cobweb-launcher 1.1.20__tar.gz → 1.1.22__tar.gz
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-launcher-1.1.20/cobweb_launcher.egg-info → cobweb-launcher-1.1.22}/PKG-INFO +1 -1
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb/crawlers/base_crawler.py +3 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb/launchers/launcher_pro.py +3 -2
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb/utils/oss.py +6 -1
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22/cobweb_launcher.egg-info}/PKG-INFO +1 -1
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/setup.py +1 -1
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/LICENSE +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/README.md +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb/__init__.py +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb/base/__init__.py +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb/base/common_queue.py +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb/base/decorators.py +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb/base/item.py +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb/base/log.py +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb/base/request.py +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb/base/response.py +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb/base/seed.py +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb/constant.py +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb/crawlers/__init__.py +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb/crawlers/file_crawler.py +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb/db/__init__.py +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb/db/redis_db.py +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb/exceptions/__init__.py +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb/exceptions/oss_db_exception.py +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb/launchers/__init__.py +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb/launchers/launcher.py +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb/pipelines/__init__.py +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb/pipelines/base_pipeline.py +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb/pipelines/loghub_pipeline.py +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb/setting.py +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb/utils/__init__.py +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb/utils/tools.py +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb_launcher.egg-info/SOURCES.txt +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb_launcher.egg-info/dependency_links.txt +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb_launcher.egg-info/requires.txt +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb_launcher.egg-info/top_level.txt +0 -0
- {cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/setup.cfg +0 -0
|
@@ -1,4 +1,5 @@
|
|
|
1
1
|
import threading
|
|
2
|
+
import time
|
|
2
3
|
|
|
3
4
|
from inspect import isgenerator
|
|
4
5
|
from typing import Union, Callable, Mapping
|
|
@@ -132,6 +133,8 @@ class Crawler(threading.Thread):
|
|
|
132
133
|
))
|
|
133
134
|
seed.params.retry += 1
|
|
134
135
|
self.launcher_queue['todo'].push(seed)
|
|
136
|
+
finally:
|
|
137
|
+
time.sleep(0.1)
|
|
135
138
|
|
|
136
139
|
def run(self):
|
|
137
140
|
for index in range(self.spider_thread_num):
|
|
@@ -125,12 +125,13 @@ class LauncherPro(Launcher):
|
|
|
125
125
|
seeds.append(seed.to_string)
|
|
126
126
|
if seeds:
|
|
127
127
|
self._db.zrem(self._todo, *seeds)
|
|
128
|
+
self._remove_doing_seeds(seeds)
|
|
128
129
|
if s_seeds:
|
|
129
130
|
self._db.done([self._todo, self._done], *s_seeds)
|
|
131
|
+
self._remove_doing_seeds(s_seeds)
|
|
130
132
|
if f_seeds:
|
|
131
133
|
self._db.done([self._todo, self._fail], *f_seeds)
|
|
132
|
-
|
|
133
|
-
self._remove_doing_seeds(seeds)
|
|
134
|
+
self._remove_doing_seeds(f_seeds)
|
|
134
135
|
|
|
135
136
|
if status:
|
|
136
137
|
time.sleep(self._done_queue_wait_seconds)
|
|
@@ -1,6 +1,7 @@
|
|
|
1
|
+
from typing import List
|
|
1
2
|
from cobweb import setting
|
|
2
3
|
from requests import Response
|
|
3
|
-
from oss2 import Auth, Bucket, models
|
|
4
|
+
from oss2 import Auth, Bucket, models, PartIterator
|
|
4
5
|
from cobweb.exceptions import oss_db_exception
|
|
5
6
|
from cobweb.base.decorators import decorator_oss_db
|
|
6
7
|
|
|
@@ -54,6 +55,10 @@ class OssUtil:
|
|
|
54
55
|
"""分片上传"""
|
|
55
56
|
return self._client.upload_part(key, upload_id, position, data)
|
|
56
57
|
|
|
58
|
+
def list_part(self, key, upload_id): # -> List[models.ListPartsResult]:
|
|
59
|
+
"""获取分片列表"""
|
|
60
|
+
return [part_info for part_info in PartIterator(self._client, key, upload_id)]
|
|
61
|
+
|
|
57
62
|
@decorator_oss_db(exception=oss_db_exception.OssDBMergeError)
|
|
58
63
|
def merge(self, key, upload_id, parts=None) -> models.PutObjectResult:
|
|
59
64
|
"""合并分片"""
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{cobweb-launcher-1.1.20 → cobweb-launcher-1.1.22}/cobweb_launcher.egg-info/dependency_links.txt
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|