crawlo 1.1.4__py3-none-any.whl → 1.1.5__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/__init__.py +61 -34
- crawlo/__version__.py +1 -1
- crawlo/cleaners/__init__.py +61 -0
- crawlo/cleaners/data_formatter.py +226 -0
- crawlo/cleaners/encoding_converter.py +126 -0
- crawlo/cleaners/text_cleaner.py +233 -0
- crawlo/cli.py +40 -40
- crawlo/commands/__init__.py +13 -13
- crawlo/commands/check.py +594 -594
- crawlo/commands/genspider.py +151 -151
- crawlo/commands/list.py +155 -155
- crawlo/commands/run.py +285 -285
- crawlo/commands/startproject.py +300 -196
- crawlo/commands/stats.py +188 -188
- crawlo/commands/utils.py +186 -186
- crawlo/config.py +309 -279
- crawlo/config_validator.py +253 -0
- crawlo/core/__init__.py +2 -2
- crawlo/core/engine.py +346 -172
- crawlo/core/processor.py +40 -40
- crawlo/core/scheduler.py +137 -166
- crawlo/crawler.py +1027 -1027
- crawlo/downloader/__init__.py +266 -242
- crawlo/downloader/aiohttp_downloader.py +220 -212
- crawlo/downloader/cffi_downloader.py +256 -251
- crawlo/downloader/httpx_downloader.py +259 -259
- crawlo/downloader/hybrid_downloader.py +214 -0
- crawlo/downloader/playwright_downloader.py +403 -0
- crawlo/downloader/selenium_downloader.py +473 -0
- crawlo/event.py +11 -11
- crawlo/exceptions.py +81 -81
- crawlo/extension/__init__.py +37 -37
- crawlo/extension/health_check.py +141 -141
- crawlo/extension/log_interval.py +57 -57
- crawlo/extension/log_stats.py +81 -81
- crawlo/extension/logging_extension.py +43 -43
- crawlo/extension/memory_monitor.py +104 -88
- crawlo/extension/performance_profiler.py +133 -117
- crawlo/extension/request_recorder.py +107 -107
- crawlo/filters/__init__.py +154 -154
- crawlo/filters/aioredis_filter.py +280 -242
- crawlo/filters/memory_filter.py +269 -269
- crawlo/items/__init__.py +23 -23
- crawlo/items/base.py +21 -21
- crawlo/items/fields.py +53 -53
- crawlo/items/items.py +104 -104
- crawlo/middleware/__init__.py +21 -21
- crawlo/middleware/default_header.py +32 -32
- crawlo/middleware/download_delay.py +28 -28
- crawlo/middleware/middleware_manager.py +135 -135
- crawlo/middleware/proxy.py +272 -248
- crawlo/middleware/request_ignore.py +30 -30
- crawlo/middleware/response_code.py +18 -18
- crawlo/middleware/response_filter.py +26 -26
- crawlo/middleware/retry.py +124 -124
- crawlo/mode_manager.py +206 -201
- crawlo/network/__init__.py +21 -21
- crawlo/network/request.py +338 -311
- crawlo/network/response.py +360 -271
- crawlo/pipelines/__init__.py +21 -21
- crawlo/pipelines/bloom_dedup_pipeline.py +156 -156
- crawlo/pipelines/console_pipeline.py +39 -39
- crawlo/pipelines/csv_pipeline.py +316 -316
- crawlo/pipelines/database_dedup_pipeline.py +224 -224
- crawlo/pipelines/json_pipeline.py +218 -218
- crawlo/pipelines/memory_dedup_pipeline.py +115 -115
- crawlo/pipelines/mongo_pipeline.py +131 -131
- crawlo/pipelines/mysql_pipeline.py +316 -316
- crawlo/pipelines/pipeline_manager.py +56 -56
- crawlo/pipelines/redis_dedup_pipeline.py +166 -162
- crawlo/project.py +153 -153
- crawlo/queue/pqueue.py +37 -37
- crawlo/queue/queue_manager.py +320 -307
- crawlo/queue/redis_priority_queue.py +277 -209
- crawlo/settings/__init__.py +7 -7
- crawlo/settings/default_settings.py +216 -278
- crawlo/settings/setting_manager.py +99 -99
- crawlo/spider/__init__.py +639 -639
- crawlo/stats_collector.py +59 -59
- crawlo/subscriber.py +130 -130
- crawlo/task_manager.py +30 -30
- crawlo/templates/crawlo.cfg.tmpl +10 -10
- crawlo/templates/project/__init__.py.tmpl +3 -3
- crawlo/templates/project/items.py.tmpl +17 -17
- crawlo/templates/project/middlewares.py.tmpl +110 -110
- crawlo/templates/project/pipelines.py.tmpl +97 -97
- crawlo/templates/project/run.py.tmpl +251 -251
- crawlo/templates/project/settings.py.tmpl +326 -279
- crawlo/templates/project/settings_distributed.py.tmpl +120 -0
- crawlo/templates/project/settings_gentle.py.tmpl +95 -0
- crawlo/templates/project/settings_high_performance.py.tmpl +152 -0
- crawlo/templates/project/settings_simple.py.tmpl +69 -0
- crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
- crawlo/templates/spider/spider.py.tmpl +141 -141
- crawlo/tools/__init__.py +183 -0
- crawlo/tools/anti_crawler.py +269 -0
- crawlo/tools/authenticated_proxy.py +241 -0
- crawlo/tools/data_validator.py +181 -0
- crawlo/tools/date_tools.py +36 -0
- crawlo/tools/distributed_coordinator.py +387 -0
- crawlo/tools/retry_mechanism.py +221 -0
- crawlo/tools/scenario_adapter.py +263 -0
- crawlo/utils/__init__.py +35 -7
- crawlo/utils/batch_processor.py +261 -0
- crawlo/utils/controlled_spider_mixin.py +439 -439
- crawlo/utils/date_tools.py +290 -233
- crawlo/utils/db_helper.py +343 -343
- crawlo/utils/enhanced_error_handler.py +360 -0
- crawlo/utils/env_config.py +106 -0
- crawlo/utils/error_handler.py +126 -0
- crawlo/utils/func_tools.py +82 -82
- crawlo/utils/large_scale_config.py +286 -286
- crawlo/utils/large_scale_helper.py +343 -343
- crawlo/utils/log.py +128 -128
- crawlo/utils/performance_monitor.py +285 -0
- crawlo/utils/queue_helper.py +175 -175
- crawlo/utils/redis_connection_pool.py +335 -0
- crawlo/utils/redis_key_validator.py +200 -0
- crawlo/utils/request.py +267 -267
- crawlo/utils/request_serializer.py +219 -219
- crawlo/utils/spider_loader.py +62 -62
- crawlo/utils/system.py +11 -11
- crawlo/utils/tools.py +4 -4
- crawlo/utils/url.py +39 -39
- {crawlo-1.1.4.dist-info → crawlo-1.1.5.dist-info}/METADATA +401 -403
- crawlo-1.1.5.dist-info/RECORD +185 -0
- examples/__init__.py +7 -7
- tests/__init__.py +7 -7
- tests/advanced_tools_example.py +276 -0
- tests/authenticated_proxy_example.py +237 -0
- tests/cleaners_example.py +161 -0
- tests/config_validation_demo.py +103 -0
- {examples → tests}/controlled_spider_example.py +205 -205
- tests/date_tools_example.py +181 -0
- tests/dynamic_loading_example.py +524 -0
- tests/dynamic_loading_test.py +105 -0
- tests/env_config_example.py +134 -0
- tests/error_handling_example.py +172 -0
- tests/redis_key_validation_demo.py +131 -0
- tests/response_improvements_example.py +145 -0
- tests/test_advanced_tools.py +149 -0
- tests/test_all_redis_key_configs.py +146 -0
- tests/test_authenticated_proxy.py +142 -0
- tests/test_cleaners.py +55 -0
- tests/test_comprehensive.py +147 -0
- tests/test_config_validator.py +194 -0
- tests/test_date_tools.py +124 -0
- tests/test_dynamic_downloaders_proxy.py +125 -0
- tests/test_dynamic_proxy.py +93 -0
- tests/test_dynamic_proxy_config.py +147 -0
- tests/test_dynamic_proxy_real.py +110 -0
- tests/test_edge_cases.py +304 -0
- tests/test_enhanced_error_handler.py +271 -0
- tests/test_env_config.py +122 -0
- tests/test_error_handler_compatibility.py +113 -0
- tests/test_final_validation.py +153 -153
- tests/test_framework_env_usage.py +104 -0
- tests/test_integration.py +357 -0
- tests/test_item_dedup_redis_key.py +123 -0
- tests/test_parsel.py +30 -0
- tests/test_performance.py +328 -0
- tests/test_proxy_health_check.py +32 -32
- tests/test_proxy_middleware_integration.py +136 -136
- tests/test_proxy_providers.py +56 -56
- tests/test_proxy_stats.py +19 -19
- tests/test_proxy_strategies.py +59 -59
- tests/test_queue_manager_redis_key.py +177 -0
- tests/test_redis_config.py +28 -28
- tests/test_redis_connection_pool.py +295 -0
- tests/test_redis_key_naming.py +182 -0
- tests/test_redis_key_validator.py +124 -0
- tests/test_redis_queue.py +224 -224
- tests/test_request_serialization.py +70 -70
- tests/test_response_improvements.py +153 -0
- tests/test_scheduler.py +241 -241
- tests/test_simple_response.py +62 -0
- tests/test_telecom_spider_redis_key.py +206 -0
- tests/test_template_content.py +88 -0
- tests/test_template_redis_key.py +135 -0
- tests/test_tools.py +154 -0
- tests/tools_example.py +258 -0
- crawlo/core/enhanced_engine.py +0 -190
- crawlo-1.1.4.dist-info/RECORD +0 -117
- {crawlo-1.1.4.dist-info → crawlo-1.1.5.dist-info}/WHEEL +0 -0
- {crawlo-1.1.4.dist-info → crawlo-1.1.5.dist-info}/entry_points.txt +0 -0
- {crawlo-1.1.4.dist-info → crawlo-1.1.5.dist-info}/top_level.txt +0 -0
crawlo/utils/url.py
CHANGED
|
@@ -1,40 +1,40 @@
|
|
|
1
|
-
from urllib.parse import urldefrag
|
|
2
|
-
from w3lib.url import add_or_replace_parameter
|
|
3
|
-
|
|
4
|
-
|
|
5
|
-
def escape_ajax(url: str) -> str:
|
|
6
|
-
"""
|
|
7
|
-
根据Google AJAX爬取规范转换URL(处理哈希片段#!):
|
|
8
|
-
https://developers.google.com/webmasters/ajax-crawling/docs/getting-started
|
|
9
|
-
|
|
10
|
-
规则说明:
|
|
11
|
-
1. 仅当URL包含 `#!` 时才转换(表示这是AJAX可爬取页面)
|
|
12
|
-
2. 将 `#!key=value` 转换为 `?_escaped_fragment_=key%3Dvalue`
|
|
13
|
-
3. 保留原始查询参数(如果有)
|
|
14
|
-
|
|
15
|
-
示例:
|
|
16
|
-
>>> escape_ajax("www.example.com/ajax.html#!key=value")
|
|
17
|
-
'www.example.com/ajax.html?_escaped_fragment_=key%3Dvalue'
|
|
18
|
-
>>> escape_ajax("www.example.com/ajax.html?k1=v1#!key=value")
|
|
19
|
-
'www.example.com/ajax.html?k1=v1&_escaped_fragment_=key%3Dvalue'
|
|
20
|
-
>>> escape_ajax("www.example.com/ajax.html#!")
|
|
21
|
-
'www.example.com/ajax.html?_escaped_fragment_='
|
|
22
|
-
|
|
23
|
-
非AJAX可爬取的URL(无#!)原样返回:
|
|
24
|
-
>>> escape_ajax("www.example.com/ajax.html#normal")
|
|
25
|
-
'www.example.com/ajax.html#normal'
|
|
26
|
-
"""
|
|
27
|
-
# 分离URL的基础部分和哈希片段
|
|
28
|
-
de_frag, frag = urldefrag(url)
|
|
29
|
-
|
|
30
|
-
# 仅处理以"!"开头的哈希片段(Google规范)
|
|
31
|
-
if not frag.startswith("!"):
|
|
32
|
-
return url # 不符合规则则原样返回
|
|
33
|
-
|
|
34
|
-
# 调用辅助函数添加 `_escaped_fragment_` 参数
|
|
35
|
-
return add_or_replace_parameter(de_frag, "_escaped_fragment_", frag[1:])
|
|
36
|
-
|
|
37
|
-
|
|
38
|
-
if __name__ == '__main__':
|
|
39
|
-
f = escape_ajax('http://example.com/page#!')
|
|
1
|
+
from urllib.parse import urldefrag
|
|
2
|
+
from w3lib.url import add_or_replace_parameter
|
|
3
|
+
|
|
4
|
+
|
|
5
|
+
def escape_ajax(url: str) -> str:
|
|
6
|
+
"""
|
|
7
|
+
根据Google AJAX爬取规范转换URL(处理哈希片段#!):
|
|
8
|
+
https://developers.google.com/webmasters/ajax-crawling/docs/getting-started
|
|
9
|
+
|
|
10
|
+
规则说明:
|
|
11
|
+
1. 仅当URL包含 `#!` 时才转换(表示这是AJAX可爬取页面)
|
|
12
|
+
2. 将 `#!key=value` 转换为 `?_escaped_fragment_=key%3Dvalue`
|
|
13
|
+
3. 保留原始查询参数(如果有)
|
|
14
|
+
|
|
15
|
+
示例:
|
|
16
|
+
>>> escape_ajax("www.example.com/ajax.html#!key=value")
|
|
17
|
+
'www.example.com/ajax.html?_escaped_fragment_=key%3Dvalue'
|
|
18
|
+
>>> escape_ajax("www.example.com/ajax.html?k1=v1#!key=value")
|
|
19
|
+
'www.example.com/ajax.html?k1=v1&_escaped_fragment_=key%3Dvalue'
|
|
20
|
+
>>> escape_ajax("www.example.com/ajax.html#!")
|
|
21
|
+
'www.example.com/ajax.html?_escaped_fragment_='
|
|
22
|
+
|
|
23
|
+
非AJAX可爬取的URL(无#!)原样返回:
|
|
24
|
+
>>> escape_ajax("www.example.com/ajax.html#normal")
|
|
25
|
+
'www.example.com/ajax.html#normal'
|
|
26
|
+
"""
|
|
27
|
+
# 分离URL的基础部分和哈希片段
|
|
28
|
+
de_frag, frag = urldefrag(url)
|
|
29
|
+
|
|
30
|
+
# 仅处理以"!"开头的哈希片段(Google规范)
|
|
31
|
+
if not frag.startswith("!"):
|
|
32
|
+
return url # 不符合规则则原样返回
|
|
33
|
+
|
|
34
|
+
# 调用辅助函数添加 `_escaped_fragment_` 参数
|
|
35
|
+
return add_or_replace_parameter(de_frag, "_escaped_fragment_", frag[1:])
|
|
36
|
+
|
|
37
|
+
|
|
38
|
+
if __name__ == '__main__':
|
|
39
|
+
f = escape_ajax('http://example.com/page#!')
|
|
40
40
|
print(f)
|