最近需要操作inf格式文档,用原本的文本读取方式不成功,于是搜索了一下找到原因。需要读取的目录下的文件有两种编码方式,一种是ANSI,另外一种是Unicode,但是Unicode的存储方式有UTF-8,UTF-16等,UTF即为Unicode Translation Format,就是把Unicode转做某种格式的意思。读取Unicode编码方式的文本时需要标明其存储方式,否则会出错。
如下代码可以读取指定目录下面以"test"为前缀以".txt"为后缀的文本文件(文件可以存在子目录下),搜索到其中是否含有"done"字串,若有则输出其文件夹路径,其完整路径还有含有该字串的行。搜索完毕后将搜索到的文件完整路径存在一个list中并再次输出。
import os.path
import codecs
rootdir = "C:\\test\\code_python\\testfile"
def lookupstring(lookup):
filelist = []
judge = False
for parent, dirnames, filenames in os.walk(rootdir):
for filename in filenames:
if filename.startswith("test") and filename.endswith(".txt"):
try:
f = codecs.open(os.path.join(parent, filename), 'r', 'utf-16')
ls = [ line.strip() for line in f]
for line in ls:
if not line.find(lookup) == -1:
print "parent is:" + parent
print "filename with full path :" + os.path.join(parent, filename)
print line
judge = True
if judge == True:
filelist.append(os.path.join(parent, filename))
judge = False
f.close()
except:
f.close()
f = open(os.path.join(parent, filename), 'r')
ls = f.readlines()
for line in ls:
if not line.find(lookup) == -1:
print "parent is:" + parent
print "filename with full path :" + os.path.join(parent, filename)
print line
judge = True
if judge == True:
filelist.append(os.path.join(parent, filename))
judge = False
f.close()
return filelist
def main():
test = lookupstring("done")
for element in test:
print element
if __name__ == '__main__':
main()