crawlo 1.2.8__py3-none-any.whl → 1.3.0__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 +63 -61
- crawlo/__version__.py +1 -1
- crawlo/cli.py +75 -75
- crawlo/commands/__init__.py +14 -14
- crawlo/commands/check.py +594 -594
- crawlo/commands/genspider.py +151 -151
- crawlo/commands/help.py +138 -138
- crawlo/commands/list.py +155 -155
- crawlo/commands/run.py +314 -323
- crawlo/commands/startproject.py +436 -436
- crawlo/commands/stats.py +187 -187
- crawlo/commands/utils.py +186 -186
- crawlo/config.py +312 -312
- crawlo/config_validator.py +277 -251
- crawlo/core/__init__.py +2 -2
- crawlo/core/engine.py +365 -365
- crawlo/core/processor.py +40 -40
- crawlo/core/scheduler.py +256 -251
- crawlo/crawler.py +1097 -1099
- crawlo/data/__init__.py +5 -5
- crawlo/data/user_agents.py +194 -107
- crawlo/downloader/__init__.py +273 -266
- crawlo/downloader/aiohttp_downloader.py +226 -228
- crawlo/downloader/cffi_downloader.py +245 -256
- crawlo/downloader/httpx_downloader.py +259 -259
- crawlo/downloader/hybrid_downloader.py +212 -212
- crawlo/downloader/playwright_downloader.py +402 -402
- crawlo/downloader/selenium_downloader.py +472 -472
- crawlo/event.py +11 -11
- crawlo/exceptions.py +81 -81
- crawlo/extension/__init__.py +39 -39
- 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 +45 -43
- crawlo/extension/memory_monitor.py +104 -104
- crawlo/extension/performance_profiler.py +133 -133
- crawlo/extension/request_recorder.py +107 -107
- crawlo/filters/__init__.py +154 -154
- crawlo/filters/aioredis_filter.py +234 -234
- crawlo/filters/memory_filter.py +269 -269
- crawlo/items/__init__.py +23 -23
- crawlo/items/base.py +21 -21
- crawlo/items/fields.py +52 -52
- crawlo/items/items.py +104 -104
- crawlo/middleware/__init__.py +21 -21
- crawlo/middleware/default_header.py +132 -132
- crawlo/middleware/download_delay.py +104 -104
- crawlo/middleware/middleware_manager.py +136 -136
- crawlo/middleware/offsite.py +114 -114
- crawlo/middleware/proxy.py +386 -368
- crawlo/middleware/request_ignore.py +86 -86
- crawlo/middleware/response_code.py +163 -163
- crawlo/middleware/response_filter.py +136 -136
- crawlo/middleware/retry.py +124 -124
- crawlo/middleware/simple_proxy.py +65 -0
- crawlo/mode_manager.py +212 -211
- crawlo/network/__init__.py +21 -21
- crawlo/network/request.py +379 -338
- crawlo/network/response.py +359 -359
- crawlo/pipelines/__init__.py +21 -21
- crawlo/pipelines/bloom_dedup_pipeline.py +157 -157
- crawlo/pipelines/console_pipeline.py +39 -39
- crawlo/pipelines/csv_pipeline.py +316 -316
- crawlo/pipelines/database_dedup_pipeline.py +223 -223
- 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 +317 -317
- crawlo/pipelines/pipeline_manager.py +74 -62
- crawlo/pipelines/redis_dedup_pipeline.py +167 -167
- crawlo/project.py +284 -315
- crawlo/queue/pqueue.py +37 -37
- crawlo/queue/queue_manager.py +379 -378
- crawlo/queue/redis_priority_queue.py +306 -306
- crawlo/settings/__init__.py +7 -7
- crawlo/settings/default_settings.py +216 -220
- crawlo/settings/setting_manager.py +175 -122
- crawlo/spider/__init__.py +639 -639
- crawlo/stats_collector.py +59 -59
- crawlo/subscriber.py +129 -129
- 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 +118 -118
- crawlo/templates/project/pipelines.py.tmpl +96 -96
- crawlo/templates/project/settings.py.tmpl +261 -288
- crawlo/templates/project/settings_distributed.py.tmpl +174 -157
- crawlo/templates/project/settings_gentle.py.tmpl +95 -100
- crawlo/templates/project/settings_high_performance.py.tmpl +125 -134
- crawlo/templates/project/settings_minimal.py.tmpl +30 -0
- crawlo/templates/project/settings_simple.py.tmpl +96 -98
- crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
- crawlo/templates/run.py.tmpl +47 -47
- crawlo/templates/spider/spider.py.tmpl +143 -143
- crawlo/tools/__init__.py +200 -182
- crawlo/tools/anti_crawler.py +268 -268
- crawlo/tools/authenticated_proxy.py +240 -240
- crawlo/{cleaners → tools}/data_formatter.py +225 -225
- crawlo/tools/data_validator.py +180 -180
- crawlo/tools/date_tools.py +290 -36
- crawlo/tools/distributed_coordinator.py +388 -387
- crawlo/{cleaners → tools}/encoding_converter.py +127 -126
- crawlo/tools/request_tools.py +83 -0
- crawlo/tools/retry_mechanism.py +224 -221
- crawlo/tools/scenario_adapter.py +262 -262
- crawlo/{cleaners → tools}/text_cleaner.py +232 -232
- crawlo/utils/__init__.py +35 -35
- crawlo/utils/batch_processor.py +259 -259
- crawlo/utils/controlled_spider_mixin.py +439 -439
- crawlo/utils/db_helper.py +343 -343
- crawlo/utils/enhanced_error_handler.py +356 -356
- crawlo/utils/env_config.py +142 -142
- crawlo/utils/error_handler.py +123 -123
- crawlo/utils/func_tools.py +82 -82
- crawlo/utils/large_scale_config.py +286 -286
- crawlo/utils/large_scale_helper.py +344 -344
- crawlo/utils/log.py +146 -128
- crawlo/utils/performance_monitor.py +285 -285
- crawlo/utils/queue_helper.py +175 -175
- crawlo/utils/redis_connection_pool.py +351 -351
- crawlo/utils/redis_key_validator.py +198 -198
- crawlo/utils/request.py +267 -267
- crawlo/utils/request_serializer.py +218 -218
- crawlo/utils/spider_loader.py +61 -61
- crawlo/utils/system.py +11 -11
- crawlo/utils/tools.py +4 -4
- crawlo/utils/url.py +39 -39
- {crawlo-1.2.8.dist-info → crawlo-1.3.0.dist-info}/METADATA +1011 -764
- crawlo-1.3.0.dist-info/RECORD +219 -0
- examples/__init__.py +7 -7
- tests/DOUBLE_CRAWLO_PREFIX_FIX_REPORT.md +81 -81
- tests/__init__.py +7 -7
- tests/advanced_tools_example.py +275 -275
- tests/authenticated_proxy_example.py +107 -237
- tests/cleaners_example.py +160 -160
- tests/config_validation_demo.py +143 -103
- tests/controlled_spider_example.py +205 -205
- tests/date_tools_example.py +180 -180
- tests/debug_pipelines.py +67 -0
- tests/dynamic_loading_example.py +523 -523
- tests/dynamic_loading_test.py +104 -104
- tests/env_config_example.py +133 -133
- tests/error_handling_example.py +171 -171
- tests/redis_key_validation_demo.py +130 -130
- tests/request_params_example.py +151 -0
- tests/response_improvements_example.py +144 -144
- tests/test_advanced_tools.py +148 -148
- tests/test_all_redis_key_configs.py +145 -145
- tests/test_authenticated_proxy.py +141 -141
- tests/test_cleaners.py +54 -54
- tests/test_comprehensive.py +146 -146
- tests/test_config_consistency.py +80 -80
- tests/test_config_merge.py +153 -0
- tests/test_config_validator.py +182 -193
- tests/test_crawlo_proxy_integration.py +109 -173
- tests/test_date_tools.py +123 -123
- tests/test_default_header_middleware.py +158 -158
- tests/test_distributed.py +65 -0
- tests/test_double_crawlo_fix.py +207 -207
- tests/test_double_crawlo_fix_simple.py +124 -124
- tests/test_download_delay_middleware.py +221 -221
- tests/test_downloader_proxy_compatibility.py +268 -268
- tests/test_dynamic_downloaders_proxy.py +124 -124
- tests/test_dynamic_proxy.py +92 -92
- tests/test_dynamic_proxy_config.py +146 -146
- tests/test_dynamic_proxy_real.py +109 -109
- tests/test_edge_cases.py +303 -303
- tests/test_enhanced_error_handler.py +270 -270
- tests/test_env_config.py +121 -121
- tests/test_error_handler_compatibility.py +112 -112
- tests/test_final_validation.py +153 -153
- tests/test_framework_env_usage.py +103 -103
- tests/test_integration.py +169 -357
- tests/test_item_dedup_redis_key.py +122 -122
- tests/test_mode_consistency.py +51 -51
- tests/test_offsite_middleware.py +221 -221
- tests/test_parsel.py +29 -29
- tests/test_performance.py +327 -327
- tests/test_proxy_api.py +264 -264
- tests/test_proxy_health_check.py +32 -32
- tests/test_proxy_middleware.py +121 -121
- tests/test_proxy_middleware_enhanced.py +216 -216
- tests/test_proxy_middleware_integration.py +136 -136
- tests/test_proxy_middleware_refactored.py +185 -0
- 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_double_crawlo.py +173 -173
- tests/test_queue_manager_redis_key.py +176 -176
- tests/test_random_user_agent.py +73 -0
- tests/test_real_scenario_proxy.py +195 -195
- tests/test_redis_config.py +28 -28
- tests/test_redis_connection_pool.py +294 -294
- tests/test_redis_key_naming.py +181 -181
- tests/test_redis_key_validator.py +123 -123
- tests/test_redis_queue.py +224 -224
- tests/test_request_ignore_middleware.py +182 -182
- tests/test_request_params.py +112 -0
- tests/test_request_serialization.py +70 -70
- tests/test_response_code_middleware.py +349 -349
- tests/test_response_filter_middleware.py +427 -427
- tests/test_response_improvements.py +152 -152
- tests/test_retry_middleware.py +241 -241
- tests/test_scheduler.py +252 -252
- tests/test_scheduler_config_update.py +133 -133
- tests/test_simple_response.py +61 -61
- tests/test_telecom_spider_redis_key.py +205 -205
- tests/test_template_content.py +87 -87
- tests/test_template_redis_key.py +134 -134
- tests/test_tools.py +159 -153
- tests/test_user_agents.py +97 -0
- tests/tools_example.py +260 -257
- tests/verify_distributed.py +117 -0
- crawlo/cleaners/__init__.py +0 -61
- crawlo/utils/date_tools.py +0 -290
- crawlo-1.2.8.dist-info/RECORD +0 -209
- {crawlo-1.2.8.dist-info → crawlo-1.3.0.dist-info}/WHEEL +0 -0
- {crawlo-1.2.8.dist-info → crawlo-1.3.0.dist-info}/entry_points.txt +0 -0
- {crawlo-1.2.8.dist-info → crawlo-1.3.0.dist-info}/top_level.txt +0 -0
|
@@ -0,0 +1,151 @@
|
|
|
1
|
+
#!/usr/bin/python
|
|
2
|
+
# -*- coding: UTF-8 -*-
|
|
3
|
+
"""
|
|
4
|
+
Request参数处理示例
|
|
5
|
+
"""
|
|
6
|
+
from crawlo.network.request import Request
|
|
7
|
+
|
|
8
|
+
|
|
9
|
+
def demo_get_params():
|
|
10
|
+
"""演示GET参数处理"""
|
|
11
|
+
print("=== GET参数处理演示 ===\n")
|
|
12
|
+
|
|
13
|
+
# 使用get_params参数
|
|
14
|
+
params = {"page": 1, "limit": 10, "search": "python"}
|
|
15
|
+
request = Request(
|
|
16
|
+
url="https://api.example.com/articles",
|
|
17
|
+
method="GET",
|
|
18
|
+
get_params=params
|
|
19
|
+
)
|
|
20
|
+
|
|
21
|
+
print(f"URL: {request.url}")
|
|
22
|
+
print(f"Method: {request.method}")
|
|
23
|
+
print()
|
|
24
|
+
|
|
25
|
+
|
|
26
|
+
def demo_form_data_with_get():
|
|
27
|
+
"""演示GET请求使用form_data"""
|
|
28
|
+
print("=== GET请求使用form_data演示 ===\n")
|
|
29
|
+
|
|
30
|
+
# GET请求使用form_data参数
|
|
31
|
+
form_data = {"category": "technology", "sort": "date"}
|
|
32
|
+
request = Request(
|
|
33
|
+
url="https://api.example.com/posts",
|
|
34
|
+
method="GET",
|
|
35
|
+
form_data=form_data
|
|
36
|
+
)
|
|
37
|
+
|
|
38
|
+
print(f"URL: {request.url}")
|
|
39
|
+
print(f"Method: {request.method}")
|
|
40
|
+
print()
|
|
41
|
+
|
|
42
|
+
|
|
43
|
+
def demo_form_data_with_post():
|
|
44
|
+
"""演示POST请求使用form_data"""
|
|
45
|
+
print("=== POST请求使用form_data演示 ===\n")
|
|
46
|
+
|
|
47
|
+
# POST请求使用form_data参数
|
|
48
|
+
form_data = {"username": "testuser", "password": "secret"}
|
|
49
|
+
request = Request(
|
|
50
|
+
url="https://api.example.com/login",
|
|
51
|
+
method="POST",
|
|
52
|
+
form_data=form_data
|
|
53
|
+
)
|
|
54
|
+
|
|
55
|
+
print(f"URL: {request.url}")
|
|
56
|
+
print(f"Method: {request.method}")
|
|
57
|
+
print(f"Body: {request.body.decode('utf-8')}")
|
|
58
|
+
print(f"Content-Type: {request.headers.get('Content-Type')}")
|
|
59
|
+
print()
|
|
60
|
+
|
|
61
|
+
|
|
62
|
+
def demo_json_body():
|
|
63
|
+
"""演示JSON请求体"""
|
|
64
|
+
print("=== JSON请求体演示 ===\n")
|
|
65
|
+
|
|
66
|
+
# 使用json_body参数
|
|
67
|
+
json_data = {"name": "John Doe", "email": "john@example.com", "age": 30}
|
|
68
|
+
request = Request(
|
|
69
|
+
url="https://api.example.com/users",
|
|
70
|
+
method="POST",
|
|
71
|
+
json_body=json_data
|
|
72
|
+
)
|
|
73
|
+
|
|
74
|
+
print(f"URL: {request.url}")
|
|
75
|
+
print(f"Method: {request.method}")
|
|
76
|
+
print(f"Body: {request.body.decode('utf-8')}")
|
|
77
|
+
print(f"Content-Type: {request.headers.get('Content-Type')}")
|
|
78
|
+
print()
|
|
79
|
+
|
|
80
|
+
|
|
81
|
+
def demo_combined_usage():
|
|
82
|
+
"""演示组合使用"""
|
|
83
|
+
print("=== 组合使用演示 ===\n")
|
|
84
|
+
|
|
85
|
+
# 复杂的请求示例
|
|
86
|
+
request = Request(
|
|
87
|
+
url="https://api.example.com/search",
|
|
88
|
+
method="GET",
|
|
89
|
+
get_params={"q": "python爬虫", "lang": "zh"},
|
|
90
|
+
headers={"User-Agent": "Crawlo/1.0", "Accept": "application/json"},
|
|
91
|
+
meta={"retries": 3, "priority": 1}
|
|
92
|
+
)
|
|
93
|
+
|
|
94
|
+
print(f"URL: {request.url}")
|
|
95
|
+
print(f"Method: {request.method}")
|
|
96
|
+
print(f"Headers: {request.headers}")
|
|
97
|
+
print(f"Meta: {request.meta}")
|
|
98
|
+
print()
|
|
99
|
+
|
|
100
|
+
|
|
101
|
+
if __name__ == '__main__':
|
|
102
|
+
# 运行演示
|
|
103
|
+
demo_get_params()
|
|
104
|
+
demo_form_data_with_get()
|
|
105
|
+
demo_form_data_with_post()
|
|
106
|
+
demo_json_body()
|
|
107
|
+
demo_combined_usage()
|
|
108
|
+
|
|
109
|
+
print("=== 在爬虫中使用Request参数 ===\n")
|
|
110
|
+
print("在爬虫项目中,您可以这样使用Request参数:")
|
|
111
|
+
print("""
|
|
112
|
+
from crawlo import Spider, Request
|
|
113
|
+
|
|
114
|
+
class ExampleSpider(Spider):
|
|
115
|
+
def start_requests(self):
|
|
116
|
+
# GET请求带参数
|
|
117
|
+
yield Request(
|
|
118
|
+
url="https://api.example.com/articles",
|
|
119
|
+
method="GET",
|
|
120
|
+
get_params={"page": 1, "limit": 20},
|
|
121
|
+
callback=self.parse_articles
|
|
122
|
+
)
|
|
123
|
+
|
|
124
|
+
# POST请求带表单数据
|
|
125
|
+
yield Request(
|
|
126
|
+
url="https://api.example.com/login",
|
|
127
|
+
method="POST",
|
|
128
|
+
form_data={"username": "user", "password": "pass"},
|
|
129
|
+
callback=self.parse_login
|
|
130
|
+
)
|
|
131
|
+
|
|
132
|
+
# POST请求带JSON数据
|
|
133
|
+
yield Request(
|
|
134
|
+
url="https://api.example.com/users",
|
|
135
|
+
method="POST",
|
|
136
|
+
json_body={"name": "John", "email": "john@example.com"},
|
|
137
|
+
callback=self.parse_user
|
|
138
|
+
)
|
|
139
|
+
|
|
140
|
+
async def parse_articles(self, response):
|
|
141
|
+
# 处理文章列表
|
|
142
|
+
pass
|
|
143
|
+
|
|
144
|
+
async def parse_login(self, response):
|
|
145
|
+
# 处理登录响应
|
|
146
|
+
pass
|
|
147
|
+
|
|
148
|
+
async def parse_user(self, response):
|
|
149
|
+
# 处理用户创建响应
|
|
150
|
+
pass
|
|
151
|
+
""")
|
|
@@ -1,145 +1,145 @@
|
|
|
1
|
-
#!/usr/bin/python
|
|
2
|
-
# -*- coding:UTF-8 -*-
|
|
3
|
-
"""
|
|
4
|
-
Response 改进功能使用示例
|
|
5
|
-
"""
|
|
6
|
-
from crawlo.network.response import Response
|
|
7
|
-
|
|
8
|
-
|
|
9
|
-
def demo_response_improvements():
|
|
10
|
-
"""演示Response改进功能"""
|
|
11
|
-
print("=== Response 改进功能演示 ===\n")
|
|
12
|
-
|
|
13
|
-
# 创建一个示例HTML响应
|
|
14
|
-
html_content = """
|
|
15
|
-
<html>
|
|
16
|
-
<head>
|
|
17
|
-
<title>Crawlo框架示例页面</title>
|
|
18
|
-
</head>
|
|
19
|
-
<body>
|
|
20
|
-
<div class="container">
|
|
21
|
-
<h1>产品列表</h1>
|
|
22
|
-
<div class="product-list">
|
|
23
|
-
<div class="product-item" data-id="1">
|
|
24
|
-
<h2>产品A</h2>
|
|
25
|
-
<p class="price">¥99.99</p>
|
|
26
|
-
<p class="description">这是产品A的描述信息</p>
|
|
27
|
-
<a href="/product/1" class="details-link">查看详情</a>
|
|
28
|
-
</div>
|
|
29
|
-
<div class="product-item" data-id="2">
|
|
30
|
-
<h2>产品B</h2>
|
|
31
|
-
<p class="price">¥149.99</p>
|
|
32
|
-
<p class="description">这是产品B的描述信息</p>
|
|
33
|
-
<a href="/product/2" class="details-link">查看详情</a>
|
|
34
|
-
</div>
|
|
35
|
-
<div class="product-item" data-id="3">
|
|
36
|
-
<h2>产品C</h2>
|
|
37
|
-
<p class="price">¥199.99</p>
|
|
38
|
-
<p class="description">这是产品C的描述信息</p>
|
|
39
|
-
<a href="/product/3" class="details-link">查看详情</a>
|
|
40
|
-
</div>
|
|
41
|
-
</div>
|
|
42
|
-
<div class="pagination">
|
|
43
|
-
<a href="/page/1" class="page-link">1</a>
|
|
44
|
-
<a href="/page/2" class="page-link active">2</a>
|
|
45
|
-
<a href="/page/3" class="page-link">3</a>
|
|
46
|
-
</div>
|
|
47
|
-
</div>
|
|
48
|
-
</body>
|
|
49
|
-
</html>
|
|
50
|
-
"""
|
|
51
|
-
|
|
52
|
-
# 创建Response对象
|
|
53
|
-
response = Response(
|
|
54
|
-
url="https://example.com/products",
|
|
55
|
-
body=html_content.encode('utf-8'),
|
|
56
|
-
headers={"content-type": "text/html; charset=utf-8"}
|
|
57
|
-
)
|
|
58
|
-
|
|
59
|
-
# 1. 演示 extract_text 方法(支持CSS和XPath)
|
|
60
|
-
print("1. 提取文本内容:")
|
|
61
|
-
title = response.extract_text('title')
|
|
62
|
-
print(f" 页面标题: {title}")
|
|
63
|
-
|
|
64
|
-
# 使用CSS选择器提取第一个产品名称
|
|
65
|
-
first_product_name = response.extract_text('.product-item:first-child h2')
|
|
66
|
-
print(f" 第一个产品名称 (CSS): {first_product_name}")
|
|
67
|
-
|
|
68
|
-
# 使用XPath选择器
|
|
69
|
-
first_product_name_xpath = response.extract_text('//div[@class="product-item"][1]/h2')
|
|
70
|
-
print(f" 第一个产品名称 (XPath): {first_product_name_xpath}")
|
|
71
|
-
|
|
72
|
-
# 使用默认值处理不存在的元素
|
|
73
|
-
non_exist = response.extract_text('.non-exist', default='未找到')
|
|
74
|
-
print(f" 不存在的元素: {non_exist}")
|
|
75
|
-
|
|
76
|
-
print()
|
|
77
|
-
|
|
78
|
-
# 2. 演示 extract_texts 方法(提取多个元素的文本)
|
|
79
|
-
print("2. 提取多个元素的文本:")
|
|
80
|
-
# 提取所有产品名称
|
|
81
|
-
product_names = response.extract_texts('.product-item h2')
|
|
82
|
-
print(f" 所有产品名称: {product_names}")
|
|
83
|
-
|
|
84
|
-
# 提取所有价格
|
|
85
|
-
prices = response.extract_texts('.price')
|
|
86
|
-
print(f" 所有价格: {prices}")
|
|
87
|
-
|
|
88
|
-
# 使用XPath提取所有产品名称
|
|
89
|
-
product_names_xpath = response.extract_texts('//div[@class="product-item"]/h2')
|
|
90
|
-
print(f" 所有产品名称 (XPath): {product_names_xpath}")
|
|
91
|
-
|
|
92
|
-
print()
|
|
93
|
-
|
|
94
|
-
# 3. 演示 extract_attr 方法(提取元素属性)
|
|
95
|
-
print("3. 提取元素属性:")
|
|
96
|
-
# 提取第一个产品项的data-id属性
|
|
97
|
-
first_product_id = response.extract_attr('.product-item', 'data-id')
|
|
98
|
-
print(f" 第一个产品ID: {first_product_id}")
|
|
99
|
-
|
|
100
|
-
# 提取详情链接的href属性
|
|
101
|
-
first_detail_link = response.extract_attr('.details-link', 'href')
|
|
102
|
-
print(f" 第一个详情链接: {first_detail_link}")
|
|
103
|
-
|
|
104
|
-
# 提取不存在属性的默认值
|
|
105
|
-
non_exist_attr = response.extract_attr('.product-item', 'non-exist', default='默认值')
|
|
106
|
-
print(f" 不存在的属性: {non_exist_attr}")
|
|
107
|
-
|
|
108
|
-
print()
|
|
109
|
-
|
|
110
|
-
# 4. 演示 extract_attrs 方法(提取多个元素的属性)
|
|
111
|
-
print("4. 提取多个元素的属性:")
|
|
112
|
-
# 提取所有产品项的data-id属性
|
|
113
|
-
product_ids = response.extract_attrs('.product-item', 'data-id')
|
|
114
|
-
print(f" 所有产品ID: {product_ids}")
|
|
115
|
-
|
|
116
|
-
# 提取所有详情链接的href属性
|
|
117
|
-
detail_links = response.extract_attrs('.details-link', 'href')
|
|
118
|
-
print(f" 所有详情链接: {detail_links}")
|
|
119
|
-
|
|
120
|
-
# 提取分页链接的href属性
|
|
121
|
-
page_links = response.extract_attrs('.page-link', 'href')
|
|
122
|
-
print(f" 分页链接: {page_links}")
|
|
123
|
-
|
|
124
|
-
print()
|
|
125
|
-
|
|
126
|
-
# 5. 演示复杂文本提取
|
|
127
|
-
print("5. 复杂文本提取:")
|
|
128
|
-
# 提取所有产品描述
|
|
129
|
-
descriptions = response.extract_texts('.description')
|
|
130
|
-
print(f" 所有产品描述: {descriptions}")
|
|
131
|
-
|
|
132
|
-
print()
|
|
133
|
-
|
|
134
|
-
# 6. 边界情况处理
|
|
135
|
-
print("6. 边界情况处理:")
|
|
136
|
-
# 空响应测试
|
|
137
|
-
empty_response = Response(url="https://example.com/empty", body=b"")
|
|
138
|
-
empty_text = empty_response.extract_text('title', default='默认标题')
|
|
139
|
-
print(f" 空响应默认值: {empty_text}")
|
|
140
|
-
|
|
141
|
-
print("\n=== 演示完成 ===")
|
|
142
|
-
|
|
143
|
-
|
|
144
|
-
if __name__ == '__main__':
|
|
1
|
+
#!/usr/bin/python
|
|
2
|
+
# -*- coding:UTF-8 -*-
|
|
3
|
+
"""
|
|
4
|
+
Response 改进功能使用示例
|
|
5
|
+
"""
|
|
6
|
+
from crawlo.network.response import Response
|
|
7
|
+
|
|
8
|
+
|
|
9
|
+
def demo_response_improvements():
|
|
10
|
+
"""演示Response改进功能"""
|
|
11
|
+
print("=== Response 改进功能演示 ===\n")
|
|
12
|
+
|
|
13
|
+
# 创建一个示例HTML响应
|
|
14
|
+
html_content = """
|
|
15
|
+
<html>
|
|
16
|
+
<head>
|
|
17
|
+
<title>Crawlo框架示例页面</title>
|
|
18
|
+
</head>
|
|
19
|
+
<body>
|
|
20
|
+
<div class="container">
|
|
21
|
+
<h1>产品列表</h1>
|
|
22
|
+
<div class="product-list">
|
|
23
|
+
<div class="product-item" data-id="1">
|
|
24
|
+
<h2>产品A</h2>
|
|
25
|
+
<p class="price">¥99.99</p>
|
|
26
|
+
<p class="description">这是产品A的描述信息</p>
|
|
27
|
+
<a href="/product/1" class="details-link">查看详情</a>
|
|
28
|
+
</div>
|
|
29
|
+
<div class="product-item" data-id="2">
|
|
30
|
+
<h2>产品B</h2>
|
|
31
|
+
<p class="price">¥149.99</p>
|
|
32
|
+
<p class="description">这是产品B的描述信息</p>
|
|
33
|
+
<a href="/product/2" class="details-link">查看详情</a>
|
|
34
|
+
</div>
|
|
35
|
+
<div class="product-item" data-id="3">
|
|
36
|
+
<h2>产品C</h2>
|
|
37
|
+
<p class="price">¥199.99</p>
|
|
38
|
+
<p class="description">这是产品C的描述信息</p>
|
|
39
|
+
<a href="/product/3" class="details-link">查看详情</a>
|
|
40
|
+
</div>
|
|
41
|
+
</div>
|
|
42
|
+
<div class="pagination">
|
|
43
|
+
<a href="/page/1" class="page-link">1</a>
|
|
44
|
+
<a href="/page/2" class="page-link active">2</a>
|
|
45
|
+
<a href="/page/3" class="page-link">3</a>
|
|
46
|
+
</div>
|
|
47
|
+
</div>
|
|
48
|
+
</body>
|
|
49
|
+
</html>
|
|
50
|
+
"""
|
|
51
|
+
|
|
52
|
+
# 创建Response对象
|
|
53
|
+
response = Response(
|
|
54
|
+
url="https://example.com/products",
|
|
55
|
+
body=html_content.encode('utf-8'),
|
|
56
|
+
headers={"content-type": "text/html; charset=utf-8"}
|
|
57
|
+
)
|
|
58
|
+
|
|
59
|
+
# 1. 演示 extract_text 方法(支持CSS和XPath)
|
|
60
|
+
print("1. 提取文本内容:")
|
|
61
|
+
title = response.extract_text('title')
|
|
62
|
+
print(f" 页面标题: {title}")
|
|
63
|
+
|
|
64
|
+
# 使用CSS选择器提取第一个产品名称
|
|
65
|
+
first_product_name = response.extract_text('.product-item:first-child h2')
|
|
66
|
+
print(f" 第一个产品名称 (CSS): {first_product_name}")
|
|
67
|
+
|
|
68
|
+
# 使用XPath选择器
|
|
69
|
+
first_product_name_xpath = response.extract_text('//div[@class="product-item"][1]/h2')
|
|
70
|
+
print(f" 第一个产品名称 (XPath): {first_product_name_xpath}")
|
|
71
|
+
|
|
72
|
+
# 使用默认值处理不存在的元素
|
|
73
|
+
non_exist = response.extract_text('.non-exist', default='未找到')
|
|
74
|
+
print(f" 不存在的元素: {non_exist}")
|
|
75
|
+
|
|
76
|
+
print()
|
|
77
|
+
|
|
78
|
+
# 2. 演示 extract_texts 方法(提取多个元素的文本)
|
|
79
|
+
print("2. 提取多个元素的文本:")
|
|
80
|
+
# 提取所有产品名称
|
|
81
|
+
product_names = response.extract_texts('.product-item h2')
|
|
82
|
+
print(f" 所有产品名称: {product_names}")
|
|
83
|
+
|
|
84
|
+
# 提取所有价格
|
|
85
|
+
prices = response.extract_texts('.price')
|
|
86
|
+
print(f" 所有价格: {prices}")
|
|
87
|
+
|
|
88
|
+
# 使用XPath提取所有产品名称
|
|
89
|
+
product_names_xpath = response.extract_texts('//div[@class="product-item"]/h2')
|
|
90
|
+
print(f" 所有产品名称 (XPath): {product_names_xpath}")
|
|
91
|
+
|
|
92
|
+
print()
|
|
93
|
+
|
|
94
|
+
# 3. 演示 extract_attr 方法(提取元素属性)
|
|
95
|
+
print("3. 提取元素属性:")
|
|
96
|
+
# 提取第一个产品项的data-id属性
|
|
97
|
+
first_product_id = response.extract_attr('.product-item', 'data-id')
|
|
98
|
+
print(f" 第一个产品ID: {first_product_id}")
|
|
99
|
+
|
|
100
|
+
# 提取详情链接的href属性
|
|
101
|
+
first_detail_link = response.extract_attr('.details-link', 'href')
|
|
102
|
+
print(f" 第一个详情链接: {first_detail_link}")
|
|
103
|
+
|
|
104
|
+
# 提取不存在属性的默认值
|
|
105
|
+
non_exist_attr = response.extract_attr('.product-item', 'non-exist', default='默认值')
|
|
106
|
+
print(f" 不存在的属性: {non_exist_attr}")
|
|
107
|
+
|
|
108
|
+
print()
|
|
109
|
+
|
|
110
|
+
# 4. 演示 extract_attrs 方法(提取多个元素的属性)
|
|
111
|
+
print("4. 提取多个元素的属性:")
|
|
112
|
+
# 提取所有产品项的data-id属性
|
|
113
|
+
product_ids = response.extract_attrs('.product-item', 'data-id')
|
|
114
|
+
print(f" 所有产品ID: {product_ids}")
|
|
115
|
+
|
|
116
|
+
# 提取所有详情链接的href属性
|
|
117
|
+
detail_links = response.extract_attrs('.details-link', 'href')
|
|
118
|
+
print(f" 所有详情链接: {detail_links}")
|
|
119
|
+
|
|
120
|
+
# 提取分页链接的href属性
|
|
121
|
+
page_links = response.extract_attrs('.page-link', 'href')
|
|
122
|
+
print(f" 分页链接: {page_links}")
|
|
123
|
+
|
|
124
|
+
print()
|
|
125
|
+
|
|
126
|
+
# 5. 演示复杂文本提取
|
|
127
|
+
print("5. 复杂文本提取:")
|
|
128
|
+
# 提取所有产品描述
|
|
129
|
+
descriptions = response.extract_texts('.description')
|
|
130
|
+
print(f" 所有产品描述: {descriptions}")
|
|
131
|
+
|
|
132
|
+
print()
|
|
133
|
+
|
|
134
|
+
# 6. 边界情况处理
|
|
135
|
+
print("6. 边界情况处理:")
|
|
136
|
+
# 空响应测试
|
|
137
|
+
empty_response = Response(url="https://example.com/empty", body=b"")
|
|
138
|
+
empty_text = empty_response.extract_text('title', default='默认标题')
|
|
139
|
+
print(f" 空响应默认值: {empty_text}")
|
|
140
|
+
|
|
141
|
+
print("\n=== 演示完成 ===")
|
|
142
|
+
|
|
143
|
+
|
|
144
|
+
if __name__ == '__main__':
|
|
145
145
|
demo_response_improvements()
|