INNER CODE UNIT · Python
extraer_urls
Hainrixz/whatsapp-agentkit · scripts/audit.py:556
def extraer_urls(markdown: str) -> list[str]:
"""URLs http(s) del README, sin comentarios HTML, deduplicadas en orden."""
sin_comentarios = COMENTARIO_HTML.sub("", markdown)
vistas: dict[str, None] = {}
for m in LINK_MARKDOWN.finditer(sin_comentarios):
vistas.setdefault(limpiar_url(m.group(1)), None)
for m in URL_SUELTA.finditer(sin_comentarios):
vistas.setdefault(limpiar_url(m.group(0)), None)
return [u for u in vistas if u]
def pedir(url: str, metodo: str) -> int:
"""Hace la peticion y devuelve el codigo HTTP. Propaga errores de red."""
req = urllib.request.Request(url, method=metodo)
req.add_header("User-Agent", USER_AGENT)
req.add_header("Accept", "*/*")
try:
with urllib.request.urlopen(req, timeout=TIMEOUT_HTTP) as resp: