python腳本語言作為轉換數據的工具示例分析

python腳本語言作為轉換數據的工具示例分析，很多新手對此不是很清楚，為了幫助大家解決這個難題，下面小編將為大家詳細講解，有這方面需求的人可以來學習下，希望你能有所收獲。

      都說python是解釋形語言，意思是讀取一行執行一行，現在就有一段python程序擺在面前，其功能是“將一個csv文件名以及按文件中的內容轉換成多個以內容為目錄的linux下目錄結構”； 這段話應該比較的模型化，用一個具體的例子來說會容易理解點，這里就假設有這樣的一個小需求：現有一個壓縮文件 JiangSu-1949-10-01-HumanScience.csv.gz，該壓縮文件包含了江蘇省1949年10月1日前建立的人文科學專業大學的詳細名單，需要轉換為一組文件夾，每個文件夾單獨存放從簽署大學總錄中包含的一個大學詳細信息。（注：
以下僅為實現該小需求的示例python， 參數文件為 JiangSu-1949-10-01-HumanScience.csv.gz）

#!/usr/bin/python<br/>import csv, gzip, os, sys, re<br/>def ResolveUnivercity(TotalUniversities, pattern):<br/>SpecifiedUnivercity = pattern.search(TotalUniversities)

if SpecifiedUnivercity is None:
return None
return SpecifiedUnivercity.groups()
def TransformData(TotalUniversities, RootUnivercity_Path, pattern):
SpecifiedUniversity = ResolveUnivercity(TotalUniversities, pattern)
if SpecifiedUniversity is None:
print 'Cannot resolved  TotalUniversities file'
return 1
else:
print 'UniversityName: [%s] Born: [%s-%s-%s] Area: [%s]' % SpecifiedUniversity
if not SpecifiedUniversity[4] in ["NatureScience", "HumanScience"]:
print "system only analyze Nature or Human Science"
return 1
if RootUnivercity_Path is None:
RootUnivercity_Path = '%s' % SpecifiedUniversity[0]
gfile = gzip.open(TotalUniversities, "rb")
rownum = 0
HasNext = False

SpecifiedUnivercity_Content = {}
SpecifiedUnivercity_DetailContent = None
for row in csv.reader(gfile):
if rownum == 0:
header = row
else:

SpecifiedUniversity_Name = row[0]
 if len(SpecifiedUniversity_Name) > 0:
HasNext = True

if SpecifiedUnivercity_Content.has_key(SpecifiedUniversity_Name):
SpecifiedUnivercity_DetailContent = SpecifiedUnivercity_Content[SpecifiedUniversity_Name][1]

else:
rownum = 0
# create new file
SpecifiedUniversity_File = '%s_%s_%s.csv' % (SpecifiedUniversity[0], SpecifiedUniversity_Name, SpecifiedUniversity[2])

AbsolutePath = os.path.join(RootUnivercity_Path, SpecifiedUniversity_Name)
AbsolutePathName = os.path.join(AbsolutePath, SpecifiedUniversity_File)

if not os.path.exists(AbsolutePath):
os.makedirs(AbsolutePath, 0777)
outfile = open(AbsolutePathName, 'wb')

SpecifiedUnivercity_DetailContent = csv.writer(outfile, Token=',')
# insert into  SpecifiedUniversity
SpecifiedUnivercity_Content[SpecifiedUniversity_Name] = [outfile, SpecifiedUnivercity_DetailContent, False]
else:
HasNext = False

if SpecifiedUnivercity_DetailContent is not None:
SpecifiedUnivercity_DetailContent.writerow(row)
else:
print "row %d has no owner file" % rownum
rownum += 1
gfile.close()
for key in SpecifiedUnivercity_Content.keys():
SpecifiedUnivercity_Content[key][1].close()
SpecifiedUnivercity_Content[key][0].close()

if __name__ == "__main__":
#JiangSu-1949-10-01-HumanScience.csv.gz
ResolvedSpecofiedUnivercity = re.compile(r'(/w{2,})-(/d{4})-(/d{2})-(/d{2})-(/w{1,})/.')

for file in sys.argv[1:]:
TransformData(file, None, ResolvedSpecofiedUnivercity)

看完上述內容是否對您有幫助呢？如果還想對相關知識有進一步的了解或閱讀更多相關文章，請關注億速云行業資訊頻道，感謝您對億速云的支持。