extract things from excel files.

#coding=utf-8
#!/usr/bin/python
import os
from glob import glob
import re
import xlrd

fo = open("foo.csv", "a+")
    
def isDigit(my_str):
    try:
        float(my_str)
    except ValueError:
        return False
    return True

def china(file_name, onlyname):
    print(file_name)
    data = xlrd.open_workbook(file_name)
    table = data.sheets()[0]
    #file = open(file_name)
    ratio=[]
    price=[]
    d3=[]
    d6=[]
    nrows = table.nrows
    #for line in file:
        #l1=line.split("\t")
        #if len(l1)>14 :
    l1=['' for i in range(20)]    
    for i in range(nrows ):
        l1[3]=table.row(i)[3].value
        if isDigit(l1[3]):
            print(l1[3])
            d3.append(float(l1[3]))
        l1[5]=table.row(i)[4].value
        if isDigit(l1[5]):
            print(l1[5])
            d6.append(float(l1[5]))
        l1[7]=table.row(i)[5].value
        if isDigit(l1[7]):
            print(l1[7])
            ratio.append(float(l1[7]))
        l1[16]=table.row(i)[13].value
        if isDigit(l1[16]):
            print(l1[16])
            price.append(float(l1[16]))
    nd3=0
    for f1 in d3:
        if f1>=13:
            nd3 += 1
    print("nd3:"+str(nd3))
    nd6=0
    for f6 in d6:
        if f6>=16:
            nd6 += 1
    print("nd6:"+str(nd6))
    r=[0 for i in range(16)]
    for r1 in ratio:
        if r1>=9.9:
            r[0] += 1
        if r1<=-9.9:
            r[1] += 1
        if r1>=8:
            r[2] += 1
        if r1<=-8:
            r[3] += 1
        if r1>=7:
            r[4] += 1
        if r1<=-7:
            r[5] += 1
        if r1>=6:
            r[6] += 1
        if r1<=-6:
            r[7] += 1
        if r1>=5:
            r[8] += 1
        if r1<=-5:
            r[9] += 1
        if r1>=4:
            r[10] += 1
        if r1<=-4:
            r[11] += 1
        if r1>=3:
            r[12] += 1
        if r1<=-3:
            r[13] += 1
        if r1>=2:
            r[14] += 1
        if r1<=-2:
            r[15] += 1
    print(r)
    print("price all:"+str(sum(price)))
    # price.sort()
    # flog = open("2.log","w")
    ##print(price)
    # d6.sort()
    # print >> flog,d6;
    # flog.close
    fo = open("foo.csv", "a")
    fo.write(onlyname+','+str(nd3)+','+str(nd6)+','+str(r[0])+','+str(r[1])+','+str(r[2])+','+str(r[3])+',,,,,'+str(r[4])+','+str(r[5])+','+str(r[6])+','+str(r[7])+','+str(r[8])+','+str(r[9])+','+str(r[10])+','+str(r[11])+','+str(r[12])+','+str(r[13])+','+str(r[14])+','+str(r[15])+','+str(sum(price))+'\n')
    fo.close()

def hk(file_name, onlyname):
    print(file_name)
    data = xlrd.open_workbook(file_name)
    table = data.sheets()[0]
    #file = open(file_name)
    ratio=[]
    price=[]
    nrows = table.nrows
    #for line in file:
        #l1=line.split("\t")
        #if len(l1)>14 :
    l1=['' for i in range(20)]    
    for i in range(nrows ):
        l1[7]=table.row(i)[4].value
        if isDigit(l1[7]):
            print(l1[7])
            ratio.append(float(l1[7]))
        l1[16]=table.row(i)[3].value
        if isDigit(l1[16]):
            print(l1[16])
            price.append(float(l1[16]))
    r=[0 for i in range(16)]
    for r1 in ratio:
        if r1>=9.9:
            r[0] += 1
        if r1<=-9.9:
            r[1] += 1
        if r1>=8:
            r[2] += 1
        if r1<=-8:
            r[3] += 1
        if r1>=7:
            r[4] += 1
        if r1<=-7:
            r[5] += 1
        if r1>=6:
            r[6] += 1
        if r1<=-6:
            r[7] += 1
        if r1>=5:
            r[8] += 1
        if r1<=-5:
            r[9] += 1
        if r1>=4:
            r[10] += 1
        if r1<=-4:
            r[11] += 1
        if r1>=3:
            r[12] += 1
        if r1<=-3:
            r[13] += 1
        if r1>=2:
            r[14] += 1
        if r1<=-2:
            r[15] += 1
    print(r)
    print("price all:"+str(sum(price)))
    # price.sort()
    # flog = open("2.log","w")
    ##print(price)
    # d6.sort()
    # print >> flog,d6;
    # flog.close
    fo = open("foo.csv", "a")
    fo.write(onlyname+','+','+str(r[0])+','+str(r[1])+','+str(r[2])+','+str(r[3])+',,,,,'+str(r[4])+','+str(r[5])+','+str(r[6])+','+str(r[7])+','+str(r[8])+','+str(r[9])+','+str(r[10])+','+str(r[11])+','+str(r[12])+','+str(r[13])+','+str(r[14])+','+str(r[15])+','+str(sum(price))+'\n')
    fo.close()

def old_hk(file_name, onlyname):
#there will be counting error with names such as YUGANG INT'L and VALE COMMON-DRS
#2916	BRK_A	伯克希尔哈撒韦-A213330.00-0.13
    print(file_name)
    file = open(file_name)
    ratio=[]
    price=[]
    issuename=[]
    for line in file:
        l1=line.split("\t")
        if len(l1)>5 :
            m=re.findall('\d+\.\d+',l1[2])
            if m:
                if len(m)>1:
                    m1=re.findall('-\d+\.\d+',l1[2])
                    if m1:
                        ratio.append(float(m1[0]))
                    else:
                        ratio.append(float(m[1]))
                    
                else:
                    issuename.append(l1[2][len(l1[2])-1])
                    issuename.append(l1[2])
                    print(l1[2])
                    if isDigit(l1[3]):
                        print(l1[3])
                        ratio.append(float(l1[3]))
                    #m=re.findall('\d+\.\d+',l1[2])
                if isDigit(m[0]):
                    print(m[0])
                    price.append(float(m[0]))
                
            else:    
                if isDigit(l1[4]):
                    print(l1[4])
                    ratio.append(float(l1[4]))
                if isDigit(l1[3]):
                    print(l1[3])
                    price.append(float(l1[3]))
    r=[0 for i in range(16)]
    r8=[0 for i in range(40)]
    for r1 in ratio:
        if r1>=9.9:
            r[0] += 1
        if r1<=-9.9:
            r[1] += 1
        if r1>=8:
            r[2] += 1
        if r1<=-8:
            r[3] += 1
            r8.append(r1)
        if r1>=7:
            r[4] += 1
        if r1<=-7:
            r[5] += 1
        if r1>=6:
            r[6] += 1
        if r1<=-6:
            r[7] += 1
        if r1>=5:
            r[8] += 1
        if r1<=-5:
            r[9] += 1
        if r1>=4:
            r[10] += 1
        if r1<=-4:
            r[11] += 1
        if r1>=3:
            r[12] += 1
        if r1<=-3:
            r[13] += 1
        if r1>=2:
            r[14] += 1
        if r1<=-2:
            r[15] += 1
    print(r)
    print("price all:"+str(sum(price)))
    r8.sort()
    print(r8)
    #print(issuename)
    fo = open("foo.csv", "a")
    fo.write(onlyname+','+str(r[0])+','+str(r[1])+','+str(r[2])+','+str(r[3])+',,,,,'+str(r[4])+','+str(r[5])+','+str(r[6])+','+str(r[7])+','+str(r[8])+','+str(r[9])+','+str(r[10])+','+str(r[11])+','+str(r[12])+','+str(r[13])+','+str(r[14])+','+str(r[15])+','+str(sum(price))+'\n')
    fo.close()




def printSeparator(func):
    def deco(path):
        print("call method %s, result is:" % func.__name__)
        print("-" * 40)
        func(path)
        print("=" * 40)
    return deco
@printSeparator
def traverseDirByShell(path):
    for f in os.popen('ls ' + path):
        print f.strip()
@printSeparator
def traverseDirByGlob(path):
    path = os.path.expanduser(path)
    for f in glob(path + '/*'):
        print f.strip()
@printSeparator
def traverseDirByListdir(path):
    path = os.path.expanduser(path)
    for f in os.listdir(path):
        print f.strip()
        if os.path.isdir(f.strip()):
            for f1 in os.listdir(f.strip()):
                print f1.strip()
                print f1
@printSeparator
def traverseDirByOSWalk(path):
    fo = open("foo.csv", "r")
    path = os.path.expanduser(path)
    all_the_text = fo.read( )
    fo.close()
    #t='时间,用户,最大出境流速(Mbps),最大入境流速(Mbps),最大总流速(Mbps),峰值95'+'\n'
    #fo.writelines(t)
    for (dirname, subdir, subfile) in os.walk(path):
        #print('dirname is %s, subdir is %s, subfile is %s' % (dirname, subdir, subfile))
        print('[' + dirname + ']')
        for f in subfile:
            print(dirname)
            #print(dirname.decode('utf8')[0:5].encode('utf8'))
            l1=dirname.split('\\')
            l2=l1[len(l1)-1] 
            print(l2)
            if f.lower().endswith('.xls'):
                if all_the_text.count(f)==0:
                    print(f+' not counted')
                    if f[6]=='.':
                        print(f+ " is A file")
                        china(os.path.join(dirname, f), f)
                    if f[6].lower()=='h':
                        print(f+ " is hongkong file")
                        hk(os.path.join(dirname, f), f)
                    if f[6].lower()=='u':
                        print(f+ " is usa file")
                        hk(os.path.join(dirname, f), f)
                    # print(os.path.join(dirname, f))
			        # file = open(os.path.join(dirname, f))
			        # file.readline()
			        # file.readline()
                    
			    # l3=file.readline()
			    # print(l3)
			    # l4=l3.split(',')
			    # print(l4[2]+',')
			    # l5=file.readline()
			    # l6=l5.split(',')
			    # print(l2+','+l4[0]+','+l4[2]+','+l4[3]+','+l4[4]+','+l6[2])
			    # fo.writelines(l2+','+l4[0]+','+l4[2]+','+l4[3]+','+l4[4]+','+l6[2]+'\n')
if __name__ == '__main__':
    path = os.getcwd()
#    traverseDirByGlob(path)
#    traverseDirByGlob(path)
#    traverseDirByListdir(path)
    traverseDirByOSWalk(path)

猜你喜欢

转载自blog.csdn.net/llrraa2010/article/details/50995243
今日推荐