【python】油管外挂字幕下载位srt歌词字幕文本文件-Toy模板网

这篇具有很好参考价值的文章主要介绍了【python】油管外挂字幕下载位srt歌词字幕文本文件。希望对大家有所帮助。如果存在错误或未考虑完全的地方，请大家不吝赐教，您也可以点击"举报违法"按钮提交疑问。

【python】油管外挂字幕下载位srt文本文件

案例截图

【python】油管外挂字幕下载位srt歌词字幕文本文件,Python,爬虫学习笔记,python,开发语言

案例代码

# python程序，可以下youtube视频的字幕文件。输入一个视频的url，就会下载它的字幕文件到一个文件夹里。
# Author WeChat:****请私信,
# Date:2023-8-2,
# Email:ack1024#hotmail.com
# 本软件遵循 Apache License 2.0协议

# 导入需要的模块
import json
import math
import time

import requests
import re
import os
import xml.etree.ElementTree as ElementTree
from html import unescape

# 梯子
proxies = {
    "http": "http://127.0.0.1:10809",
    "https": "http://127.0.0.1:10809",
}
# 请求头
headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.66 Safari/537.36'
}


# 定义一个函数，根据视频的url获取字幕的url
def get_subtitle_url(video_url):

    # 发送请求，获取视频页面的源码
    response = requests.get(video_url, proxies=proxies, headers=headers)

    html = response.text

    # 用正则表达式匹配字幕的url
    match = re.search(pattern, html)
    if match:
        # 如果找到了字幕的url，返回它
        subtitle_url = match.group(1)
        return subtitle_url
    else:
        # 如果没有找到字幕的url，返回None
        return None

# 定义一个函数，根据字幕的url下载字幕文件
def download_subtitle(subtitle_url, video_id):

    # 发送请求，获取字幕的内容
    response = requests.get(subtitle_url, proxies=proxies, headers=headers)
    content = response.text

    # 用正则表达式去掉不需要的标签

    content = xml_caption_to_srt(content)

    # 创建一个文件夹，用于存放字幕文件
    folder = 'subtitles'
    if not os.path.exists(folder):
        os.mkdir(folder)

    filename = video_id + '.srt'

    filepath = os.path.join(folder, filename)

    with open(filepath, 'w', encoding='utf-8') as f:
        f.write(content)

    print('已下载字幕文件：' + filepath)

# 根据视频的url下载视频的字幕文件
def download_video_subtitle(video_url):

    video_id = video_url.split('=')[-1]
    print('当前视频id:',video_id)

    # 调用函数，获取字幕的url
    subtitle_url = get_subtitle_url(video_url)

    if not subtitle_url:
        # 如果没有字幕的url，打印提示信息
        print('该视频没有字幕')
        exit(0)

    subtitle_url = '[' + subtitle_url + ']'

    subtitle_urlDics = json.loads(subtitle_url)
    strp = ['序号:' + str(i) + ' ' + subtitle_urlDics[i]['name']['simpleText'] for i in range(len(subtitle_urlDics))]
    for i in strp:
        print(i)

    choiceIndex = int(input('请输入要下载的语言(最前面数字序号)：'))

    subtitle_url = subtitle_urlDics[choiceIndex]['baseUrl']

    if subtitle_url:
        # 如果有字幕的url，调用函数，下载字幕文件
        download_subtitle(subtitle_url, video_id)
    else:
        # 如果没有字幕的url，打印提示信息
        print('该视频没有字幕')

def xml_caption_to_srt(xml_captions: str) -> str:
    segments = []
    root = ElementTree.fromstring(xml_captions)
    for i, child in enumerate(list(root)):
        caption = unescape(text.replace("\n", " ").replace("  ", " "), )
        try:
            duration = float(child.attrib["dur"])
        except KeyError:
            duration = 0.0
        start = float(child.attrib["start"])
        end = start + duration
        sequence_number = i + 1  # convert from 0-indexed to 1.
        line = "{seq}\n{start} --> {end}\n{text}\n".format(
            seq=sequence_number,
            start=float_to_srt_time_format(start),
            end=float_to_srt_time_format(end),
            text=caption,
        )
        segments.append(line)
    return "\n".join(segments).strip()

def float_to_srt_time_format(d: float) -> str:
    time_fmt = time.strftime("%H:%M:%S,", time.gmtime(whole))
    ms = f"{fraction:.3f}".replace("0.", "")
    return time_fmt + ms

# 输入一个视频的url，下载它的字幕文件
if __name__ == '__main__':

    while True:
        video_url = input('请输入一个youtube视频的网址(例子:https://www.youtube.com/watch?v=wjTn)先复制再回来右击即可：')
        # video_url = "https://www.youtube.com/watch?v=wjTn_Ek"
        download_video_subtitle(video_url)

        if input('请输入0退出：') == 0:
            exit(0)