Files
val-blog/tmp/lightpanda_search_debug.py
T

77 lines
3.2 KiB
Python

import asyncio, json, urllib.request
async def recv_one(reader):
b1 = await reader.readexactly(2)
opcode = b1[0] & 0x0F
masked_len = b1[1]
length = masked_len & 0x7F
if length == 126:
length = int.from_bytes(await reader.readexactly(2), 'big')
elif length == 127:
length = int.from_bytes(await reader.readexactly(8), 'big')
if masked_len & 0x80:
mask = await reader.readexactly(4)
payload = await reader.readexactly(length) if length else b''
payload = bytes(b ^ mask[i % 4] for i, b in enumerate(payload))
else:
payload = await reader.readexactly(length) if length else b''
return opcode, payload
async def send_text(writer, obj):
data = json.dumps(obj).encode()
mask = b'ABCD'
frame = bytearray([0x81])
n = len(data)
if n < 126:
frame.append(0x80 | n)
elif n < (1<<16):
frame.append(0x80 | 126); frame += n.to_bytes(2,'big')
else:
frame.append(0x80 | 127); frame += n.to_bytes(8,'big')
frame += mask + bytes(b ^ mask[i % 4] for i,b in enumerate(data))
writer.write(frame); await writer.drain()
async def main():
ws = json.load(urllib.request.urlopen('http://127.0.0.1:9222/json/version'))['webSocketDebuggerUrl']
hp = ws[len('ws://'):]
hostport, _, path = hp.partition('/')
host, port = hostport.split(':'); port = int(port); path='/' + path
reader, writer = await asyncio.open_connection(host, port)
req = f'GET {path} HTTP/1.1\r\nHost: {host}:{port}\r\nUpgrade: websocket\r\nConnection: Upgrade\r\nSec-WebSocket-Key: dGhlIHNhbXBsZSBub25jZQ==\r\nSec-WebSocket-Version: 13\r\n\r\n'
writer.write(req.encode()); await writer.drain(); await reader.readuntil(b'\r\n\r\n')
next_id = 1
async def call(method, params=None, sessionId=None):
nonlocal next_id
cid = next_id; next_id += 1
msg = {'id': cid, 'method': method}
if params is not None: msg['params'] = params
if sessionId is not None: msg['sessionId'] = sessionId
await send_text(writer, msg)
while True:
op, payload = await recv_one(reader)
if op != 1: continue
data = json.loads(payload.decode(errors='ignore'))
if data.get('id') == cid:
return data
tid = (await call('Target.createTarget', {'url':'about:blank'}))['result']['targetId']
sid = (await call('Target.attachToTarget', {'targetId': tid, 'flatten': True}))['result']['sessionId']
await call('Page.enable', sessionId=sid)
await call('Runtime.enable', sessionId=sid)
await call('Page.navigate', {'url':'https://www.google.com/search?q=lightpanda'}, sessionId=sid)
await asyncio.sleep(5)
exprs = {
'title': 'document.title',
'url': 'location.href',
'body': 'document.body ? document.body.innerText.slice(0,1500) : "NO_BODY"',
'html': 'document.documentElement ? document.documentElement.outerHTML.slice(0,1500) : "NO_HTML"',
'anchors': 'document.querySelectorAll("a").length'
}
for k,e in exprs.items():
r = await call('Runtime.evaluate', {'expression': e, 'returnByValue': True}, sessionId=sid)
print('@@'+k)
print(r['result']['result'].get('value'))
writer.close(); await writer.wait_closed()
asyncio.run(main())