Skip to main content

支持AI总结的社交媒体聚合解析器

Project description

ParseHub

支持AI总结的社交媒体聚合解析器

视频总结会调用 whisper-1 模型

支持的平台:
Twitter 视频|图文
Instagram 视频|图文
微博 视频|图文
贴吧 视频|图文
小红书 视频|图文
Youtube 视频|音乐
Facebook 视频
Bilibili 视频|动态
抖音|TikTok 视频|图文
......

安装

pip install parsehub

安装yt-dlp: wiki


[!IMPORTANT]

注意

Linux用户在导入skia-python包时可能会遇到以下报错

libGL.so.1: cannot open shared object file: No such file or directory

Windows用户在缺少Microsoft Visual C++ Runtime时可能会遇到以下报错

ImportError: DLL load failed while importing skia: The specified module could not be found.

解决方法

ubuntu用户

apt install libgl1-mesa-glx

ArchLinux用户

pacman -S libgl

centos用户

yum install mesa-libGL -y

Windows用户

下载链接Microsoft Visual C++ 2015 Redistributable Update 3 RC

使用

from parsehub import ParseHub
from parsehub.config import ParseConfig, DownloadConfig
import asyncio


async def main():
    ph = ParseHub(config=ParseConfig())
    result = await ph.parse('https://twitter.com/aobuta_anime/status/1827284717848424696')
    print(result)

    # dr = await result.download()
    # print(dr.media)
    # sr = await dr.summary()
    # await dr.delete()

    sr = await result.summary(download_config=DownloadConfig())
    print(sr.content)


if __name__ == '__main__':
    asyncio.run(main())

环境变量

名称 描述 默认值
PROVIDER 模型提供商, 暂只支持openai openai
API_KEY API Key
BASE_URL API 地址 https://api.openai.com/v1
MODEL AI总结使用的模型 gpt-4o-mini
PROMPT AI总结提示词 You are a useful assistant to summarize the main points of articles and video captions. Summarize 3 to 8 points in "Simplified Chinese" and summarize them all at the end.

参考项目

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

parsehub-1.0.5.tar.gz (56.8 kB view details)

Uploaded Source

Built Distribution

parsehub-1.0.5-py3-none-any.whl (79.8 kB view details)

Uploaded Python 3

File details

Details for the file parsehub-1.0.5.tar.gz.

File metadata

  • Download URL: parsehub-1.0.5.tar.gz
  • Upload date:
  • Size: 56.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.4.16

File hashes

Hashes for parsehub-1.0.5.tar.gz
Algorithm Hash digest
SHA256 0ad7de376876879acd4d2c7b129ac1b5cf5d8d1d135805c5f0f37f900fc4594e
MD5 2f3d13715f6217af71484d95735b6154
BLAKE2b-256 6af923a95e9428045025706769a787453c9999b81ff99bfc4a2435fdde88fb61

See more details on using hashes here.

File details

Details for the file parsehub-1.0.5-py3-none-any.whl.

File metadata

File hashes

Hashes for parsehub-1.0.5-py3-none-any.whl
Algorithm Hash digest
SHA256 93e7191935051cff55524e0d60be3b15f6c76def1229ed7321c228b9e2132f52
MD5 a60f7d6a7816deb201e1c9ad4e5e14c1
BLAKE2b-256 242d5552118af01c58ca8bad3f3ff45f3aee5b5ac908c7558d2a7858ebaeb6b7

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page