csv — 操作 csv 文件的 API

读

# csv_reader.py
import csv
import sys

with open(sys.argv[1], 'rt') as f:
    reader = csv.reader(f)
    for row in reader:
        print(row)

写

# csv_writer.py
import csv
import sys

unicode_chars = 'å∫ç'

with open(sys.argv[1], 'wt') as f:
    writer = csv.writer(f)
    writer.writerow(('Title 1', 'Title 2', 'Title 3', 'Title 4'))
    for i in range(3):
        row = (
            i + 1,
            chr(ord('a') + i),
            '08/{:02d}/07'.format(i + 1),
            unicode_chars[i],
        )
        writer.writerow(row)

print(open(sys.argv[1], 'rt').read())

方言

# csv_list_dialects.py
import csv

print(csv.list_dialects())

创建方言

# csv_dialect.py
import csv

csv.register_dialect('pipes', delimiter='|')

with open('testdata.pipes', 'r') as f:
    reader = csv.reader(f, dialect='pipes')
    for row in reader:
        print(row)

方言参数

# csv_dialect_variations.py
import csv
import sys

csv.register_dialect('escaped',
                     escapechar='\\',
                     doublequote=False,
                     quoting=csv.QUOTE_NONE,
                     )
csv.register_dialect('singlequote',
                     quotechar="'",
                     quoting=csv.QUOTE_ALL,
                     )

quoting_modes = {
    getattr(csv, n): n
    for n in dir(csv)
    if n.startswith('QUOTE_')
}

TEMPLATE = '''\
Dialect: "{name}"

  delimiter   = {dl!r:<6}    skipinitialspace = {si!r}
  doublequote = {dq!r:<6}    quoting          = {qu}
  quotechar   = {qc!r:<6}    lineterminator   = {lt!r}
  escapechar  = {ec!r:<6}
'''

for name in sorted(csv.list_dialects()):
    dialect = csv.get_dialect(name)

    print(TEMPLATE.format(
        name=name,
        dl=dialect.delimiter,
        si=dialect.skipinitialspace,
        dq=dialect.doublequote,
        qu=quoting_modes[dialect.quoting],
        qc=dialect.quotechar,
        lt=dialect.lineterminator,
        ec=dialect.escapechar,
    ))

    writer = csv.writer(sys.stdout, dialect=dialect)
    writer.writerow(
        ('col1', 1, '10/01/2010',
         'Special chars: " \' {} to parse'.format(
             dialect.delimiter))
    )
    print()

自动检测方言

# csv_dialect_sniffer.py
import csv
from io import StringIO
import textwrap

csv.register_dialect('escaped',
                     escapechar='\\',
                     doublequote=False,
                     quoting=csv.QUOTE_NONE)
csv.register_dialect('singlequote',
                     quotechar="'",
                     quoting=csv.QUOTE_ALL)

# Generate sample data for all known dialects
samples = []
for name in sorted(csv.list_dialects()):
    buffer = StringIO()
    dialect = csv.get_dialect(name)
    writer = csv.writer(buffer, dialect=dialect)
    writer.writerow(
        ('col1', 1, '10/01/2010',
         'Special chars " \' {} to parse'.format(
             dialect.delimiter))
    )
    samples.append((name, dialect, buffer.getvalue()))

# Guess the dialect for a given sample, and then use the results
# to parse the data.
sniffer = csv.Sniffer()
for name, expected, sample in samples:
    print('Dialect: "{}"'.format(name))
    print('In: {}'.format(sample.rstrip()))
    dialect = sniffer.sniff(sample, delimiters=',\t')
    reader = csv.reader(StringIO(sample), dialect=dialect)
    print('Parsed:\n  {}\n'.format(
          '\n  '.join(repr(r) for r in next(reader))))

使用字段名

# csv_dictreader.py
import csv
import sys

with open(sys.argv[1], 'rt') as f:
    reader = csv.DictReader(f)
    for row in reader:
        print(row)

# csv_dictwriter.py
import csv
import sys

fieldnames = ('Title 1', 'Title 2', 'Title 3', 'Title 4')
headers = {
    n: n
    for n in fieldnames
}
unicode_chars = 'å∫ç'

with open(sys.argv[1], 'wt') as f:

    writer = csv.DictWriter(f, fieldnames=fieldnames)
    writer.writeheader()

    for i in range(3):
        writer.writerow({
            'Title 1': i + 1,
            'Title 2': chr(ord('a') + i),
            'Title 3': '08/{:02d}/07'.format(i + 1),
            'Title 4': unicode_chars[i],
        })

print(open(sys.argv[1], 'rt').read())