cobweb-launcher 1.1.13__py3-none-any.whl → 1.1.14__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.

Potentially problematic release.


This version of cobweb-launcher might be problematic. Click here for more details.

@@ -32,7 +32,7 @@ class Crawler(threading.Thread):
32
32
  @staticmethod
33
33
  def request(seed: Seed) -> Union[Request, BaseItem]:
34
34
  stream = True if setting.DOWNLOAD_MODEL else False
35
- return Request(seed.url, seed, stream=stream, timeout=5)
35
+ yield Request(seed.url, seed, stream=stream, timeout=5)
36
36
 
37
37
  @staticmethod
38
38
  def download(item: Request) -> Union[Seed, BaseItem, Response, str]:
@@ -43,12 +43,27 @@ class Crawler(threading.Thread):
43
43
  def parse(item: Response) -> BaseItem:
44
44
  pass
45
45
 
46
- def get(self) -> Seed:
46
+ def get_seed(self) -> Seed:
47
47
  return self.launcher_queue['todo'].pop()
48
48
 
49
+ def distribute(self, item, seed):
50
+ if isinstance(item, BaseItem):
51
+ self.upload_queue.push(item)
52
+ elif isinstance(item, Seed):
53
+ self.launcher_queue['new'].push(item)
54
+ elif isinstance(item, str) and item == DealModel.poll:
55
+ self.launcher_queue['todo'].push(seed)
56
+ elif isinstance(item, str) and item == DealModel.done:
57
+ self.launcher_queue['done'].push(seed)
58
+ elif isinstance(item, str) and item == DealModel.fail:
59
+ seed.identifier = DealModel.fail
60
+ self.launcher_queue['done'].push(seed)
61
+ else:
62
+ raise TypeError("yield value type error!")
63
+
49
64
  def spider(self):
50
65
  while True:
51
- seed = self.get()
66
+ seed = self.get_seed()
52
67
 
53
68
  if not seed:
54
69
  continue
@@ -58,63 +73,54 @@ class Crawler(threading.Thread):
58
73
  self.launcher_queue['done'].push(seed)
59
74
  continue
60
75
 
61
- item = self.request(seed)
62
-
63
- if isinstance(item, Request):
64
-
65
- download_iterators = self.download(item)
66
-
67
- if not isgenerator(download_iterators):
68
- raise TypeError("download function isn't a generator")
69
-
70
- seed_detail_log_info = download_log_info(seed.to_dict)
71
-
72
- try:
73
- for it in download_iterators:
74
- if isinstance(it, Response):
75
- response_detail_log_info = download_log_info(it.to_dict)
76
- logger.info(LogTemplate.download_info.format(
77
- detail=seed_detail_log_info, retry=item.seed.params.retry,
78
- priority=item.seed.params.priority,
79
- seed_version=item.seed.params.seed_version,
80
- identifier=item.seed.identifier or "",
81
- status=it.response, response=response_detail_log_info
82
- ))
83
- parse_iterators = self.parse(it)
84
- if not isgenerator(parse_iterators):
85
- raise TypeError("parse function isn't a generator")
86
- for upload_item in parse_iterators:
87
- if not isinstance(upload_item, BaseItem):
88
- raise TypeError("upload_item isn't BaseItem subclass")
89
- self.upload_queue.push(upload_item)
90
- elif isinstance(it, BaseItem):
91
- self.upload_queue.push(it)
92
- elif isinstance(it, Seed):
93
- self.launcher_queue['new'].push(it)
94
- elif isinstance(it, str) and it == DealModel.poll:
95
- self.launcher_queue['todo'].push(item)
96
- break
97
- elif isinstance(it, str) and it == DealModel.done:
98
- self.launcher_queue['done'].push(seed)
99
- break
100
- elif isinstance(it, str) and it == DealModel.fail:
101
- seed.params.identifier = DealModel.fail
102
- self.launcher_queue['done'].push(seed)
103
- break
104
- else:
105
- raise TypeError("yield value type error!")
106
-
107
- except Exception as e:
108
- logger.info(LogTemplate.download_exception.format(
109
- detail=seed_detail_log_info, retry=seed.params.retry,
110
- priority=seed.params.priority, seed_version=seed.params.seed_version,
111
- identifier=seed.identifier or "", exception=e
112
- ))
113
- seed.params.retry += 1
114
- self.launcher_queue['todo'].push(seed)
115
-
116
- elif isinstance(item, BaseItem):
117
- self.upload_queue.push(item)
76
+ seed_detail_log_info = download_log_info(seed.to_dict)
77
+
78
+ request_iterators = self.request(seed)
79
+
80
+ if not isgenerator(request_iterators):
81
+ raise TypeError("request function isn't a generator!")
82
+
83
+ for request_item in request_iterators:
84
+
85
+ if isinstance(request_item, BaseItem):
86
+ self.upload_queue.push(request_item)
87
+
88
+ elif isinstance(request_item, Request):
89
+ try:
90
+ download_iterators = self.download(request_item)
91
+ if not isgenerator(download_iterators):
92
+ raise TypeError("download function isn't a generator")
93
+ for download_item in download_iterators:
94
+ if isinstance(download_item, Response):
95
+ response_detail_log_info = download_log_info(download_item.to_dict)
96
+ logger.info(LogTemplate.download_info.format(
97
+ detail=seed_detail_log_info,
98
+ retry=seed.params.retry,
99
+ priority=seed.params.priority,
100
+ seed_version=seed.params.seed_version,
101
+ identifier=seed.identifier or "",
102
+ status=download_item.response,
103
+ response=response_detail_log_info
104
+ ))
105
+ parse_iterators = self.parse(download_item)
106
+ if not isgenerator(parse_iterators):
107
+ raise TypeError("parse function isn't a generator")
108
+ for parse_item in parse_iterators:
109
+ if isinstance(parse_item, Response):
110
+ raise TypeError("upload_item can't be a Response instance")
111
+ self.distribute(parse_item, seed)
112
+ else:
113
+ self.distribute(download_item, seed)
114
+ except Exception as e:
115
+ logger.info(LogTemplate.download_exception.format(
116
+ detail=seed_detail_log_info,
117
+ retry=seed.params.retry,
118
+ priority=seed.params.priority,
119
+ seed_version=seed.params.seed_version,
120
+ identifier=seed.identifier or "", exception=e
121
+ ))
122
+ seed.params.retry += 1
123
+ self.launcher_queue['todo'].push(seed)
118
124
 
119
125
  def run(self):
120
126
  for index in range(self.spider_thread_num):
@@ -93,7 +93,7 @@ class Launcher(threading.Thread):
93
93
  @launcher.request
94
94
  def request(seed: Seed) -> Union[Request, BaseItem]:
95
95
  ...
96
- return Request(seed.url, seed)
96
+ yield Request(seed.url, seed)
97
97
  """
98
98
  def decorator(func):
99
99
  self.__CUSTOM_FUNC__["request"] = func
@@ -117,7 +117,7 @@ class LauncherPro(Launcher):
117
117
  seed = self.__LAUNCHER_QUEUE__['done'].pop()
118
118
  if not seed:
119
119
  break
120
- if seed.params.identifier == DealModel.fail:
120
+ if seed.identifier == DealModel.fail:
121
121
  f_seeds.append(seed.to_string)
122
122
  elif self._done_model == 1:
123
123
  s_seeds.append(seed.to_string)
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: cobweb-launcher
3
- Version: 1.1.13
3
+ Version: 1.1.14
4
4
  Summary: spider_hole
5
5
  Home-page: https://github.com/Juannie-PP/cobweb
6
6
  Author: Juannie-PP
@@ -10,23 +10,23 @@ cobweb/base/request.py,sha256=tEkgMVUfdQI-kZuzWuiit9P_q4Q9-_RZh9aXXpc0314,2352
10
10
  cobweb/base/response.py,sha256=eB1DWMXFCpn3cJ3yzgCRU1WeZAdayGDohRgdjdMUFN4,406
11
11
  cobweb/base/seed.py,sha256=QxlXztWjV8VvcHu-cTzyoDHaDvoX26iyoJKiWk64HnE,2759
12
12
  cobweb/crawlers/__init__.py,sha256=Rr3DTjD-abMA1_FYcQJZYNvQvcWMuEVcsIU6duqHrw4,75
13
- cobweb/crawlers/base_crawler.py,sha256=H-cUfrn79PAI8Z7Xv_NhW-9J0G-SiBU4wtzymzAJMYc,4961
13
+ cobweb/crawlers/base_crawler.py,sha256=U8MwxPlj0ld3o9dvUegcX-9arw8KvtbGUNe_LZUcjMQ,5325
14
14
  cobweb/crawlers/file_crawler.py,sha256=2Sjbdgxzqd41WykKUQE3QQlGai3T8k-pmHNmPlTchjQ,4454
15
15
  cobweb/db/__init__.py,sha256=ut0iEyBLjcJL06WNG_5_d4hO5PJWvDrKWMkDOdmgh2M,30
16
16
  cobweb/db/redis_db.py,sha256=NNI2QkRV1hEZI-z-COEncXt88z3pZN6wusKlcQzc8V4,4304
17
17
  cobweb/exceptions/__init__.py,sha256=E9SHnJBbhD7fOgPFMswqyOf8SKRDrI_i25L0bSpohvk,32
18
18
  cobweb/exceptions/oss_db_exception.py,sha256=iP_AImjNHT3-Iv49zCFQ3rdLnlvuHa3h2BXApgrOYpA,636
19
19
  cobweb/launchers/__init__.py,sha256=qwlkEJVri7dvCgi45aX3lqAmQS0HrPicAipDvH75kew,69
20
- cobweb/launchers/launcher.py,sha256=XSZrrtg9ge3GLFnMY_AHuo8n1-QJSmY7j_XsheQu0rk,5708
21
- cobweb/launchers/launcher_pro.py,sha256=T4mgSBqFkbU64EF6Fo_oMxzWldD_-l0rC-zFEZxqBQU,6593
20
+ cobweb/launchers/launcher.py,sha256=LQdlpaF4fafEX01_3B9CB6hD-6YMPag6QOGl9rDprNE,5707
21
+ cobweb/launchers/launcher_pro.py,sha256=20o-Yd_JAdzJPchpilCtCd61hrf90LKkxXcCjm2azhQ,6586
22
22
  cobweb/pipelines/__init__.py,sha256=xanY-Z1d7zRR5JhCdW2htzrAywnKBkigiaUlTFa6of0,80
23
23
  cobweb/pipelines/base_pipeline.py,sha256=fYnWf79GmhufXpcnMa3te18SbmnVeYLwxfyo-zLd9CY,1577
24
24
  cobweb/pipelines/loghub_pipeline.py,sha256=cjPO6w6UJ0jNw2fVvdX0BCdlm58T7dmYXlxzXOBpvfY,1027
25
25
  cobweb/utils/__init__.py,sha256=JTE4sBfHnKHhD6w9Auk0MIT7O9BMOamCeryhlHNx3Zg,47
26
26
  cobweb/utils/oss.py,sha256=qAl05ybL2Jp6KFjHDHVMfmeBHQmDKPtZleHjHAY7LZc,3277
27
27
  cobweb/utils/tools.py,sha256=bVd3iRGBvwhohQAH7AXTTjbmQ54Z35K0O-fatEyhePU,1249
28
- cobweb_launcher-1.1.13.dist-info/LICENSE,sha256=z1rxSIGOyzcSb3orZxFPxzx-0C1vTocmswqBNxpKfEk,1063
29
- cobweb_launcher-1.1.13.dist-info/METADATA,sha256=ShOTXcWNMBOaLR50TU0QFjR25Ae9aZ-PNyBgwTkxckE,1246
30
- cobweb_launcher-1.1.13.dist-info/WHEEL,sha256=ewwEueio1C2XeHTvT17n8dZUJgOvyCWCt0WVNLClP9o,92
31
- cobweb_launcher-1.1.13.dist-info/top_level.txt,sha256=4GETBGNsKqiCUezmT-mJn7tjhcDlu7nLIV5gGgHBW4I,7
32
- cobweb_launcher-1.1.13.dist-info/RECORD,,
28
+ cobweb_launcher-1.1.14.dist-info/LICENSE,sha256=z1rxSIGOyzcSb3orZxFPxzx-0C1vTocmswqBNxpKfEk,1063
29
+ cobweb_launcher-1.1.14.dist-info/METADATA,sha256=FoDq1JfDihDH-hEYOfYNpVcJSGHM44yWHLkWj2aUmJQ,1246
30
+ cobweb_launcher-1.1.14.dist-info/WHEEL,sha256=ewwEueio1C2XeHTvT17n8dZUJgOvyCWCt0WVNLClP9o,92
31
+ cobweb_launcher-1.1.14.dist-info/top_level.txt,sha256=4GETBGNsKqiCUezmT-mJn7tjhcDlu7nLIV5gGgHBW4I,7
32
+ cobweb_launcher-1.1.14.dist-info/RECORD,,