cobweb-launcher 1.0.5__py3-none-any.whl → 1.0.7__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.
- cobweb/crawlers/base_crawler.py +1 -1
- cobweb/crawlers/file_crawler.py +0 -6
- cobweb/setting.py +1 -1
- cobweb/utils/tools.py +1 -1
- {cobweb_launcher-1.0.5.dist-info → cobweb_launcher-1.0.7.dist-info}/METADATA +1 -1
- {cobweb_launcher-1.0.5.dist-info → cobweb_launcher-1.0.7.dist-info}/RECORD +9 -9
- {cobweb_launcher-1.0.5.dist-info → cobweb_launcher-1.0.7.dist-info}/LICENSE +0 -0
- {cobweb_launcher-1.0.5.dist-info → cobweb_launcher-1.0.7.dist-info}/WHEEL +0 -0
- {cobweb_launcher-1.0.5.dist-info → cobweb_launcher-1.0.7.dist-info}/top_level.txt +0 -0
cobweb/crawlers/base_crawler.py
CHANGED
|
@@ -71,7 +71,7 @@ class Crawler(threading.Thread):
|
|
|
71
71
|
try:
|
|
72
72
|
for it in download_iterators:
|
|
73
73
|
if isinstance(it, Response):
|
|
74
|
-
response_detail_log_info = download_log_info(it.to_dict
|
|
74
|
+
response_detail_log_info = download_log_info(it.to_dict)
|
|
75
75
|
logger.info(LogTemplate.download_info.format(
|
|
76
76
|
detail=seed_detail_log_info, retry=item.seed.params.retry,
|
|
77
77
|
priority=item.seed.params.priority,
|
cobweb/crawlers/file_crawler.py
CHANGED
|
@@ -20,8 +20,6 @@ class CrawlerAir(Crawler):
|
|
|
20
20
|
if CrawlerAir.oss_util.exists(key):
|
|
21
21
|
content_length = CrawlerAir.oss_util.head(key).content_length
|
|
22
22
|
yield Response(item.seed, "exists", bucket_name=bucket_name, data_size=content_length, **seed_dict)
|
|
23
|
-
# data, cols = download_meta(item.seed, bucket_name=bucket_name, data_size=content_length, **seed_dict)
|
|
24
|
-
# yield DownloadItem(item.seed, sid=item.seed.sid, cols=cols, data=data)
|
|
25
23
|
|
|
26
24
|
end = seed_dict.get("end", "")
|
|
27
25
|
start = seed_dict.get("start", "0")
|
|
@@ -80,15 +78,11 @@ class CrawlerAir(Crawler):
|
|
|
80
78
|
content_length += len(content)
|
|
81
79
|
CrawlerAir.oss_util.merge(key, upload_id)
|
|
82
80
|
yield Response(item.seed, response, bucket_name=bucket_name, data_size=content_length, **seed_dict)
|
|
83
|
-
# data, cols = download_meta(item.seed, bucket_name, data_size=content_length, **seed_dict)
|
|
84
|
-
# yield DownloadItem(item.seed, sid=item.seed.sid, cols=cols, data=data)
|
|
85
81
|
|
|
86
82
|
elif item.seed.params.identifier == "merge":
|
|
87
83
|
CrawlerAir.oss_util.merge(key, seed_dict["upload_id"])
|
|
88
84
|
content_length = CrawlerAir.oss_util.head(key).content_length
|
|
89
85
|
yield Response(item.seed, "merge", bucket_name=bucket_name, data_size=content_length, **seed_dict)
|
|
90
|
-
# data, cols = download_meta(item.seed, bucket_name, data_size=content_length, **seed_dict)
|
|
91
|
-
# yield DownloadItem(item.seed, sid=item.seed.sid, cols=cols, data=data)
|
|
92
86
|
except OssDBPutPartError:
|
|
93
87
|
yield Seed(seed_dict)
|
|
94
88
|
except OssDBMergeError:
|
cobweb/setting.py
CHANGED
|
@@ -23,7 +23,7 @@ OSS_BUCKET = os.getenv("OSS_BUCKET")
|
|
|
23
23
|
OSS_ENDPOINT = os.getenv("OSS_ENDPOINT")
|
|
24
24
|
OSS_ACCESS_KEY = os.getenv("OSS_ACCESS_KEY")
|
|
25
25
|
OSS_SECRET_KEY = os.getenv("OSS_SECRET_KEY")
|
|
26
|
-
OSS_MIN_UPLOAD_SIZE = 1024
|
|
26
|
+
OSS_MIN_UPLOAD_SIZE = 1024
|
|
27
27
|
OSS_CHUNK_SIZE = 1024 ** 2
|
|
28
28
|
|
|
29
29
|
# 采集器选择
|
cobweb/utils/tools.py
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
cobweb/__init__.py,sha256=IkGcdTU6fEBNyzWowcJSSMdErntFM1kmu4WUp1BgImU,45
|
|
2
2
|
cobweb/constant.py,sha256=Aw2ES_nohVRLTWylZp6WMiUAlgyw4kLbae7LpwdZ5y4,1867
|
|
3
|
-
cobweb/setting.py,sha256=
|
|
3
|
+
cobweb/setting.py,sha256=fYK8KgrZYwSoJC9ywsopAtV0mdRw0_MGAoYORgET01M,1949
|
|
4
4
|
cobweb/base/__init__.py,sha256=diiK5MygQaWjlWNLbW6eUIg-93O6glMGC9WLNM5jyOc,209
|
|
5
5
|
cobweb/base/common_queue.py,sha256=W7PPZZFl52j3Mc916T0imHj7oAUelA6aKJwW-FecDPE,872
|
|
6
6
|
cobweb/base/decorators.py,sha256=wDCaQ94aAZGxks9Ljc0aXq6omDXT1_yzFy83ZW6VbVI,930
|
|
@@ -10,8 +10,8 @@ cobweb/base/request.py,sha256=b08AtUSZjlFLEFIEw5uGS__FjU6QSldL20-UjZD0LbI,2128
|
|
|
10
10
|
cobweb/base/response.py,sha256=7h9TwCNqRlwM_fvNmid9zOoRfHbKB8ABSU0eaVUJdVo,405
|
|
11
11
|
cobweb/base/seed.py,sha256=XswH16eEd6iwIBpt71E2S_AsV5UVCcOEOBFoP0r5QRo,2900
|
|
12
12
|
cobweb/crawlers/__init__.py,sha256=1sMhQ0-NJxiff3IqF2aMCXkSXcJFzzoCKIayQ5go4aI,71
|
|
13
|
-
cobweb/crawlers/base_crawler.py,sha256
|
|
14
|
-
cobweb/crawlers/file_crawler.py,sha256=
|
|
13
|
+
cobweb/crawlers/base_crawler.py,sha256=snfjGYV9oZl3UnrxUcpAD9cK0n_rPeuyUYQkU1aCBrA,4891
|
|
14
|
+
cobweb/crawlers/file_crawler.py,sha256=MyuJP0v4Rn4kFxCKb7JRInlzzwj8NsY0-jOHhpLFpTk,9085
|
|
15
15
|
cobweb/db/__init__.py,sha256=ut0iEyBLjcJL06WNG_5_d4hO5PJWvDrKWMkDOdmgh2M,30
|
|
16
16
|
cobweb/db/redis_db.py,sha256=XE1ebIi_4e0KBKiyPdKX7l2lSgV5vhMwEhNDlAcsccU,4247
|
|
17
17
|
cobweb/exceptions/__init__.py,sha256=E9SHnJBbhD7fOgPFMswqyOf8SKRDrI_i25L0bSpohvk,32
|
|
@@ -24,9 +24,9 @@ cobweb/pipelines/base_pipeline.py,sha256=fYnWf79GmhufXpcnMa3te18SbmnVeYLwxfyo-zL
|
|
|
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=uD5aN2oVYImit3amE6TjxWMaTAcbAh9dCnpIQhf4M9Q,3238
|
|
27
|
-
cobweb/utils/tools.py,sha256=
|
|
28
|
-
cobweb_launcher-1.0.
|
|
29
|
-
cobweb_launcher-1.0.
|
|
30
|
-
cobweb_launcher-1.0.
|
|
31
|
-
cobweb_launcher-1.0.
|
|
32
|
-
cobweb_launcher-1.0.
|
|
27
|
+
cobweb/utils/tools.py,sha256=bVd3iRGBvwhohQAH7AXTTjbmQ54Z35K0O-fatEyhePU,1249
|
|
28
|
+
cobweb_launcher-1.0.7.dist-info/LICENSE,sha256=z1rxSIGOyzcSb3orZxFPxzx-0C1vTocmswqBNxpKfEk,1063
|
|
29
|
+
cobweb_launcher-1.0.7.dist-info/METADATA,sha256=vsC5TBqJEwb85vKo0PXhH84sO8YYtZPPeqI1WGLpwNY,1245
|
|
30
|
+
cobweb_launcher-1.0.7.dist-info/WHEEL,sha256=ewwEueio1C2XeHTvT17n8dZUJgOvyCWCt0WVNLClP9o,92
|
|
31
|
+
cobweb_launcher-1.0.7.dist-info/top_level.txt,sha256=4GETBGNsKqiCUezmT-mJn7tjhcDlu7nLIV5gGgHBW4I,7
|
|
32
|
+
cobweb_launcher-1.0.7.dist-info/RECORD,,
|
|
File without changes
|
|
File without changes
|
|
File without changes
|