forked from Boris-code/feapder
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathparser_control.py
More file actions
724 lines (622 loc) · 32.5 KB
/
parser_control.py
File metadata and controls
724 lines (622 loc) · 32.5 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
# -*- coding: utf-8 -*-
"""
Created on 2017-01-03 16:06
---------
@summary: parser 控制类
---------
@author: Boris
@email: boris_liu@foxmail.com
"""
import random
import threading
import time
from collections.abc import Iterable
import feapder.setting as setting
import feapder.utils.tools as tools
from feapder.buffer.item_buffer import ItemBuffer
from feapder.db.memory_db import MemoryDB
from feapder.network.item import Item
from feapder.network.request import Request
from feapder.utils import metrics
from feapder.utils.log import log
class PaserControl(threading.Thread):
DOWNLOAD_EXCEPTION = "download_exception"
DOWNLOAD_SUCCESS = "download_success"
DOWNLOAD_TOTAL = "download_total"
PAESERS_EXCEPTION = "parser_exception"
is_show_tip = False
# 实时统计已做任务数及失败任务数，若失败任务数/已做任务数>0.5 则报警
_success_task_count = 0
_failed_task_count = 0
def __init__(self, collector, redis_key, request_buffer, item_buffer):
super(PaserControl, self).__init__()
self._parsers = []
self._collector = collector
self._redis_key = redis_key
self._request_buffer = request_buffer
self._item_buffer = item_buffer
self._thread_stop = False
self._wait_task_time = 0
def run(self):
self._thread_stop = False
while not self._thread_stop:
try:
requests = self._collector.get_requests(setting.SPIDER_TASK_COUNT)
if not requests:
if not self.is_show_tip:
log.debug("parser 等待任务...")
self.is_show_tip = True
# log.debug('parser 等待任务{}...'.format(tools.format_seconds(self._wait_task_time)))
time.sleep(1)
self._wait_task_time += 1
continue
self.is_show_tip = False
self.deal_requests(requests)
except Exception as e:
log.exception(e)
time.sleep(3)
def is_not_task(self):
return self.is_show_tip
@classmethod
def get_task_status_count(cls):
return cls._failed_task_count, cls._success_task_count
def deal_requests(self, requests):
for request in requests:
response = None
request_redis = request["request_redis"]
request = request["request_obj"]
del_request_redis_after_item_to_db = False
del_request_redis_after_request_to_db = False
for parser in self._parsers:
if parser.name == request.parser_name:
used_download_midware_enable = False
try:
# 记录需下载的文档
self.record_download_status(
PaserControl.DOWNLOAD_TOTAL, parser.name
)
# 解析request
if request.auto_request:
request_temp = None
response = None
# 下载中间件
if request.download_midware:
if isinstance(request.download_midware, (list, tuple)):
request_temp = request
for download_midware in request.download_midware:
download_midware = (
download_midware
if callable(download_midware)
else tools.get_method(
parser, download_midware
)
)
request_temp = download_midware(request_temp)
else:
download_midware = (
request.download_midware
if callable(request.download_midware)
else tools.get_method(
parser, request.download_midware
)
)
request_temp = download_midware(request)
elif request.download_midware != False:
request_temp = parser.download_midware(request)
# 请求
if request_temp:
if (
isinstance(request_temp, (tuple, list))
and len(request_temp) == 2
):
request_temp, response = request_temp
if not isinstance(request_temp, Request):
raise Exception(
"download_midware need return a request, but received type: {}".format(
type(request_temp)
)
)
used_download_midware_enable = True
if not response:
response = (
request_temp.get_response()
if not setting.RESPONSE_CACHED_USED
else request_temp.get_response_from_cached(
save_cached=False
)
)
else:
response = (
request.get_response()
if not setting.RESPONSE_CACHED_USED
else request.get_response_from_cached(
save_cached=False
)
)
if response == None:
raise Exception(
"连接超时 url: %s" % (request.url or request_temp.url)
)
else:
response = None
# 校验
if parser.validate(request, response) == False:
continue
if request.callback: # 如果有parser的回调函数，则用回调处理
callback_parser = (
request.callback
if callable(request.callback)
else tools.get_method(parser, request.callback)
)
results = callback_parser(request, response)
else: # 否则默认用parser处理
results = parser.parse(request, response)
if results and not isinstance(results, Iterable):
raise Exception(
"%s.%s返回值必须可迭代"
% (parser.name, request.callback or "parse")
)
# 标识上一个result是什么
result_type = 0 # 0\1\2 (初始值\request\item)
# 此处判断是request 还是 item
for result in results or []:
if isinstance(result, Request):
result_type = 1
# 给request的 parser_name 赋值
result.parser_name = result.parser_name or parser.name
# 判断是同步的callback还是异步的
if result.request_sync: # 同步
request_dict = {
"request_obj": result,
"request_redis": None,
}
requests.append(request_dict)
else: # 异步
# 将next_request 入库
self._request_buffer.put_request(result)
del_request_redis_after_request_to_db = True
elif isinstance(result, Item):
result_type = 2
# 将item入库
self._item_buffer.put_item(result)
# 需删除正在做的request
del_request_redis_after_item_to_db = True
elif callable(result): # result为可执行的无参函数
if (
result_type == 2
): # item 的 callback，buffer里的item均入库后再执行
self._item_buffer.put_item(result)
del_request_redis_after_item_to_db = True
else: # result_type == 1: # request 的 callback，buffer里的request均入库后再执行。可能有的parser直接返回callback
self._request_buffer.put_request(result)
del_request_redis_after_request_to_db = True
# else:
# raise TypeError('Expect Request、Item、callback func, bug get type: {}'.format(type(result)))
except Exception as e:
exception_type = (
str(type(e)).replace("<class '", "").replace("'>", "")
)
if exception_type.startswith("requests"):
# 记录下载失败的文档
self.record_download_status(
PaserControl.DOWNLOAD_EXCEPTION, parser.name
)
else:
# 记录解析程序异常
self.record_download_status(
PaserControl.PAESERS_EXCEPTION, parser.name
)
if setting.LOG_LEVEL == "DEBUG": # 只有debug模式下打印， 超时的异常篇幅太多
log.exception(e)
log.error(
"""
-------------- %s.%s error -------------
error %s
response %s
deal request %s
"""
% (
parser.name,
(
request.callback
and callable(request.callback)
and getattr(request.callback, "__name__")
or request.callback
)
or "parse",
str(e),
response,
tools.dumps_json(request.to_dict, indent=28)
if setting.LOG_LEVEL == "DEBUG"
else request,
)
)
request.error_msg = "%s: %s" % (exception_type, e)
request.response = str(response)
if "Invalid URL" in str(e):
request.is_abandoned = True
requests = parser.exception_request(request, response) or [
request
]
if not isinstance(requests, Iterable):
raise Exception(
"%s.%s返回值必须可迭代" % (parser.name, "exception_request")
)
for request in requests:
if callable(request):
self._request_buffer.put_request(request)
continue
if not isinstance(request, Request):
raise Exception("exception_request 需 yield request")
if (
request.retry_times + 1 > setting.SPIDER_MAX_RETRY_TIMES
or request.is_abandoned
):
self.__class__._failed_task_count += 1 # 记录失败任务数
# 处理failed_request的返回值 request 或 func
results = parser.failed_request(request, response) or [
request
]
if not isinstance(results, Iterable):
raise Exception(
"%s.%s返回值必须可迭代"
% (parser.name, "failed_request")
)
for result in results:
if isinstance(result, Request):
if setting.SAVE_FAILED_REQUEST:
if used_download_midware_enable:
# 去掉download_midware 添加的属性
original_request = (
Request.from_dict(
eval(request_redis)
)
if request_redis
else result
)
original_request.error_msg = (
request.error_msg
)
original_request.response = (
request.response
)
self._request_buffer.put_failed_request(
original_request
)
else:
self._request_buffer.put_failed_request(
result
)
elif callable(result):
self._request_buffer.put_request(result)
elif isinstance(result, Item):
self._item_buffer.put_item(result)
del_request_redis_after_request_to_db = True
else:
# 将 requests 重新入库 爬取
request.retry_times += 1
request.filter_repeat = False
log.info(
"""
入库 等待重试
url %s
重试次数 %s
最大允许重试次数 %s"""
% (
request.url,
request.retry_times,
setting.SPIDER_MAX_RETRY_TIMES,
)
)
if used_download_midware_enable:
# 去掉download_midware 添加的属性 使用原来的requests
original_request = (
Request.from_dict(eval(request_redis))
if request_redis
else request
)
if hasattr(request, "error_msg"):
original_request.error_msg = request.error_msg
if hasattr(request, "response"):
original_request.response = request.response
original_request.retry_times = request.retry_times
original_request.filter_repeat = (
request.filter_repeat
)
self._request_buffer.put_request(original_request)
else:
self._request_buffer.put_request(request)
del_request_redis_after_request_to_db = True
else:
# 记录下载成功的文档
self.record_download_status(
PaserControl.DOWNLOAD_SUCCESS, parser.name
)
# 记录成功任务数
self.__class__._success_task_count += 1
# 缓存下载成功的文档
if setting.RESPONSE_CACHED_ENABLE:
request.save_cached(
response=response,
expire_time=setting.RESPONSE_CACHED_EXPIRE_TIME,
)
finally:
# 释放浏览器
if response and hasattr(response, "browser"):
request._webdriver_pool.put(response.browser)
break
# 删除正在做的request 跟随item优先
if request_redis:
if del_request_redis_after_item_to_db:
self._item_buffer.put_item(request_redis)
elif del_request_redis_after_request_to_db:
self._request_buffer.put_del_request(request_redis)
else:
self._request_buffer.put_del_request(request_redis)
if setting.SPIDER_SLEEP_TIME:
if (
isinstance(setting.SPIDER_SLEEP_TIME, (tuple, list))
and len(setting.SPIDER_SLEEP_TIME) == 2
):
sleep_time = random.randint(
int(setting.SPIDER_SLEEP_TIME[0]), int(setting.SPIDER_SLEEP_TIME[1])
)
time.sleep(sleep_time)
else:
time.sleep(setting.SPIDER_SLEEP_TIME)
def record_download_status(self, status, spider):
"""
记录html等文档下载状态
@return:
"""
metrics.emit_counter(f"{spider}:{status}", 1, classify="document")
def stop(self):
self._thread_stop = True
self._started.clear()
def add_parser(self, parser):
self._parsers.append(parser)
class AirSpiderParserControl(PaserControl):
is_show_tip = False
# 实时统计已做任务数及失败任务数，若失败任务数/已做任务数>0.5 则报警
_success_task_count = 0
_failed_task_count = 0
def __init__(self, memory_db: MemoryDB, item_buffer: ItemBuffer):
super(PaserControl, self).__init__()
self._parsers = []
self._memory_db = memory_db
self._thread_stop = False
self._wait_task_time = 0
self._item_buffer = item_buffer
def run(self):
while not self._thread_stop:
try:
requests = self._memory_db.get()
if not requests:
if not self.is_show_tip:
log.debug("parser 等待任务...")
self.is_show_tip = True
time.sleep(1)
self._wait_task_time += 1
continue
self.is_show_tip = False
self.deal_requests([requests])
except Exception as e:
log.exception(e)
time.sleep(3)
def deal_requests(self, requests):
for request in requests:
response = None
for parser in self._parsers:
if parser.name == request.parser_name:
try:
# 记录需下载的文档
self.record_download_status(
PaserControl.DOWNLOAD_TOTAL, parser.name
)
# 解析request
if request.auto_request:
request_temp = None
response = None
# 下载中间件
if request.download_midware:
if isinstance(request.download_midware, (list, tuple)):
request_temp = request
for download_midware in request.download_midware:
download_midware = (
download_midware
if callable(download_midware)
else tools.get_method(
parser, download_midware
)
)
request_temp = download_midware(request_temp)
else:
download_midware = (
request.download_midware
if callable(request.download_midware)
else tools.get_method(
parser, request.download_midware
)
)
request_temp = download_midware(request)
elif request.download_midware != False:
request_temp = parser.download_midware(request)
# 请求
if request_temp:
if (
isinstance(request_temp, (tuple, list))
and len(request_temp) == 2
):
request_temp, response = request_temp
if not isinstance(request_temp, Request):
raise Exception(
"download_midware need return a request, but received type: {}".format(
type(request_temp)
)
)
request = request_temp
if not response:
response = (
request.get_response()
if not setting.RESPONSE_CACHED_USED
else request.get_response_from_cached(
save_cached=False
)
)
else:
response = None
# 校验
if parser.validate(request, response) == False:
continue
if request.callback: # 如果有parser的回调函数，则用回调处理
callback_parser = (
request.callback
if callable(request.callback)
else tools.get_method(parser, request.callback)
)
results = callback_parser(request, response)
else: # 否则默认用parser处理
results = parser.parse(request, response)
if results and not isinstance(results, Iterable):
raise Exception(
"%s.%s返回值必须可迭代"
% (parser.name, request.callback or "parse")
)
# 此处判断是request 还是 item
for result in results or []:
if isinstance(result, Request):
# 给request的 parser_name 赋值
result.parser_name = result.parser_name or parser.name
# 判断是同步的callback还是异步的
if result.request_sync: # 同步
requests.append(result)
else: # 异步
# 将next_request 入库
self._memory_db.add(result)
elif isinstance(result, Item):
self._item_buffer.put_item(result)
except Exception as e:
exception_type = (
str(type(e)).replace("<class '", "").replace("'>", "")
)
if exception_type.startswith("requests"):
# 记录下载失败的文档
self.record_download_status(
PaserControl.DOWNLOAD_EXCEPTION, parser.name
)
else:
# 记录解析程序异常
self.record_download_status(
PaserControl.PAESERS_EXCEPTION, parser.name
)
if setting.LOG_LEVEL == "DEBUG": # 只有debug模式下打印， 超时的异常篇幅太多
log.exception(e)
log.error(
"""
-------------- %s.%s error -------------
error %s
response %s
deal request %s
"""
% (
parser.name,
(
request.callback
and callable(request.callback)
and getattr(request.callback, "__name__")
or request.callback
)
or "parse",
str(e),
response,
tools.dumps_json(request.to_dict, indent=28)
if setting.LOG_LEVEL == "DEBUG"
else request,
)
)
request.error_msg = "%s: %s" % (exception_type, e)
request.response = str(response)
if "Invalid URL" in str(e):
request.is_abandoned = True
requests = parser.exception_request(request, response) or [
request
]
if not isinstance(requests, Iterable):
raise Exception(
"%s.%s返回值必须可迭代" % (parser.name, "exception_request")
)
for request in requests:
if not isinstance(request, Request):
raise Exception("exception_request 需 yield request")
if (
request.retry_times + 1 > setting.SPIDER_MAX_RETRY_TIMES
or request.is_abandoned
):
self.__class__._failed_task_count += 1 # 记录失败任务数
# 处理failed_request的返回值 request 或 func
results = parser.failed_request(request, response) or [
request
]
if not isinstance(results, Iterable):
raise Exception(
"%s.%s返回值必须可迭代"
% (parser.name, "failed_request")
)
log.info(
"""
任务超过最大重试次数，丢弃
url %s
重试次数 %s
最大允许重试次数 %s"""
% (
request.url,
request.retry_times,
setting.SPIDER_MAX_RETRY_TIMES,
)
)
else:
# 将 requests 重新入库 爬取
request.retry_times += 1
request.filter_repeat = False
log.info(
"""
入库 等待重试
url %s
重试次数 %s
最大允许重试次数 %s"""
% (
request.url,
request.retry_times,
setting.SPIDER_MAX_RETRY_TIMES,
)
)
self._memory_db.add(request)
else:
# 记录下载成功的文档
self.record_download_status(
PaserControl.DOWNLOAD_SUCCESS, parser.name
)
# 记录成功任务数
self.__class__._success_task_count += 1
# 缓存下载成功的文档
if setting.RESPONSE_CACHED_ENABLE:
request.save_cached(
response=response,
expire_time=setting.RESPONSE_CACHED_EXPIRE_TIME,
)
finally:
# 释放浏览器
if response and hasattr(response, "browser"):
request._webdriver_pool.put(response.browser)
break
if setting.SPIDER_SLEEP_TIME:
if (
isinstance(setting.SPIDER_SLEEP_TIME, (tuple, list))
and len(setting.SPIDER_SLEEP_TIME) == 2
):
sleep_time = random.randint(
int(setting.SPIDER_SLEEP_TIME[0]), int(setting.SPIDER_SLEEP_TIME[1])
)
time.sleep(sleep_time)
else:
time.sleep(setting.SPIDER_SLEEP_TIME)