Question

我试图以Python的方式读取数据，就像这样

states = """
        Alabama
        Alberta
        Alaska
        Arizona
        Arkansas
        Bob
        Tom
        Ted
        William
        """
states_list = [w.strip().lower() for w in states.splitlines() if w]

现在，如果我尝试从文件中读取类似的数据，那么它无效。我是这样做的

file1 = open('dictionary_file.txt','r')
data = file1.read()
file1.close()

然后迭代数据中的项目

这是整个代码，相关部分在最后。

def _get_child_branches(tree):
"""
This method return all the branches of the tree
"""
return tree[1:]


def _get_child_branch(tree, c):
"""
This method returns the specific branch of the tree given the character
"""
for branch in _get_child_branches(tree):
    if branch[0] == c:
        return branch

return None


def _retrive_branch(k, tree):
"""
This method is used for getting the branch for a given word
"""
if not k:
    return None

for c in k:
    child_branch = _get_child_branch(tree, c)
    if not child_branch:
        return None
    tree = child_branch

return tree


def _is_tree_bucket(bucket):
if len(bucket) != 2:
    return False

return type(bucket[1]) is tuple


def _get_bucket_key(bucket):
if not _is_tree_bucket(bucket):
    return None

return bucket[1][0]


def has_key(k, tree):
"""
To check if the tree containes the keyword
"""
return _retrive_branch(k, tree) is not None


def retree_val(k, tree):
key_tuple = _retrive_branch(k, tree)
if not key_tuple:
    return None

return key_tuple[1]


def insert_key(key, v, tree):
"""
Insert a (key, value) pair into tree
"""
if not key or has_key(key, tree):
    return

for char in key:
    branch = _get_child_branch(tree, char)
    if not branch:
        new_branch = [char]
        tree.append(new_branch)
        tree = new_branch
    else:
        tree = branch
tree.append((key, v))


def start_with_prefix(prefix, tree):
"""
Find words start with prefix
"""
branch = _retrive_branch(prefix, tree)
if not branch:
    return []

prefix_list = []
q = branch[1:]
while q:
    curr_branch = q.pop(0)
    if _is_tree_bucket(curr_branch):
        prefix_list.append(_get_bucket_key(curr_branch))
    else:
        q.extend(curr_branch[1:])

return prefix_list






if __name__ == "__main__":
tree = [[]]
file1 = open('dictionary_file.txt','r')
data = file1.read().split('\n')
file1.close()
states = """
        Alabama
        Alberta
        Alaska
        Arizona
        Arkansas
        Bob
        Tom
        Ted
        William"""
states_list = [w.strip().lower() for w in states.splitlines() if w]
print(states_list)
print(states)
for state in data:
    insert_key(state, True, tree)


print start_with_prefix("a", tree)

Answer 1

只需用file object替换分割线并迭代：

with open('dictionary_file.txt','r') as f:
   lines  =[w.strip().lower() for w in f if w]

除非你真的需要一次数据，文件对象是可迭代的并且在你迭代时会给你每一行，所以永远不需要将整个文件读入内存。

在旁注中，您需要在分界线代码中if w，因为您在行之前和之后添加换行符，在引号处开始您的字符串并在引号处结束它并且您不会得到任何空字符串：

states = """Alabama
    Alberta
    Alaska
    Arizona
    Arkansas
    Bob
    Tom
    Ted
    William"""

Answer 2

请阅读Reading and writing files。

with open('dictionary_file.txt', 'r') as f:
   lines = f.readlines()

states_list = [w.strip().lower() for w in lines if w]

修改：我意识到这里不需要使用readlines()。只需使用@ Padraic的答案。

Answer 3

添加.split('\n')将解决此问题。

file1 = open('dictionary_file.txt','r')
data = file1.read().split('\n')
file1.close()
for i in data:
    print i

在python中读取数据？

3 个答案: