学习记录

解决方法：

在字符串后面加上.decode("utf-8")，问题解决

如：res.content.decode("utf-8")

# 列表
# 查找元素在列表中位置
p=list.index(value) # list为列表的名字 value为查找的值 p为value在list的位置

# Python中bytes与字符串的相互转化
# bytes转字符串方式一
b=b'\xe9\x80\x86\xe7\x81\xab'
string=str(b,'utf-8')
print(string)

# bytes转字符串方式二
b=b'\xe9\x80\x86\xe7\x81\xab'
string=b.decode() # 第一参数默认utf8，第二参数默认strict
print(string)

# bytes转字符串方式三
b=b'\xe9\x80\x86\xe7\x81haha\xab'
string=b.decode('utf-8','ignore') # 忽略非法字符，用strict会抛出异常
print(string)

# bytes转字符串方式四
b=b'\xe9\x80\x86\xe7\x81haha\xab'
string=b.decode('utf-8','replace') # 用？取代非法字符
print(string)

# 字符串转bytes方式一
str1='逆火'
b=bytes(str1, encoding='utf-8')
print(b)

# 字符串转bytes方式二
b=str1.encode('utf-8')
print(b)

# python3 字典、列表、数组和字符串之间的相互转化
# 字典
dict_1 = {'1': 'a', '2': 'b', '3': 'c'}
print(dict_1)  # 打印字典
print(type(dict_1))  # 打印新赋值的字典的类型

print(str(dict_1), end='字符串\n')  # 把字典转化成字符串后打印

print(tuple(dict_1), end='元组\n')  # 把字典转化为元组后打印

print(list(dict_1), end='列表\n')  # 把字典转化为列表后打印

# 元组
tuple_1 = (1, 2, 3, 4, 5)
print(tuple_1)  # 打印元组
print(type(tuple_1))  # 打印新赋值的元祖的类型

print(str(tuple_1), end='字符串\n')  # 把元组转化成字符串后打印

print(list(tuple_1), end='列表\n')  # 把元组转化为列表后打印

# 元组不可转化为字典

#列表
list_1 = [1, 2, 3, 4, 5]
print(list_1)  # 打印列表
print(type(list_1))  # 打印新赋值的列表的类型

print(str(list_1), end='字符串\n')  # 把列表转化成字符串后打印

print(tuple(list_1), end='元组\n')  # 把列表转化为元组后打印

#字符串
string_1 = '(1, 2, 3, 4, 5)'
print(string_1)  # 打印字符串
print(type(string_1))  # 打印新赋值的字符串

print(tuple(eval(string_1)), end='元组\n')  # 把字符串转化成元组后输出

print(list(eval(string_1)), end='列表\n')  # 把字符串转化成列表后输出

# 只有特殊字符串才能转化为字典
string_2 = '{"name":"tom","age":6}'
print(string_2)  # 打印新赋值的字符串
print(type(string_2))  # 打印新赋值的字符串的类型

print(eval(string_2), end='字典\n')  # 把字符串转化为字典后打印

# coding:utf-8

import struct
import requests

class Mp4info:
    def __init__(self, file):
        self.file = file
        self.seek = 0
        self.duration = 0
        self.s = requests.session()
        self.timeout = 6
        self.s.headers = {
            'Connection': 'keep-alive',
            'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
            'Accept-Encoding': 'gzip, deflate',
            'Accept-Language': 'zh-CN,zh;q=0.9,en-US;q=0.8,en;q=0.7',
            'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36'
        }

    # 设置请求头  set request header
    # 传入的seek表示代表需要跳过的字节数量  use seek to skip initial data
    # 在这里进行判断是为了后续获取视频的宽高信息预留的  the condition here is for reserving space for getting the media data
    def _set_headers(self, seek, type):
        if type in ['moov', 'duration']:
            self.s.headers['Range'] = 'bytes={}-{}'.format(seek, seek + 7)

    def _send_request(self):
        try:
            data = self.s.get(url=self.file, stream=True,
                              timeout=self.timeout).raw.read()
        except requests.Timeout:
            raise '连接超时:超过6秒(默认)服务器没有响应任何数据！'  # timeout 6 seconds, the server fails to respond and assumes there is no data
        return data

    def _find_moov_request(self):
        self._set_headers(self.seek, type='moov')
        data = self._send_request()
        size = int(struct.unpack('>I', data[:4])[0])
        flag = data[-4:].decode('ascii')
        return size, flag

    def _find_duration_request(self):
        # 4+4是moov的大小和标识,跳过20个字符，直接读到time_scale，duration  # 4+4 is the first 8 characters denoting charset, skip the next 20 to time_scale and duration
        self._set_headers(seek=self.seek+4+4+20, type='duration')
        data = self._send_request()
        time_scale = int(struct.unpack('>I', data[:4])[0])
        duration = int(struct.unpack('>I', data[-4:])[0])
        return time_scale, duration

    def get_duration(self):
        while True:
            size, flag = self._find_moov_request()
            if flag == 'moov':
                time_scale, duration = self._find_duration_request()
                self.duration = duration/time_scale
                return self.duration
            else:
                self.seek += size


if __name__ == '__main__':
    url = 'https://vd2.bdstatic.com/mda-mfqszq3mzd845q23/1080p/cae_h264/1624620686306577424/mda-mfqszq3mzd845q23.mp4?v_from_s=hkapp-haokan-tucheng&auth_key=1625478247-0-0-6baa0019344f9a31db76ddb4be3909e5&bcevod_channel=searchbox_feed&pd=1&pt=3&abtest=3000165_1'
    file = Mp4info(url)
    a = file.get_duration()
    print(a)