vndangkhoa/kv-tiktok-download
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

🛠 Fix regex to find video id

Browse source
This commit is contained in:
Evil0ctal 2022-11-10 01:20:26 -08:00 committed by GitHub
parent 72b7ded789
commit b1802dced2
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 7 additions and 13 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

20
scraper.py
View file

@ -2,7 +2,7 @@
# -*- encoding: utf-8 -*- # -*- encoding: utf-8 -*-
# @Author: https://github.com/Evil0ctal/ # @Author: https://github.com/Evil0ctal/
# @Time: 2021/11/06 # @Time: 2021/11/06
# @Update: 2022/11/09 # @Update: 2022/11/10
# @Version: 3.1.0 # @Version: 3.1.0
# @Function: # @Function:
# 核心代码，估值1块(๑•̀ㅂ•́)و✧ # 核心代码，估值1块(๑•̀ㅂ•́)و✧
@ -124,6 +124,9 @@ class Scraper:
1. https://live.douyin.com/88815422890 1. https://live.douyin.com/88815422890
""" """
if 'v.douyin' in url: if 'v.douyin' in url:
# 转换链接/convert url
# 例子/Example: https://v.douyin.com/rLyAJgf/8.74
url = re.compile(r'(https://v.douyin.com/)\w+', re.I).match(url).group()
print('正在通过抖音分享链接获取原始链接...') print('正在通过抖音分享链接获取原始链接...')
try: try:
async with httpx.AsyncClient(proxies=self.proxies) as client: async with httpx.AsyncClient(proxies=self.proxies) as client:
@ -281,7 +284,7 @@ class Scraper:
video_id = original_url.split('/')[-1] video_id = original_url.split('/')[-1]
if '.html' in video_id: if '.html' in video_id:
video_id = video_id.replace('.html', '') video_id = video_id.replace('.html', '')
# video_id = re.findall('/video/(\d+)?', original_url)[0] video_id = re.findall('/video/(\d+)', original_url)[0]
print('获取到的TikTok视频ID是{}'.format(video_id)) print('获取到的TikTok视频ID是{}'.format(video_id))
# 返回视频ID/Return video ID # 返回视频ID/Return video ID
return video_id return video_id
@ -516,15 +519,6 @@ class Scraper:
async def async_test(douyin_url: str = None, tiktok_url: str = None): async def async_test(douyin_url: str = None, tiktok_url: str = None):
# 异步测试/Async test # 异步测试/Async test
print("正在测试异步转换URL方法...")
if douyin_url:
douyin_url = await api.convert_share_urls(douyin_url)
elif tiktok_url:
tiktok_url = await api.convert_share_urls(tiktok_url)
else:
douyin_url = await api.convert_share_urls('https://v.douyin.com/MtutjoY/')
tiktok_url = await api.convert_share_urls('https://www.tiktok.com/@tiktok/video/6825760761660357638')
print("正在测试异步获取抖音视频ID方法...") print("正在测试异步获取抖音视频ID方法...")
douyin_id = await api.get_douyin_video_id(douyin_url) douyin_id = await api.get_douyin_video_id(douyin_url)
print("正在测试异步获取抖音视频数据方法...") print("正在测试异步获取抖音视频数据方法...")
@ -543,6 +537,6 @@ async def async_test(douyin_url: str = None, tiktok_url: str = None):
if __name__ == '__main__': if __name__ == '__main__':
api = Scraper() api = Scraper()
# 运行测试 # 运行测试
douyin_url = 'https://v.douyin.com/MtutjoY/' douyin_url = 'https://v.douyin.com/rLyrQxA/6.66'
tiktok_url = 'https://www.tiktok.com/@tiktok/video/6825760761660357638' tiktok_url = 'https://vm.tiktok.com/ZMFf3HPbB/'
asyncio.run(async_test(douyin_url=douyin_url, tiktok_url=tiktok_url)) asyncio.run(async_test(douyin_url=douyin_url, tiktok_url=tiktok_url))