, .
, data_.pop() .
, .
csv .
.
, , ,
, , , .
import csv
import os
class StreamCSV:
def __init__(self, header_file_name, body_file_name):
self.header_file_name = header_file_name
self.fbody = open(body_file_name, 'a', newline='', encoding='utf-8')
self.csv_body = csv.writer(self.fbody)
def add_item(self, item):
if os.path.exists(self.header_file_name):
with open(self.header_file_name, 'r', newline='', encoding='utf-8') as fobj:
reader = csv.reader(fobj)
try:
current_header = next(reader)
except StopIteration:
current_header = []
else:
current_header = []
header_set = set(current_header)
for key in item:
if key not in header_set:
current_header.append(key)
if len(header_set) < len(current_header):
with open(self.header_file_name, 'w', newline='', encoding='utf-8') as fobj:
writer = csv.writer(fobj)
writer.writerow(current_header)
item_data = [item.get(head, '') for head in current_header]
self.csv_body.writerow(item_data)
self.fbody.flush()
if __name__ == '__main__':
data_ = [
{
'a': '1',
'b': '2',
'c': '3',
},
{
'a': '6',
'd': '1',
'b': '3',
},
{
'c': '2',
'e': '1',
'f': '9',
}
]
def show_saved(file_names):
for name in file_names:
with open(name) as fobj:
print(name)
print(fobj.read())
header_file_name, body_file_name = 'header.csv', 'body.csv'
stream_writer = StreamCSV(header_file_name, body_file_name)
for x in range(1, 4):
print('step:', x)
stream_writer.add_item(data_.pop())
show_saved([header_file_name, body_file_name])
, :
step: 1
header.csv
c,e,f
body.csv
2,1,9
step: 2
header.csv
c,e,f,a,d,b
body.csv
2,1,9
,,,6,1,3
step: 3
header.csv
c,e,f,a,d,b
body.csv
2,1,9
,,,6,1,3
3,,,1,,2
, , .
def merge_header_body(header_file_name, body_file_name, out_file_name):
with open(header_file_name, 'r', newline='', encoding='utf-8') as fobj:
reader = csv.reader(fobj)
header = next(reader)
with open(out_file_name, 'w', newline='', encoding='utf-8') as fobj_out, \
open(body_file_name, 'r', newline='', encoding='utf-8') as fobj_in:
reader = csv.reader(fobj_in)
writer = csv.writer(fobj_out)
writer.writerow(header)
target_length = len(header)
for row in reader:
diff = target_length - len(row)
row.extend([''] * diff)
writer.writerow(row)
out_file_name = 'merged.csv'
merge_header_body(header_file_name, body_file_name, out_file_name)
merged.csv:
c,e,f,a,d,b
2,1,9,,,
,,,6,1,3
3,,,1,,2
, .
, , :
for x in range(1, 4):
print('step:', x)
stream_writer.add_item(data_.pop())
show_saved([header_file_name, body_file_name])
:
step: 1
header.csv
c,e,f,a,d,b
body.csv
2,1,9
,,,6,1,3
3,,,1,,2
2,1,9,,,
step: 2
header.csv
c,e,f,a,d,b
body.csv
2,1,9
,,,6,1,3
3,,,1,,2
2,1,9,,,
,,,6,1,3
step: 3
header.csv
c,e,f,a,d,b
body.csv
2,1,9
,,,6,1,3
3,,,1,,2
2,1,9,,,
,,,6,1,3
3,,,1,,2