoutExtension(file)[pyUtils.getLastIndexOf(file, '-') + 1:]
# print(handler)
soup = Soup(handler)
rows = soup.findAll('row')
headers = []
row_num = 0
headers_row_num = -1
found_headers = False
for row in rows:
autofitheight = row.get('ss:AutoFitHeight'.lower(), '')
# print(row)
csv_row = []
styleId = row.get('ss:styleid', '')
if found_headers is False:
if styleId == 's5' and autofitheight == '0':
found_headers = True
# headers_row_num = i
cells = row.findAll('data')
for i in range(0, len(cells)):
cell = cells[i]
# for cell in cells:
# csv_row.append(pyUtils.returnNormalText(cell.contents[0]))
headers.append(pyUtils.returnNormalText(cell.contents[0]))
if cell.contents[0] == key_field_name:
key_field_column = i
if cell.contents[0] == country_field_name:
country_field_column = i
# writer.writerow(csv_row)
else:
# print("autofitheight: " + autofitheight)
if autofitheight == "0":
# print("autoheight is 0")
school = {}
cells = row.findAll('cell')
country = ''
# for column in cells:
for i in range(0, len(cells)):
if i == key_field_column:
continue
column = cells[i]
if i == country_field_column:
country = pyUtils.returnNormalText(column.data.contents[0])
continue
dataType = column.data['ss:Type'.lower()]
if len(column.data.contents) == 0:
if dataType.lower() == 'number':
# csv_row.append(-100)
school[headers[i]] = -100
else:
# csv_row.append('')
school[headers[i]] = ''
else:
if dataType.lower() == 'number':
# csv_row.append(column.data.contents[0].replace(',', '.'))
school[headers[i]] = float(column.data.contents[0].replace(',', '.'))
else:
content = column.data.contents[0]
# csv_row.append(pyUtils.returnNormalText(content))
school[headers[i]] = pyUtils.returnNormalText(content)
# writer.writerow(csv_row)
addSchoolData(cells[key_field_column].data.contents[0], year, country, school)
# print("Row num: " + str(row_num))
row_num = row_num + 1