python函数库

发表于 | 分类于
用过的python函数库
字符串
截取字符串

截取指定两个符号间的字符串返回所有符合结果的list

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
def get_list_hash(template):  # HashTag以‘#’开头，以空格或回车结尾
    copy = False
    finished = False
    slotList = []
    str = ""
    for s in template:
        if s == '#':
            copy = True
        elif s == ' ':
            copy = False
            finished = True
        elif s == '\n':
            copy = False
            finished = True
        elif copy:
            str = str + s
        if finished:
            if str != "":
                slotList.append(str)
            str = ""
            finished = False
    return slotList

1
2
3
4
def get_text(template):
    rule = r':::(.*?)\n'
    slot_list = re.findall(rule, template)
    return slot_list
判断是否为英文字母
1
2
3
4
5
6
7
#解决.isalpha()方法对（unicode string，string.isalpha会根据字符串中的字符是否属于Unicode编码的LETTER区域来判断是否都由字母组成。
# 所以得出的结果为True，不一定表示只有26个英文字母。）
def is_alpha(word):
    try:
        return word.encode('ascii').isalpha()
    except UnicodeEncodeError:
        return False
文件操作
创建文件夹
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
def mkdir(path):
    # 去除首位空格
    path = path.strip()
    # 去除尾部 \ 符号
    path = path.rstrip("/")

    # 判断路径是否存在
    # 存在     True
    # 不存在   False
    isExists = os.path.exists(path)

    # 判断结果
    if not isExists:
        # 如果不存在则创建目录
        # 创建目录操作函数
        os.makedirs(path)

        print(str(path) + ' 创建成功')
        return True
    else:
        # 如果目录存在则不创建，并提示目录已存在
        print(str(path) + ' 目录已存在')
        return False
读取文件

读取并按行遍历文件

1
2
3
4
5
6
7
f_video_text = open("video_text.txt",encoding='utf8', errors='ignore')
while 1:
    line_video_text = f_video_text.readline()
    if not line_video_text:
        break
    else:
        do something

读取文件夹下所有文件名，返回list
1
2
3
4
def get_list_file_name(file_dir):  # 获取视频名list
    for root, dirs, files in os.walk(file_dir):
        continue
    return files
获取文件行数
1
2
3
4
5
6
7
8
9
10
def get_lines(file_name):
    count = 0
    thefile = open(file_name, encoding='utf8', errors='ignore')
    while True:
        buffer = thefile.read(1024 * 8192)
        if not buffer:
            break
        count += buffer.count('\n')
    thefile.close()
    return count
读取文件dict or list
1
2
3
4
5
6
def get_list_or_dict(path):
    f = open(path,encoding='utf8', errors='ignore')
    a = f.read()
    dict_or_list = eval(a)
    f.close()
    return dict_or_list
txt文件数据写成dict or list文件
1
2
3
4
5
6
7
8
9
10
11
12
13
14
def write_list_or_dict(path_txt,path_dict_or_list_txt):
    f = open(path_txt,encoding='utf8', errors='ignore')
    while 1:
        line_txt = f.readline()
        if not line_txt:
            break
        else:
            handle
            list_or_dict[id] = content
    f.close()
    f = open(path_dict_or_list_txt, 'w' , encoding='utf8' , errors='ignore')
    f.write(str(list_or_dict))
    f.close
    print('写入成功')
获取视频或音频时长

获取视频或音频时长，需要安装ffmpeg

1
2
3
4
5
6
7
8
def get_time(filename):
    command = 'ffprobe -loglevel quiet -print_format json -show_format -show_streams -i ' + filename
    result = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
    out = result.stdout.read()

    temp = str(out.decode('utf-8'))
    data = json.loads(temp)["format"]['duration']
    return data