Python:如何解析位置？

Question

没有任何包含多个列的标题:

john, 1, orange, chicken
mary, 7, purple, hamburger
joey, 2, yellow, chicken

Answer 1

为此你不需要csv，只需要简单的python。该解决方案在内存方面非常高效，因为它只是逐行操作。

with open('temp.csv', 'r') as fin, open('temp2.csv', 'w') as fout:
    for row in fin:
        if row.split()[3] == 'chicken':
            fout.write(row)

这比需要读取并在内存中存储所有将写入文件的数据的列表理解更有效。

时间

# Create sample data file of 30k rows, 2/3rds with 'chicken'.
with open('temp.csv', 'w') as f:
    for _ in range(10000):
        f.write("john,1,orange,chicken\n")
        f.write("mary,7,purple,hamburger\n")
        f.write("joey,2,yellow,chicken\n")

%%timeit
with open('temp.csv', 'r') as fin, open('temp2.csv', 'w') as fout:
    for row in fin:
        if row.split()[3] == 'chicken':
            fout.write(row)
# 10 loops, best of 3: 41 ms per loop

%%timeit
with open('temp.csv') as old_file, open('temp3.csv', 'w') as new_file:
    cr = csv.reader(old_file)
    cw = csv.writer(new_file)
    cw.writerows([r for r in cr if r[3] == 'chicken'])
# 10 loops, best of 3: 58.7 ms per loop

# Turn previous list comprehension into a generator.
%%timeit
with open('temp.csv') as old_file, open('temp3.csv', 'w') as new_file:
    cr = csv.reader(old_file)
    cw = csv.writer(new_file)
    cw.writerows((r for r in cr if r[3] == 'chicken'))
# 10 loops, best of 3: 66.5 ms per loop

with open('temp.csv') as input_file, open('temp4.csv', 'w', newline='') as output_file:
    reader = csv.reader(input_file, delimiter=',')
    writer = csv.writer(output_file, delimiter=',')
    writer.writerows(filter(lambda x: x[3].strip() != 'chcicken', reader))
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-41-072d37a3ff92> in <module>()
----> 1 with open('temp.csv') as input_file, open('temp4.csv', 'w', newline='') as output_file:
      2     reader = csv.reader(input_file, delimiter=',')
      3     writer = csv.writer(output_file, delimiter=',')
      4     writer.writerows(filter(lambda x: x[3].strip() != 'chcicken', reader))

TypeError: 'newline' is an invalid keyword argument for this function