import re import requests html = requests.get("https://www.gongzicp.com/", timeout=30).text for m in re.finditer(r"/assets/[A-Za-z0-9_.-]+\.js", html): name = m.group() if "Home" in name or "Type" in name or "Search" in name: print(name) # grep all js from index.eef719ce for webapi paths t = requests.get("https://www.gongzicp.com/assets/index.eef719ce.js", timeout=60).text for m in re.finditer(r"/[a-zA-Z]+/[a-zA-Z]+[a-zA-Z0-9]*", t): s = m.group() if "novel" in s.lower() or "search" in s.lower() or "home" in s.lower() or "type" in s.lower(): if len(s) < 40: pass for m in re.finditer(r"url:\s*[\"']/[^\"']+[\"']", t): s = m.group() if any(k in s for k in ("novel", "search", "home", "type", "rank")): print(s)