cobweb-launcher 1.0.9__tar.gz → 1.1.1__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-1.0.9/cobweb_launcher.egg-info → cobweb-launcher-1.1.1}/PKG-INFO +1 -1
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb/crawlers/base_crawler.py +2 -1
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb/db/redis_db.py +1 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb/launchers/launcher_pro.py +2 -5
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb/setting.py +1 -1
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1/cobweb_launcher.egg-info}/PKG-INFO +1 -1
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/setup.py +1 -1
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/LICENSE +0 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/README.md +0 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb/__init__.py +0 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb/base/__init__.py +0 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb/base/common_queue.py +0 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb/base/decorators.py +0 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb/base/item.py +0 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb/base/log.py +0 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb/base/request.py +0 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb/base/response.py +0 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb/base/seed.py +0 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb/constant.py +0 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb/crawlers/__init__.py +0 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb/crawlers/file_crawler.py +0 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb/db/__init__.py +0 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb/exceptions/__init__.py +0 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb/exceptions/oss_db_exception.py +0 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb/launchers/__init__.py +0 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb/launchers/launcher.py +0 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb/pipelines/__init__.py +0 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb/pipelines/base_pipeline.py +0 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb/pipelines/loghub_pipeline.py +0 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb/utils/__init__.py +0 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb/utils/oss.py +0 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb/utils/tools.py +0 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb_launcher.egg-info/SOURCES.txt +0 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb_launcher.egg-info/dependency_links.txt +0 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb_launcher.egg-info/requires.txt +0 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/cobweb_launcher.egg-info/top_level.txt +0 -0
- {cobweb-launcher-1.0.9 → cobweb-launcher-1.1.1}/setup.cfg +0 -0
|
@@ -37,7 +37,7 @@ class Crawler(threading.Thread):
|
|
|
37
37
|
@staticmethod
|
|
38
38
|
def download(item: Request) -> Union[Seed, BaseItem, Response, str]:
|
|
39
39
|
response = item.download()
|
|
40
|
-
yield Response(item.seed, response)
|
|
40
|
+
yield Response(item.seed, response, **item.to_dict)
|
|
41
41
|
|
|
42
42
|
@staticmethod
|
|
43
43
|
def parse(item: Response) -> BaseItem:
|
|
@@ -54,6 +54,7 @@ class Crawler(threading.Thread):
|
|
|
54
54
|
continue
|
|
55
55
|
|
|
56
56
|
elif seed.params.retry >= self.max_retries:
|
|
57
|
+
seed.params.identifier = DealModel.fail
|
|
57
58
|
self.launcher_queue['done'].push(seed)
|
|
58
59
|
continue
|
|
59
60
|
|
|
@@ -16,7 +16,6 @@ class LauncherPro(Launcher):
|
|
|
16
16
|
self._fail = "{%s:%s}:fail" % (project, task)
|
|
17
17
|
self._heartbeat = "heartbeat:%s_%s" % (project, task)
|
|
18
18
|
self._reset_lock = "lock:reset:%s_%s" % (project, task)
|
|
19
|
-
self._heartbeat_lock = "lock:heartbeat:%s_%s" % (project, task)
|
|
20
19
|
self._db = RedisDB()
|
|
21
20
|
|
|
22
21
|
self._heartbeat_start_event = threading.Event()
|
|
@@ -29,10 +28,8 @@ class LauncherPro(Launcher):
|
|
|
29
28
|
def _execute_heartbeat(self):
|
|
30
29
|
while not self._stop.is_set():
|
|
31
30
|
if self._heartbeat_start_event.is_set():
|
|
32
|
-
|
|
33
|
-
|
|
34
|
-
time.sleep(1)
|
|
35
|
-
time.sleep(0.5)
|
|
31
|
+
self._db.setex(self._heartbeat, 3)
|
|
32
|
+
time.sleep(2)
|
|
36
33
|
|
|
37
34
|
def _reset(self):
|
|
38
35
|
"""
|
|
@@ -23,8 +23,8 @@ 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_CHUNK_SIZE = 10 * 1024 ** 2
|
|
26
27
|
OSS_MIN_UPLOAD_SIZE = 1024
|
|
27
|
-
OSS_CHUNK_SIZE = 1024 ** 2
|
|
28
28
|
|
|
29
29
|
# 采集器选择
|
|
30
30
|
CRAWLER = "cobweb.crawlers.CrawlerAir"
|
|
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-1.0.9 → cobweb-launcher-1.1.1}/cobweb_launcher.egg-info/dependency_links.txt
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|