study-tool
16346159c2
- 新增 platforms/gdgxk.py：base64 登录 → ssoItlmsGxkTicket 换票进 jsxx → /uc/store/courseRegister 取课程 → updateViewTime1 心跳上报进度（无需真播） - platforms/__init__.py 注册；配套抓包脚本与自测脚本 - CHANGELOG / OPTIMIZATION / todo 同步，版本升到 0.0.2
128 lines
4.0 KiB
Python
128 lines
4.0 KiB
Python
"""广东省教师继续教育平台抓包工具（一次性取证用，不参与运行）。
|
||
|
||
用法：
|
||
python script/capture-jsglpt.py [分钟数]
|
||
|
||
行为：开一个有头 Chromium（持久 profile，登录态会保留），打开 jsglpt 登录页，
|
||
把你在窗口里操作期间产生的 XHR/fetch 全量落到 data/capture-jsglpt-<时间>.jsonl，
|
||
同时每 3 秒把 cookie 快照写到 data/capture-jsglpt-cookies.json。
|
||
"""
|
||
import json
|
||
import os
|
||
import sys
|
||
import time
|
||
|
||
from playwright.sync_api import sync_playwright
|
||
|
||
ROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
|
||
DATA = os.path.join(ROOT, "data")
|
||
LOGIN = "https://jsglpt.gds.edu.cn/login.jsp"
|
||
MINUTES = float(sys.argv[1]) if len(sys.argv) > 1 else 40
|
||
|
||
os.makedirs(DATA, exist_ok=True)
|
||
STAMP = time.strftime("%Y%m%d-%H%M%S")
|
||
JSONL = os.path.join(DATA, "capture-jsglpt-%s.jsonl" % STAMP)
|
||
COOKIES = os.path.join(DATA, "capture-jsglpt-cookies.json")
|
||
PROFILE = os.path.join(DATA, ".gd-profile")
|
||
|
||
out = open(JSONL, "a", encoding="utf-8")
|
||
seen = 0
|
||
|
||
|
||
def emit(rec):
|
||
global seen
|
||
seen += 1
|
||
rec["n"] = seen
|
||
out.write(json.dumps(rec, ensure_ascii=False) + "\n")
|
||
out.flush()
|
||
print(" %-4s %s %s -> %s" % (rec.get("rt", "doc"), rec.get("method", ""),
|
||
rec.get("url", "")[:150], rec.get("status", "")), flush=True)
|
||
|
||
|
||
def on_response(r):
|
||
try:
|
||
req = r.request
|
||
rt = req.resource_type
|
||
if rt not in ("xhr", "fetch", "document"):
|
||
return
|
||
h = {}
|
||
try:
|
||
h = dict(r.headers or {})
|
||
except Exception:
|
||
pass
|
||
body = ""
|
||
# 只留文本类响应，视频/图片跳过
|
||
if not (r.url or "").lower().split("?")[0].endswith((".mp4", ".m3u8", ".ts", ".png", ".jpg", ".gif", ".woff", ".woff2", ".css", ".js")):
|
||
try:
|
||
body = r.text()[:8000]
|
||
except Exception:
|
||
body = "<binary>"
|
||
emit({
|
||
"t": time.strftime("%H:%M:%S"),
|
||
"rt": rt,
|
||
"method": req.method,
|
||
"url": r.url,
|
||
"req_headers": dict(req.headers or {}),
|
||
"req": (req.post_data or "")[:4000],
|
||
"status": r.status,
|
||
"resp_headers": h,
|
||
"resp": body,
|
||
})
|
||
except Exception:
|
||
pass
|
||
|
||
|
||
def main():
|
||
print("抓包输出：%s" % JSONL, flush=True)
|
||
with sync_playwright() as p:
|
||
ctx = p.chromium.launch_persistent_context(
|
||
PROFILE, headless=False,
|
||
args=["--disable-blink-features=AutomationControlled"],
|
||
viewport={"width": 1440, "height": 900},
|
||
)
|
||
hooked = set()
|
||
|
||
def hook(page):
|
||
if id(page) in hooked:
|
||
return
|
||
hooked.add(id(page))
|
||
page.on("response", on_response)
|
||
print("[页面] %s" % (page.url or "about:blank"), flush=True)
|
||
|
||
ctx.on("page", hook)
|
||
pg = ctx.pages[0] if ctx.pages else ctx.new_page()
|
||
hook(pg)
|
||
try:
|
||
pg.goto(LOGIN, wait_until="domcontentloaded", timeout=60000)
|
||
except Exception as e:
|
||
print("打开登录页失败：%s" % e, flush=True)
|
||
|
||
last = 0.0
|
||
t0 = time.time()
|
||
while time.time() - t0 < MINUTES * 60:
|
||
try:
|
||
now = time.time()
|
||
if now - last > 3:
|
||
last = now
|
||
with open(COOKIES, "w", encoding="utf-8") as f:
|
||
json.dump(ctx.cookies(), f, ensure_ascii=False, indent=1)
|
||
ctx.pages[0].wait_for_timeout(1000)
|
||
except Exception:
|
||
# 用户把所有页面关掉了，收工
|
||
break
|
||
try:
|
||
with open(COOKIES, "w", encoding="utf-8") as f:
|
||
json.dump(ctx.cookies(), f, ensure_ascii=False, indent=1)
|
||
except Exception:
|
||
pass
|
||
try:
|
||
ctx.close()
|
||
except Exception:
|
||
pass
|
||
out.close()
|
||
print("抓包结束：%d 条 → %s" % (seen, JSONL), flush=True)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
main()
|