Python strp csv行示例。向我展示您将如何处理此问题

想象一下，如果在CSV中有数千行这样的内容

maps.google.co.ke   GET /maps?f=q&source=s_q&hl=en&geocode=&q=Africa&aq=0&sll=1.845384,32.871094&sspn=18.498214,20.786133&ie=UTF8&hq=&hnear=Africa&ll=-8.783195,34.508523&spn=69.476093,83.144531&z=3&output=embed HTTP/1.1 1.29646542461634E+015   168722060   1606370688  ?   ken

#! /usr/bin/env python
# Split the CSV and eliminate text before GET/ and text after HTTP1.1 and reorganize in simple sheet . 

import csv

try:
    dremel = csv.reader(open('dremel-columns.csv', 'rb'), delimiter=' ', quotechar='|')

except IOError:
    print 'CSV Error'


dremel_list= list(dremel)
dremel_l = []
cw = csv.writer(open("out.txt", "wb"))

#print dremel_list

for l in dremel_list:
    if l[1:-1]:
        l_shout = l[1:-1]
        #print l_shout
        cw.writerow(l_shout)
        #print "".join(l_shout)

        #cw.writerow("".join(l_shout)) 

#! /usr/bin/env python
# Split the CSV and eliminate text before GET/ and text after HTTP1.1 and reorganize in simple sheet . 

import csv

try:
    dremel = csv.reader(open('dremel-columns.csv', 'rb'), delimiter=' ', quotechar='|')

except IOError:
    print 'CSV Error'


dremel_list= list(dremel)
dremel_l = []
cw = csv.writer(open("out.txt", "wb"))

#print dremel_list

for l in dremel_list:
    if l[1:-1]:
        l_shout = l[1:-1]
        #print l_shout
        cw.writerow(l_shout)
        #print "".join(l_shout)

        #cw.writerow("".join(l_shout)) 

---

我认为这段代码足够做这项工作

#! /usr/bin/env python
# Split the CSV and eliminate text before GET/ and text after HTTP1.1 and reorganize in simple sheet . 

import csv

try:
    dremel = csv.reader(open('dremel-columns.csv', 'rb'), delimiter=' ', quotechar='|')

except IOError:
    print 'CSV Error'


dremel_list= list(dremel)
dremel_l = []
cw = csv.writer(open("out.txt", "wb"))

#print dremel_list

for l in dremel_list:
    if l[1:-1]:
        l_shout = l[1:-1]
        #print l_shout
        cw.writerow(l_shout)
        #print "".join(l_shout)

        #cw.writerow("".join(l_shout)) 

import re

pat = re.compile('GET.*?HTTP1.1')

with open('dremel-columns.csv', 'rb') as f_in, open("out.txt", "wb") as g_out:
    g_out.write(u + '\n' for u in pat.finditer(f_in.read()))

不是吗

#! /usr/bin/env python
# Split the CSV and eliminate text before GET/ and text after HTTP1.1 and reorganize in simple sheet . 

import csv

try:
    dremel = csv.reader(open('dremel-columns.csv', 'rb'), delimiter=' ', quotechar='|')

except IOError:
    print 'CSV Error'


dremel_list= list(dremel)
dremel_l = []
cw = csv.writer(open("out.txt", "wb"))

#print dremel_list

for l in dremel_list:
    if l[1:-1]:
        l_shout = l[1:-1]
        #print l_shout
        cw.writerow(l_shout)
        #print "".join(l_shout)

        #cw.writerow("".join(l_shout)) 

编辑：对不起，我忘了“\n”

#! /usr/bin/env python
# Split the CSV and eliminate text before GET/ and text after HTTP1.1 and reorganize in simple sheet . 

import csv

try:
    dremel = csv.reader(open('dremel-columns.csv', 'rb'), delimiter=' ', quotechar='|')

except IOError:
    print 'CSV Error'


dremel_list= list(dremel)
dremel_l = []
cw = csv.writer(open("out.txt", "wb"))

#print dremel_list

for l in dremel_list:
    if l[1:-1]:
        l_shout = l[1:-1]
        #print l_shout
        cw.writerow(l_shout)
        #print "".join(l_shout)

        #cw.writerow("".join(l_shout)) 

#! /usr/bin/env python
# Split the CSV and eliminate text before GET/ and text after HTTP1.1 and reorganize in simple sheet . 

import csv

try:
    dremel = csv.reader(open('dremel-columns.csv', 'rb'), delimiter=' ', quotechar='|')

except IOError:
    print 'CSV Error'


dremel_list= list(dremel)
dremel_l = []
cw = csv.writer(open("out.txt", "wb"))

#print dremel_list

for l in dremel_list:
    if l[1:-1]:
        l_shout = l[1:-1]
        #print l_shout
        cw.writerow(l_shout)
        #print "".join(l_shout)

        #cw.writerow("".join(l_shout)) 

编辑2：不，它不起作用

#! /usr/bin/env python
# Split the CSV and eliminate text before GET/ and text after HTTP1.1 and reorganize in simple sheet . 

import csv

try:
    dremel = csv.reader(open('dremel-columns.csv', 'rb'), delimiter=' ', quotechar='|')

except IOError:
    print 'CSV Error'


dremel_list= list(dremel)
dremel_l = []
cw = csv.writer(open("out.txt", "wb"))

#print dremel_list

for l in dremel_list:
    if l[1:-1]:
        l_shout = l[1:-1]
        #print l_shout
        cw.writerow(l_shout)
        #print "".join(l_shout)

        #cw.writerow("".join(l_shout)) 

g_out.write(u for u in pat.finditer(f_in.read()))
TypeError: must be string or buffer, not generator

这个有效

#! /usr/bin/env python
# Split the CSV and eliminate text before GET/ and text after HTTP1.1 and reorganize in simple sheet . 

import csv

try:
    dremel = csv.reader(open('dremel-columns.csv', 'rb'), delimiter=' ', quotechar='|')

except IOError:
    print 'CSV Error'


dremel_list= list(dremel)
dremel_l = []
cw = csv.writer(open("out.txt", "wb"))

#print dremel_list

for l in dremel_list:
    if l[1:-1]:
        l_shout = l[1:-1]
        #print l_shout
        cw.writerow(l_shout)
        #print "".join(l_shout)

        #cw.writerow("".join(l_shout)) 

import re

pat = re.compile('GET.*?HTTP1.1')

with open('dremel-columns.csv', 'rb') as f_in, open("out.txt", "wb") as g_out:
    for u in pat.finditer(f_in.read()):
        g_out.write(u)

或者，如果文件很大：

#! /usr/bin/env python
# Split the CSV and eliminate text before GET/ and text after HTTP1.1 and reorganize in simple sheet . 

import csv

try:
    dremel = csv.reader(open('dremel-columns.csv', 'rb'), delimiter=' ', quotechar='|')

except IOError:
    print 'CSV Error'


dremel_list= list(dremel)
dremel_l = []
cw = csv.writer(open("out.txt", "wb"))

#print dremel_list

for l in dremel_list:
    if l[1:-1]:
        l_shout = l[1:-1]
        #print l_shout
        cw.writerow(l_shout)
        #print "".join(l_shout)

        #cw.writerow("".join(l_shout)) 

import re

pat = re.compile('GET.*?HTTP1.1')

with open('dremel-columns.txt', 'rb') as f_in, open("out.txt", "wb") as g_out:
    for line in f_in:
        g_out.write(pat.search(line).group())

---

只是一个思维练习——每天至少一次练习想象一些特定的东西！我想象着我会问谁在雇用我，他们希望我用这样一个有数千行的csv做什么。这是Qn？拆分CSV文件行，删除GET/之前的文本和HTTP1.1之后的文本，并在简单工作表中重新组织。向我展示您的代码版本，以及如何执行此操作。。