aioVextractor

Extract video structured data from more than 40 websites/mobile apps/H5 pages. Supporting TikTok, Youtube, Instagram, etc.

解析视频网站/APP/H5 页面视频信息。支持抖音、腾讯视频、YouTube、Instagram 等40余个网站与APP

开发文档

docker便捷部署

git clone https://github.com/panoslin/aioVextractor &&\
cd aioVextractor &&\
sudo chmod +x build.sh &&\
sudo sh build.sh

使用

from aioVextractor.api import (
    extract,
    breakdown,
    hybrid_worker
)
import aiohttp
import asyncio

async def test():
    async with aiohttp.ClientSession() as session:
        single_url = "https://creative.adquan.com/show/286788"
        playlist_url = "https://weibo.com/p/1005055882998192/photos?type=video#place"
        print(await extract(webpage_url=single_url, session=session))
        print(await hybrid_worker(webpage_url=single_url, session=session))
        print(await breakdown(webpage_url=playlist_url, session=session))
        print(await hybrid_worker(webpage_url=playlist_url, session=session))


asyncio.run(test())

以上提供最高级的 API 解析视频网页链接

extract: 解析单个视频网址
breakdown: 解析整个播放列表网址
hybrid_worker: 自动检测网页是否为单个视频网址/播放列表网址并且返回对应结果

支持的网站
- youtube
- tvcf
- vimeo
- vmovier
- iwebad
- douyin
- naver
- hellorf
- pinterest
- digitaling
- weibo
- adquan
- xinpianchang
- carben
- bilibili
- tencent
- instagram
- lanfan
- youku
- renren
- socialbeta
- weixin
- eyepetizer

测试Demo

from aioVextractor.extractor.tencent import Extractor as tencentIE
from pprint import pprint

with tencentIE() as extractor:
    webpage_url = "https://v.qq.com/iframe/player.html?vid=c0912n1rqrw&tiny=0&auto=0"
    res = extractor.sync_entrance(webpage_url=webpage_url)
    pprint(res)

"""
OUTPUT:
[{'ad_link': None,
  'author': 'Apple 官方频道',
  'author_attention': None,
  'author_avatar': None,
  'author_birthday': None,
  'author_description': None,
  'author_follwer_count': None,
  'author_follwing_count': None,
  'author_gender': None,
  'author_id': None,
  'author_sign': None,
  'author_url': 'http://v.qq.com/vplus/c855f20d041bc7e06f356522325b0902',
  'author_videoNum': None,
  'category': None,
  'cdn_url': None,
  'collect_count': None,
  'comment_count': None,
  'cover': 'http://vpic.video.qq.com/0/c0912n1rqrw.png',
  'description': None,
  'dislike_count': None,
  'download_count': None,
  'downloader': 'aria2c',
  'duration': '30',
  'forward_count': None,
  'from': 'tencent',
  'gender': None,
  'height': None,
  'language': None,
  'like_count': None,
  'play_addr': 'http://video.dispatch.tc.qq.com/uwMROfz2r5zIIaQXGdGlQmdfDmZvd0vRcymWSecrfGm8rzTb/c0912n1rqrw.mp4?vkey=0A9434327F854F742C34AEA63A4F5D91ECD3BD9941D4A21621691B03C74371E884E6AF55D20955207FFCE82AA75A01A55B29C753410E57BDCD9CB487C427D06C88D3DC8EEAF862862C5ACE1D009EA9AB4E9E9FD248C76EA2072BCAF06BA0F96DE76EE242119D5AAC873A6C18214552B745D194B35B1F1525CBE32AC7B90C7EAA',
  'rating': None,
  'recommend': None,
  'region': None,
  'share_count': None,
  'tag': ['敬 Mac 背后的你 - 试出可能 - Apple',
          '腾讯视频',
          '电影',
          '电视剧',
          '综艺',
          '新闻',
          '财经',
          '音乐',
          'MV',
          '高清',
          '视频',
          '在线观看'],
  'title': '敬 Mac 背后的你 - 试出可能 - Apple',
  'upload_date': None,
  'upload_ts': 1262275200,
  'vid': 'c0912n1rqrw',
  'view_count': '246304',
  'webpage_url': 'https://v.qq.com/x/page/c0912n1rqrw.html',
  'width': None}]
"""

测试Demo

from aioVextractor.api import hybrid_worker
import aiohttp
import asyncio
from pprint import pprint

async def test(url):
    async with  aiohttp.ClientSession() as session:
        result = await hybrid_worker(
            webpage_url=url,
            session=session,
        )
        return result

url = "https://www.youtube.com/playlist?list=PLs54iBUqIopDv2wRhkqArl9AEV1PU-gmc"  ## u can try any url from `TEST_CASE`
pprint(asyncio.run(test(url=url)))


"""
OUTPUT:
Processing URL: https://www.youtube.com/playlist?list=PLs54iBUqIopDv2wRhkqArl9AEV1PU-gmc
([{'ad_link': None,
   'author': None,
   'author_attention': None,
   'author_avatar': None,
   'author_birthday': None,
   'author_description': None,
   'author_follwer_count': None,
   'author_follwing_count': None,
   'author_gender': None,
   'author_id': None,
   'author_sign': None,
   'author_url': None,
   'author_videoNum': None,
   'category': None,
   'cdn_url': None,
   'collect_count': None,
   'comment_count': None,
   'cover': 'https://i.ytimg.com/vi/61CQm2zVVk0/hqdefault.jpg?sqp=-oaymwEZCPYBEIoBSFXyq4qpAwsIARUAAIhCGAFwAQ==&rs=AOn4CLAKICJl2FlmleQsKntUd0KIeOEjZA',
   'description': None,
   'dislike_count': None,
   'download_count': None,
   'downloader': 'ytd',
   'duration': None,
   'forward_count': None,
   'from': 'youtube',
   'gender': None,
   'height': None,
   'language': None,
   'like_count': None,
   'play_addr': None,
   'playlist_url': 'https://www.youtube.com/playlist?list=PLs54iBUqIopDv2wRhkqArl9AEV1PU-gmc',
   'rating': None,
   'recommend': None,
   'region': None,
   'share_count': None,
   'tag': None,
   'title': "The Avengers Earth's Mightiest Heroes Se1 - Ep01 Breakout (Part "
            '1) - Part 01',
   'upload_date': None,
   'upload_ts': None,
   'vid': '61CQm2zVVk0',
   'view_count': None,
   'webpage_url': 'https://www.youtube.com/watch?v=61CQm2zVVk0&list=PLs54iBUqIopDv2wRhkqArl9AEV1PU-gmc&index=2&t=0s',
   'width': None},
   ...
  {'ad_link': None,
   'author': None,
   'author_attention': None,
   'author_avatar': None,
   'author_birthday': None,
   'author_description': None,
   'author_follwer_count': None,
   'author_follwing_count': None,
   'author_gender': None,
   'author_id': None,
   'author_sign': None,
   'author_url': None,
   'author_videoNum': None,
   'category': None,
   'cdn_url': None,
   'collect_count': None,
   'comment_count': None,
   'cover': 'https://i.ytimg.com/vi/PRT3FjaP71E/hqdefault.jpg?sqp=-oaymwEZCNACELwBSFXyq4qpAwsIARUAAIhCGAFwAQ==&rs=AOn4CLA2zBcMa68iPw6tQO5nSbKlkwFv8w',
   'description': None,
   'dislike_count': None,
   'download_count': None,
   'downloader': 'ytd',
   'duration': None,
   'forward_count': None,
   'from': 'youtube',
   'gender': None,
   'height': None,
   'language': None,
   'like_count': None,
   'play_addr': None,
   'playlist_url': 'https://www.youtube.com/playlist?list=PLs54iBUqIopDv2wRhkqArl9AEV1PU-gmc',
   'rating': None,
   'recommend': None,
   'region': None,
   'share_count': None,
   'tag': None,
   'title': "The Avengers Earth's Mightiest Heroes Se1 - Ep10 Everything Is "
            'Wonderful - Screen 04',
   'upload_date': None,
   'upload_ts': None,
   'vid': 'PRT3FjaP71E',
   'view_count': None,
   'webpage_url': 'https://www.youtube.com/watch?v=PRT3FjaP71E&list=PLs54iBUqIopDv2wRhkqArl9AEV1PU-gmc&index=101&t=0s',
   'width': None}],
 True,
 {'clickTrackingParams': 'CD0QybcCIhMI16ucw-G35QIV40L1BR0A1weh',
  'continuation': '4qmFsgI2EiRWTFBMczU0aUJVcUlvcER2MndSaGtxQXJsOUFFVjFQVS1nbWMaDmVnWlFWRHBEUjFFJTNE'})
"""

测试通过链接：

panoslin / aio-vextractor Goto Github PK

aio-vextractor's Introduction

aioVextractor

开发文档

aio-vextractor's People

Contributors

Stargazers

Watchers

Forkers

aio-vextractor's Issues

对python版本的判断有问题

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent

Jobs