crawlo 1.4.1__py3-none-any.whl → 1.4.2__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 crawlo might be problematic. Click here for more details.

crawlo/__version__.py CHANGED
@@ -1 +1 @@
1
- __version__ = '1.4.1'
1
+ __version__ = '1.4.2'
crawlo/commands/run.py CHANGED
@@ -23,7 +23,7 @@ from crawlo.crawler import CrawlerProcess
23
23
  from crawlo.project import get_settings, _find_project_root
24
24
  # 使用新的统一初始化系统
25
25
  from crawlo.initialization import initialize_framework
26
- from crawlo.initialization import get_framework_initializer
26
+ from crawlo.core import get_framework_initializer
27
27
  from crawlo.utils.log import get_logger
28
28
 
29
29
  # 延迟获取logger,确保在日志系统配置之后获取
@@ -55,8 +55,13 @@ class AioHttpDownloader(DownloaderBase):
55
55
  family=0, # 允许IPv4和IPv6
56
56
  )
57
57
 
58
- # 超时控制
59
- timeout = ClientTimeout(total=timeout_secs)
58
+ # 超时控制 - 增加更多超时设置
59
+ timeout = ClientTimeout(
60
+ total=timeout_secs,
61
+ connect=timeout_secs/2, # 连接超时
62
+ sock_read=timeout_secs, # 读取超时
63
+ sock_connect=timeout_secs/2 # socket连接超时
64
+ )
60
65
 
61
66
  # 请求追踪
62
67
  trace_config = TraceConfig()
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: crawlo
3
- Version: 1.4.1
3
+ Version: 1.4.2
4
4
  Summary: Crawlo 是一款基于异步IO的高性能Python爬虫框架,支持分布式抓取。
5
5
  Home-page: https://github.com/crawl-coder/Crawlo.git
6
6
  Author: crawl-coder
@@ -1,5 +1,5 @@
1
1
  crawlo/__init__.py,sha256=WD-F_HxUb9ad2v7J_yipTK4wwENCzIYwa7AF14eL4sg,2288
2
- crawlo/__version__.py,sha256=6ImxnR8EAFBMtiyEcHsEjoEJrEuzUcOFUzWJTeupvpM,22
2
+ crawlo/__version__.py,sha256=Gom1_ABKKkZoIghfDiYvSntLG2OKXC64sJD2Xm8bUKc,22
3
3
  crawlo/cli.py,sha256=OXprmcTUbFK02ptw_Gq8Gk4-ZCU-WEMJgzU1ztgP6Bk,2327
4
4
  crawlo/config.py,sha256=dNoNyTkXLe2msQ7bZx3YTQItk1m49nIg5-g89FQDNwE,9486
5
5
  crawlo/config_validator.py,sha256=gsiLqf5swWd9ISDvoLqCdG7iSXr-ZdBPD4iT6ug1ua4,11239
@@ -17,7 +17,7 @@ crawlo/commands/check.py,sha256=7pD43s97DD-fSLO9OEOuNcNr7o-2g94rJULL8fUzdaI,2260
17
17
  crawlo/commands/genspider.py,sha256=HhtvBLkIuhYtJUzom6PquItiC22vU9LNpOkjDUiqdM4,4937
18
18
  crawlo/commands/help.py,sha256=gwfHibRpdYDmZO6waUMOEn8SMJ_ubdjL-prD5fiuVY8,4973
19
19
  crawlo/commands/list.py,sha256=BqlPjBa5FLotjAlyZ3-nGmXg5cWcCNbHi8U5znb2_D8,5722
20
- crawlo/commands/run.py,sha256=NKVNOxJHZYr4aMEOcwmXRcQuDId1HltocvW8ufF_jBU,12838
20
+ crawlo/commands/run.py,sha256=gQ14PN3ZxsRNapRsyGZ4qdhbqzh70EnuS2YPaIUA8q0,12828
21
21
  crawlo/commands/startproject.py,sha256=aqKRJarKqTf5XjJnGXwjRpp0uYF16LreFbwwQLGpK-0,16070
22
22
  crawlo/commands/stats.py,sha256=8wTubR1RQ1JPTlpOKArcGcQ39bM-0cuH27lDpndnwPQ,6014
23
23
  crawlo/commands/utils.py,sha256=Psfu2tKrmDloMq0WnfXLaxx0lJFitMZ-FWS3HAIrziQ,5382
@@ -28,7 +28,7 @@ crawlo/core/scheduler.py,sha256=C2V23SIm1VGdi3A41TThB3zE99QFxTnsJp4SDOvSaBE,1256
28
28
  crawlo/data/__init__.py,sha256=8MgDxcMhx-emFARcLAw_ODOZNz0neYBcx7kEbzothd8,116
29
29
  crawlo/data/user_agents.py,sha256=6V34lYHREWV5ZR5wH-1pCnr1Y3ZYC7iMLfC6vZHyhZQ,9697
30
30
  crawlo/downloader/__init__.py,sha256=PB8oluLFMX2PBmeb3NBKkM6GaceX0ujFId8t2URy1ks,8624
31
- crawlo/downloader/aiohttp_downloader.py,sha256=rkCgEfX_s7w-cRK2ZoX43Unt9C7pPPYP64q22ShJMso,9107
31
+ crawlo/downloader/aiohttp_downloader.py,sha256=nlsq2CE-NcmT7nsNEENWC66YlWDx_JzS-eA-P2cvw_Q,9323
32
32
  crawlo/downloader/cffi_downloader.py,sha256=BpA1q6Udz7sSXJ0gX94xGnzy8cdgK-vlr_Q6YA4QIxE,10243
33
33
  crawlo/downloader/httpx_downloader.py,sha256=7jfQfvAtfk8yD_mvwUbWLhYOxMM7r1nudiU7m_Jl9wc,12037
34
34
  crawlo/downloader/hybrid_downloader.py,sha256=4SzOPEwBlSZVzUAWR3DyxMx2Tsx15YrpBvQS4it4Vps,8028
@@ -302,8 +302,8 @@ tests/verify_distributed.py,sha256=krnYYA5Qx9xXDMWc9YF5DxPSplGvawDg2n0l-3CAqoM,3
302
302
  tests/verify_log_fix.py,sha256=TD7M1R22NxLqQPufvgE-H33u9tUjyz-rSR2ayIXozRU,4225
303
303
  tests/scrapy_comparison/ofweek_scrapy.py,sha256=2Hvpi6DRTubUxBy6RyJApQxMQONPLc1zWjKTQO_i5U4,5652
304
304
  tests/scrapy_comparison/scrapy_test.py,sha256=5sw7jOHhaTmQ8bsUd1TiolAUTRQYQOe-f49HPfysqbI,5466
305
- crawlo-1.4.1.dist-info/METADATA,sha256=tDmbPTJeTIF-s2ZhOLup_Uh5xghOixlqneUGIVHZa00,33235
306
- crawlo-1.4.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
307
- crawlo-1.4.1.dist-info/entry_points.txt,sha256=5HoVoTSPxI8SCa5B7pQYxLSrkOdiunyO9tqNsLMv52g,43
308
- crawlo-1.4.1.dist-info/top_level.txt,sha256=keG_67pbZ_wZL2dmDRA9RMaNHTaV_x_oxZ9DKNgwvR0,22
309
- crawlo-1.4.1.dist-info/RECORD,,
305
+ crawlo-1.4.2.dist-info/METADATA,sha256=IwT9XfhtTQOUvMyKss9cne9PjX5RuWpiOkwMVu6zV6c,33235
306
+ crawlo-1.4.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
307
+ crawlo-1.4.2.dist-info/entry_points.txt,sha256=5HoVoTSPxI8SCa5B7pQYxLSrkOdiunyO9tqNsLMv52g,43
308
+ crawlo-1.4.2.dist-info/top_level.txt,sha256=keG_67pbZ_wZL2dmDRA9RMaNHTaV_x_oxZ9DKNgwvR0,22
309
+ crawlo-1.4.2.dist-info/RECORD,,
File without changes