ks_automation/common/srt.py

import re

import requests
import json

class SRT():


    @classmethod
    # 定义函数去掉文字后的标点符号并添加换行符
    def process_srt(cls, srt):
        lines = srt.strip().split('\n')
        processed_lines = []

        for line in lines:
            # 匹配字幕编号行
            if re.match(r'^\d+$', line):
                processed_lines.append(line)
            # 匹配时间戳行
            elif re.match(r'^\d{2}:\d{2}:\d{2}\.\d{1,3}-->\d{2}:\d{2}:\d{2}\.\d{1,3}$', line):
                processed_lines.append(line.replace('-->', ' --> '))
            # 处理字幕文本行
            else:
                # 去掉末尾的标点符号
                line = re.sub(r'[，。！？；、]$', '', line)
                # 添加换行符
                processed_lines.append(line + '\n')

        return '\n'.join(processed_lines)

    @classmethod
    def getSrt(cls, mp3_id):
        url = "http://api-internal.piaoquantv.com/produce-center/srt/get/content"

        payload = json.dumps({
            "params": {
                "resourceChannel": "inner",
                "videoId": mp3_id
            }
        })
        headers = {
            'User-Agent': 'Apifox/1.0.0 (https://apifox.com)',
            'Content-Type': 'application/json',
            'Accept': '*/*',
            'Host': 'api-internal.piaoquantv.com',
            'Connection': 'keep-alive'
        }

        response = requests.request("POST", url, headers=headers, data=payload)
        data_list = response.json()
        code = data_list["code"]
        if code == 0:
            srt = data_list["data"]
            if srt:
                srt = srt.replace("/n", "\n")
                # srt = re.sub(r'(\w+)([,。!?])', r'\n\n', srt)
                new_srt = cls.process_srt(srt)
                return new_srt
            else:
                return None
        else:
            return None