Files

51 lines
1.5 KiB
Python
Raw Permalink Normal View History

2026-11-16 20:45:22 +08:00
"""Probe gongzicp.com HTML/API structure."""
from __future__ import annotations
import json
import re
import requests
UA = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) Chrome/124.0.0.0"
BASE = "https://www.gongzicp.com"
def fetch(path: str) -> str:
url = path if path.startswith("http") else f"{BASE}{path}"
r = requests.get(url, headers={"User-Agent": UA, "Referer": BASE + "/"}, timeout=45)
print(f"GET {url} -> {r.status_code} len={len(r.text)}")
return r.text
def main() -> None:
html = fetch("/novel-429598.html")
# API hints
for line in html.splitlines():
lower = line.lower()
if any(k in lower for k in ("api", "chapter", "catalog", "novelid", "read")):
if len(line.strip()) < 300:
print(line.strip()[:200])
# chapter links
chapters = re.findall(r'href="([^"]*chapter[^"]*)"', html, re.I)
print("chapter hrefs sample:", chapters[:10])
chapters2 = re.findall(r'href="(/read/\d+[^"]*)"', html)
print("read hrefs:", chapters2[:10])
chapters3 = re.findall(r'novel-\d+', html)
print("novel ids in page:", list(set(chapters3))[:5])
print("html preview:", html[:2000])
# try search API guesses
for api in [
"/webapi/search/novel?keyword=测试",
"/api/search?keyword=测试",
"/search?keyword=测试",
]:
try:
t = fetch(api)
print(t[:500])
except Exception as exc:
print(api, exc)
if __name__ == "__main__":
main()