从 Zip 文件中读取 CSV

Question

我有一个 zip 文件目录（大约 10,000 个小文件），每个目录中都有一个 CSV 文件，我正在尝试读取并拆分为多个不同的 CSV 文件。

我设法编写代码将 CSV 文件从 CSV 目录中拆分出来，如下所示，它读取 CSV 的第一个属性，并根据将其写入相关 CSV 的内容。

import csv
import os
import sys
import re
import glob

reader = csv.reader(open("C:/Projects/test.csv", "rb"), delimiter=',', quotechar='"')
write10 = csv.writer(open('ouput10.csv', 'w'), delimiter=',', lineterminator='\n', quotechar='"', quoting=csv.QUOTE_NONNUMERIC)
write15 = csv.writer(open('ouput15.csv', 'w'), delimiter=',', lineterminator='\n', quotechar='"', quoting=csv.QUOTE_NONNUMERIC)


headings10=["RECORD_IDENTIFIER","CUSTODIAN_NAME","LOCAL_CUSTODIAN_NAME","PROCESS_DATE","VOLUME_NUMBER","ENTRY_DATE","TIME_STAMP","VERSION","FILE_TYPE"]
write10.writerow(headings10)

headings15=["RECORD_IDENTIFIER","CHANGE_TYPE","PRO_ORDER","USRN","STREET_DESCRIPTION","LOCALITY_NAME","TOWN_NAME","ADMINSTRATIVE_AREA","LANGUAGE"]
write15.writerow(headings15)


for row in reader:
    type = row[0]
    if "10" in type:        
        write10.writerow(row)
    elif "15" in type:
        write15.writerow(row)

所以我现在尝试读取 Zip 文件，而不是浪费时间先提取它们。

这是我在学习了尽可能多的教程之后所拥有的

import glob
import os
import csv
import zipfile
import StringIO

for name in glob.glob('C:/Projects/abase/*.zip'):
    base = os.path.basename(name)
    filename = os.path.splitext(base)[0]


datadirectory = 'C:/Projects/abase/'
dataFile = filename
archive = '.'.join([dataFile, 'zip'])
fullpath = ''.join([datadirectory, archive])
csv = '.'.join([dataFile, 'csv'])


filehandle = open(fullpath, 'rb')
zfile = zipfile.ZipFile(filehandle)
data = StringIO.StringIO(zfile.read(csv))
reader = csv.reader(data)

for row in reader:
    print row

但是会抛出错误

AttributeError: 'str' 对象没有属性 'reader'

希望有人能告诉我如何更改我的 CSV 读取代码以读取 Zip 文件。

非常感谢

提姆

Answer 1

简单的修复。您正在使用本地 csv 变量覆盖 csv 模块。只需更改该变量的名称：

import glob
import os
import csv
import zipfile
import StringIO

for name in glob.glob('C:/Projects/abase/*.zip'):
    base = os.path.basename(name)
    filename = os.path.splitext(base)[0]


    datadirectory = 'C:/Projects/abase/'
    dataFile = filename
    archive = '.'.join([dataFile, 'zip'])
    fullpath = ''.join([datadirectory, archive])
    csv_file = '.'.join([dataFile, 'csv']) #all fixed


    filehandle = open(fullpath, 'rb')
    zfile = zipfile.ZipFile(filehandle)
    data = StringIO.StringIO(zfile.read(csv_file)) #don't forget this line!
    reader = csv.reader(data)

    for row in reader:
        print row