zenx 0.6.1__py3-none-any.whl → 0.6.3__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
zenx/clients/http.py CHANGED
@@ -124,7 +124,7 @@ class CurlCffi(HttpClient):
124
124
  )
125
125
  recv_at = get_time()
126
126
  latency = recv_at - req_at
127
- self.logger.debug("response", status=response.status_code, url=url, impersonate=session.impersonate, client=self.name, requested_at=req_at, responded_at=recv_at, latency_ms=latency)
127
+ self.logger.debug("response", status=response.status_code, url=url, impersonate=impersonate, client=self.name, requested_at=req_at, responded_at=recv_at, latency_ms=latency)
128
128
  except Exception:
129
129
  self.logger.exception("request", url=url, client=self.name)
130
130
  raise
zenx/engine.py CHANGED
@@ -26,6 +26,16 @@ class Engine:
26
26
  self.shutdown_event.set()
27
27
 
28
28
 
29
+ async def _log_stats(self, spider: Spider) -> None:
30
+ while True:
31
+ await asyncio.sleep(60)
32
+ try:
33
+ rpm = spider.get_stats().get("rpm")
34
+ spider.logger.info("stats", rpm=rpm)
35
+ except asyncio.CancelledError:
36
+ break
37
+
38
+
29
39
  async def _execute(self, spider_name: str) -> None:
30
40
  loop = asyncio.get_running_loop()
31
41
  loop.add_signal_handler(signal.SIGINT, self._shutdown_handler)
@@ -48,6 +58,7 @@ class Engine:
48
58
 
49
59
  spider = spider_cls(client=client, pm=pm, logger=logger, settings=settings)
50
60
 
61
+ stats_task = asyncio.create_task(self._log_stats(spider))
51
62
  try:
52
63
  if self.forever:
53
64
  while not self.shutdown_event.is_set():
@@ -61,6 +72,15 @@ class Engine:
61
72
  finally:
62
73
  if self.shutdown_event.is_set():
63
74
  logger.info("shutdown", spider=spider_name)
75
+
76
+ stats_task.cancel()
77
+ try:
78
+ await stats_task
79
+ except asyncio.CancelledError:
80
+ pass
81
+ stats = spider.get_stats()
82
+ logger.info("summary", **stats)
83
+
64
84
  await client.close()
65
85
  await db.close()
66
86
  await pm.close_pipelines()
zenx/spiders/base.py CHANGED
@@ -1,5 +1,7 @@
1
1
  from __future__ import annotations
2
2
  from abc import ABC, abstractmethod
3
+ from collections import deque
4
+ import time
3
5
  from typing import ClassVar, Dict, List, Literal, Type
4
6
  from structlog import BoundLogger
5
7
 
@@ -44,6 +46,22 @@ class Spider(ABC):
44
46
  self.pm = pm
45
47
  self.logger = logger
46
48
  self.settings = settings
49
+ # stats
50
+ self.requests_timestamps = deque()
51
+ self.total_requests = 0
52
+
53
+
54
+ def get_stats(self) -> Dict:
55
+ # calculate RPM based on rolling window of 1 min
56
+ now = time.time()
57
+ # remove requests older than 60 sec
58
+ while self.requests_timestamps and self.requests_timestamps[0] < (now - 60):
59
+ self.requests_timestamps.popleft()
60
+ rpm = len(self.requests_timestamps)
61
+ return {
62
+ "rpm": rpm,
63
+ "total_requests": self.total_requests,
64
+ }
47
65
 
48
66
 
49
67
  @abstractmethod
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: zenx
3
- Version: 0.6.1
3
+ Version: 0.6.3
4
4
  Summary: mini-framework
5
5
  Requires-Python: >=3.12
6
6
  Requires-Dist: curl-cffi>=0.12.0
@@ -1,14 +1,14 @@
1
1
  zenx/cli.py,sha256=pHKhOTdqI6NQQoYK91waRIMpxCXLYtXEryzVaTbmvqc,2810
2
2
  zenx/debug_runner.py,sha256=B2Jd9A4_EHDa-ohLcwnFIxOV73FagTWXX2fl3qgwlpY,809
3
3
  zenx/discovery.py,sha256=YANVGzy2IG1fYruUud-11Y-ynyO6iEp3EjlHnhIQJQI,1014
4
- zenx/engine.py,sha256=VX2sDmEqvgfvkN1lDFNTgQIKuX1U1aobt-5WhoCgV_g,2350
4
+ zenx/engine.py,sha256=1rIX44wMjgGrvarVVe6uD3MQO9HJ31cBHSTPqo-qNE8,2948
5
5
  zenx/exceptions.py,sha256=BJXxzwwX2CU6inhppfblx8c8Z6Mhvsk7MAhQ1LAnhBg,37
6
6
  zenx/logger.py,sha256=UmEk0vV1mSCozV7z_DDgCCXdAManDr5wgkrhKiRQtyU,1651
7
7
  zenx/settings.py,sha256=Q0z3oGyVkhucRyqsraZQR1lAPSq1sjiGKmAkDCmQsA0,940
8
8
  zenx/utils.py,sha256=ozf3dpcH1KyDXh9coDe3NqzL8OS-1uA6SaQ8lfHfI40,587
9
9
  zenx/clients/__init__.py,sha256=CaAAuNa8DPyMdejR0KNSDDg_UzC3WxaTol5_QvwwwG8,132
10
10
  zenx/clients/database.py,sha256=GaIafQ2OkYJQ_sz2f6u7sZKn77VOReWun09hogk6dO0,6019
11
- zenx/clients/http.py,sha256=tkUN-1Lij1GFhxqTVry_mTWhB5XRNt_5t38mRoRdF84,5700
11
+ zenx/clients/http.py,sha256=MXXC0dYqd3mfuywsh4UMPXm0-9d0qoXHUky-ZC1DTE4,5692
12
12
  zenx/pipelines/__init__.py,sha256=IxkZ0UpEJdYjLdd-PMcC9PzzzArTBNNcpgKc7NiOe5Y,131
13
13
  zenx/pipelines/base.py,sha256=N_388z5DFMeaU6wMwcClZAbQFWKh4kpAF7eUJhpQevs,1863
14
14
  zenx/pipelines/google_rpc.py,sha256=F7p5ml9W1UliZbrDrF9MFNVKlCP5pG1WpO6rdmBgKp8,4707
@@ -19,9 +19,9 @@ zenx/resources/proto/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hS
19
19
  zenx/resources/proto/feed_pb2.py,sha256=ZyICOLnyuXekkvV4bAHZ1nE1-wwzcYYRRrmRJCMrSoo,2810
20
20
  zenx/resources/proto/feed_pb2_grpc.py,sha256=Mim6FfBgIMj0PmTqHk036nVUMJH3A6I3ts6r1j3bQF8,7441
21
21
  zenx/spiders/__init__.py,sha256=rs5LuqdM2MQlUYiTGJrzkYhzN8_SSLTrR7wGjSRrrSo,25
22
- zenx/spiders/base.py,sha256=KoMsT7ezwne1clTtP66dfvQGZPzdg2e7ygkM40h2QbA,1659
23
- zenx-0.6.1.dist-info/METADATA,sha256=OcOwmfvef4XORRAqIE1RrBbOP0dSiPcf5-_eyFWYnJM,1273
24
- zenx-0.6.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
25
- zenx-0.6.1.dist-info/entry_points.txt,sha256=8JXob2f1VtvzGFris-e9Usqywg7oca-cChDlH9moOZU,38
26
- zenx-0.6.1.dist-info/top_level.txt,sha256=JeXwvK86d7sB-2x-avugFnZIZa33zaHWKI8RHWJR6KY,5
27
- zenx-0.6.1.dist-info/RECORD,,
22
+ zenx/spiders/base.py,sha256=LaX29ArNIAiv8E8hUUpJxahBpRnGfskDlxx4hU0gsTg,2232
23
+ zenx-0.6.3.dist-info/METADATA,sha256=eoDHZHHXDTZwAkOx8yovY5VIJnjHV2XJcSHoft8stUg,1273
24
+ zenx-0.6.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
25
+ zenx-0.6.3.dist-info/entry_points.txt,sha256=8JXob2f1VtvzGFris-e9Usqywg7oca-cChDlH9moOZU,38
26
+ zenx-0.6.3.dist-info/top_level.txt,sha256=JeXwvK86d7sB-2x-avugFnZIZa33zaHWKI8RHWJR6KY,5
27
+ zenx-0.6.3.dist-info/RECORD,,
File without changes