30 lines
1.7 KiB
Python
30 lines
1.7 KiB
Python
import re
|
|
from urllib.parse import urlparse
|
|
|
|
|
|
def url_extract(text):
|
|
urls = re.findall(r'\b((?:https?://)?(?:(?:www\.)?(?:[\da-z\.-]+)\.(?:[a-z]{2,6})|(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.){3}(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)|(?:(?:[0-9a-fA-F]{1,4}:){7,7}[0-9a-fA-F]{1,4}|(?:[0-9a-fA-F]{1,4}:){1,7}:|(?:[0-9a-fA-F]{1,4}:){1,6}:[0-9a-fA-F]{1,4}|(?:[0-9a-fA-F]{1,4}:){1,5}(?::[0-9a-fA-F]{1,4}){1,2}|(?:[0-9a-fA-F]{1,4}:){1,4}(?::[0-9a-fA-F]{1,4}){1,3}|(?:[0-9a-fA-F]{1,4}:){1,3}(?::[0-9a-fA-F]{1,4}){1,4}|(?:[0-9a-fA-F]{1,4}:){1,2}(?::[0-9a-fA-F]{1,4}){1,5}|[0-9a-fA-F]{1,4}:(?:(?::[0-9a-fA-F]{1,4}){1,6})|:(?:(?::[0-9a-fA-F]{1,4}){1,7}|:)|fe80:(?::[0-9a-fA-F]{0,4}){0,4}%[0-9a-zA-Z]{1,}|::(?:ffff(?::0{1,4}){0,1}:){0,1}(?:(?:25[0-5]|(?:2[0-4]|1{0,1}[0-9]){0,1}[0-9])\.){3,3}(?:25[0-5]|(?:2[0-4]|1{0,1}[0-9]){0,1}[0-9])|(?:[0-9a-fA-F]{1,4}:){1,4}:(?:(?:25[0-5]|(?:2[0-4]|1{0,1}[0-9]){0,1}[0-9])\.){3,3}(?:25[0-5]|(?:2[0-4]|1{0,1}[0-9]){0,1}[0-9])))(?::[0-9]{1,4}|[1-5][0-9]{4}|6[0-4][0-9]{3}|65[0-4][0-9]{2}|655[0-2][0-9]|6553[0-5])?(?:/[\w\.-]*)*/?)\b', text)
|
|
return urls
|
|
|
|
def extract_ytid(url):
|
|
query = urlparse(url)
|
|
if query.hostname == 'youtu.be':
|
|
return query.path[1:]
|
|
if query.hostname in ('www.youtube.com', 'youtube.com'):
|
|
if query.path == '/watch':
|
|
p = urlparse.parse_qs(query.query)
|
|
return p['v'][0]
|
|
if query.path[:7] == '/embed':
|
|
return query.path.split('/')[2]
|
|
if query.path[:3] == '/v/':
|
|
return query.path.split('/')[2]
|
|
return None
|
|
|
|
server = 'yewtu.be/watch?v='
|
|
|
|
def redirect(text):
|
|
url = url_extract(text)[0]
|
|
id = extract_ytid(url)
|
|
cleaned = server+id
|
|
return cleaned
|