我想打开文件夹中的所有文档,并将每个文档放入列表的元素中,如:["doc1", "doc2", "doc3", ... ]
for dirpath, dirs, files in os.walk('filepath'):
for filename in fnmatch.filter(files, '*-*'):
with open(os.path.join(dirpath, filename)) as text:
lines=text.readlines()
print lines
然而,它只是将文档的所有内容变成一个字符串。
请告诉我如何达到预期的结果。
docs = []
for dirpath, dirs, files in os.walk('filepath'):
for filename in fnmatch.filter(files, '*-*'):
with open(os.path.join(dirpath, filename)) as text:
docs.append(text.read())
print docs
从文件夹获取不同文件类型路径的通用玻璃
idir = "c:\data\" #In directory
class Paths_to_files:
def __init__(self, idir):
self.idir = idir
def get_paths(self, rf):
rf_list = []
listing = os.listdir(self.idir)
for files in listing:
if rf in files:
rf_list.append(files)
return sorted(rf_list)
class Wrapper(Paths_to_files):
def __init__(self, idir):
self.idir = idir
#Get all files:
files = Wrapper(idir)
#Get all tiff files:
tifpath = files.get_paths('tif')
#Get all csv files:
csvpath = files.get_paths('csv')