[Python] 三种文件读取方式：生成器分块/按行/一次读取

三种文件读取方式。一次读取文件、按行读取文件、按行读取并跳过某些行、按块读取文件。

一次读取

def read_file_by_total(file):
    """ 一次读取整个文件 """
    with open(file, mode='r', encoding='utf-8') as f:
        return f.read()

按行读取

""" 按行读取，去掉行尾换行符 """
def read_file_by_line(file):
    with open(file, mode='r', encoding='utf-8') as f:
        while True:
            one_line = f.readline()
            if not one_line:
                return
            else:
                yield one_line.strip()  # 去掉每行结尾的换行


""" 按行读取，遇到空行退出 """
def read_file_by_line(file):
    
    with open(file, mode='r', encoding='utf-8') as f:
        while True:
            one_line = f.readline().strip()
            if not one_line:
                return
            yield one_line

""" 按行读取，跳过空行，去掉行尾换行符 """
def read_file_by_line(file):
    with open(file, mode='r', encoding='utf-8') as f:
        while True:
            one_line = f.readline()
            if one_line.isspace():
                continue
            elif not one_line:
                return
            else:
                yield one_line.strip()  # 去掉每行结尾的换行

""" 按行读取，跳过以startwith开头的行，遇到空行退出 """
def read_file_by_line_skip(file, startwith=None):
    with open(file, mode='r', encoding='utf-8') as f:
        while True:
            one_line = f.readline().strip()
            while one_line.startswith(startwith):
                one_line = f.readline().strip()
            if not one_line:
                return
            yield one_line

调用：

lines = read_file_by_line('test.txt')
for line in lines:
    print(line)

lines = read_file_by_line_skip('test.txt', startwith='#')
for line in lines:
    print(line)

按块读取

""" 按块读取 """
def read_file_by_chunk(file, chunk_size=512):
    with open(file, mode='r', encoding='utf-8') as f:
        while True:
            chunk = f.read(chunk_size)
            if not chunk:
                return
            yield chunk

调用：

chunks = read_file_by_chunk('test.txt')
for chunk in chunks:
    print(chunk, end='')