crawlo 1.2.0__py3-none-any.whl → 1.2.2__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/__init__.py +61 -61
- crawlo/__version__.py +1 -1
- crawlo/cleaners/__init__.py +60 -60
- crawlo/cleaners/data_formatter.py +225 -225
- crawlo/cleaners/encoding_converter.py +125 -125
- crawlo/cleaners/text_cleaner.py +232 -232
- crawlo/cli.py +81 -65
- crawlo/commands/__init__.py +14 -14
- crawlo/commands/check.py +594 -594
- crawlo/commands/genspider.py +151 -151
- crawlo/commands/help.py +143 -133
- crawlo/commands/list.py +155 -155
- crawlo/commands/run.py +292 -292
- crawlo/commands/startproject.py +418 -418
- crawlo/commands/stats.py +188 -188
- crawlo/commands/utils.py +186 -186
- crawlo/config.py +312 -312
- crawlo/config_validator.py +252 -252
- crawlo/core/__init__.py +2 -2
- crawlo/core/engine.py +354 -354
- crawlo/core/processor.py +40 -40
- crawlo/core/scheduler.py +143 -143
- crawlo/crawler.py +1027 -1027
- crawlo/downloader/__init__.py +266 -266
- crawlo/downloader/aiohttp_downloader.py +220 -220
- crawlo/downloader/cffi_downloader.py +256 -256
- crawlo/downloader/httpx_downloader.py +259 -259
- crawlo/downloader/hybrid_downloader.py +213 -213
- 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 +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 -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 +280 -280
- 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 +132 -32
- crawlo/middleware/download_delay.py +105 -28
- crawlo/middleware/middleware_manager.py +135 -135
- crawlo/middleware/offsite.py +116 -0
- crawlo/middleware/proxy.py +366 -272
- crawlo/middleware/request_ignore.py +88 -30
- crawlo/middleware/response_code.py +164 -18
- crawlo/middleware/response_filter.py +138 -26
- crawlo/middleware/retry.py +124 -124
- crawlo/mode_manager.py +211 -211
- crawlo/network/__init__.py +21 -21
- crawlo/network/request.py +338 -338
- crawlo/network/response.py +359 -359
- 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 +61 -61
- crawlo/pipelines/redis_dedup_pipeline.py +167 -167
- crawlo/project.py +187 -187
- crawlo/queue/pqueue.py +37 -37
- crawlo/queue/queue_manager.py +337 -337
- crawlo/queue/redis_priority_queue.py +298 -298
- crawlo/settings/__init__.py +7 -7
- crawlo/settings/default_settings.py +226 -219
- crawlo/settings/setting_manager.py +122 -122
- 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 +118 -109
- crawlo/templates/project/pipelines.py.tmpl +96 -96
- crawlo/templates/project/run.py.tmpl +45 -45
- crawlo/templates/project/settings.py.tmpl +327 -326
- crawlo/templates/project/settings_distributed.py.tmpl +119 -119
- crawlo/templates/project/settings_gentle.py.tmpl +94 -94
- crawlo/templates/project/settings_high_performance.py.tmpl +151 -151
- crawlo/templates/project/settings_simple.py.tmpl +68 -68
- crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
- crawlo/templates/spider/spider.py.tmpl +143 -141
- crawlo/tools/__init__.py +182 -182
- crawlo/tools/anti_crawler.py +268 -268
- crawlo/tools/authenticated_proxy.py +240 -240
- crawlo/tools/data_validator.py +180 -180
- crawlo/tools/date_tools.py +35 -35
- crawlo/tools/distributed_coordinator.py +386 -386
- crawlo/tools/retry_mechanism.py +220 -220
- crawlo/tools/scenario_adapter.py +262 -262
- crawlo/utils/__init__.py +35 -35
- crawlo/utils/batch_processor.py +260 -260
- crawlo/utils/controlled_spider_mixin.py +439 -439
- crawlo/utils/date_tools.py +290 -290
- crawlo/utils/db_helper.py +343 -343
- crawlo/utils/enhanced_error_handler.py +359 -359
- crawlo/utils/env_config.py +105 -105
- crawlo/utils/error_handler.py +125 -125
- 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 +284 -284
- crawlo/utils/queue_helper.py +175 -175
- crawlo/utils/redis_connection_pool.py +334 -334
- crawlo/utils/redis_key_validator.py +199 -199
- 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-1.2.0.dist-info → crawlo-1.2.2.dist-info}/METADATA +692 -697
- crawlo-1.2.2.dist-info/RECORD +220 -0
- examples/__init__.py +7 -7
- examples/aiohttp_settings.py +42 -0
- examples/curl_cffi_settings.py +41 -0
- examples/default_header_middleware_example.py +107 -0
- examples/default_header_spider_example.py +129 -0
- examples/download_delay_middleware_example.py +160 -0
- examples/httpx_settings.py +42 -0
- examples/multi_downloader_proxy_example.py +81 -0
- examples/offsite_middleware_example.py +55 -0
- examples/offsite_spider_example.py +107 -0
- examples/proxy_spider_example.py +166 -0
- examples/request_ignore_middleware_example.py +51 -0
- examples/request_ignore_spider_example.py +99 -0
- examples/response_code_middleware_example.py +52 -0
- examples/response_filter_middleware_example.py +67 -0
- examples/tong_hua_shun_settings.py +62 -0
- examples/tong_hua_shun_spider.py +170 -0
- 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 +236 -236
- tests/cleaners_example.py +160 -160
- tests/config_validation_demo.py +102 -102
- tests/controlled_spider_example.py +205 -205
- tests/date_tools_example.py +180 -180
- 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/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_validator.py +193 -193
- tests/test_crawlo_proxy_integration.py +173 -0
- tests/test_date_tools.py +123 -123
- tests/test_default_header_middleware.py +159 -0
- tests/test_double_crawlo_fix.py +207 -207
- tests/test_double_crawlo_fix_simple.py +124 -124
- tests/test_download_delay_middleware.py +222 -0
- tests/test_downloader_proxy_compatibility.py +269 -0
- 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 +356 -356
- tests/test_item_dedup_redis_key.py +122 -122
- tests/test_offsite_middleware.py +222 -0
- tests/test_parsel.py +29 -29
- tests/test_performance.py +327 -327
- tests/test_proxy_api.py +265 -0
- tests/test_proxy_health_check.py +32 -32
- tests/test_proxy_middleware.py +122 -0
- tests/test_proxy_middleware_enhanced.py +217 -0
- 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_double_crawlo.py +173 -173
- tests/test_queue_manager_redis_key.py +176 -176
- tests/test_real_scenario_proxy.py +196 -0
- 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 +183 -0
- tests/test_request_serialization.py +70 -70
- tests/test_response_code_middleware.py +350 -0
- tests/test_response_filter_middleware.py +428 -0
- tests/test_response_improvements.py +152 -152
- tests/test_retry_middleware.py +242 -0
- tests/test_scheduler.py +241 -241
- 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 +153 -153
- tests/tools_example.py +257 -257
- crawlo-1.2.0.dist-info/RECORD +0 -190
- {crawlo-1.2.0.dist-info → crawlo-1.2.2.dist-info}/WHEEL +0 -0
- {crawlo-1.2.0.dist-info → crawlo-1.2.2.dist-info}/entry_points.txt +0 -0
- {crawlo-1.2.0.dist-info → crawlo-1.2.2.dist-info}/top_level.txt +0 -0
|
@@ -1,237 +1,237 @@
|
|
|
1
|
-
#!/usr/bin/python
|
|
2
|
-
# -*- coding: UTF-8 -*-
|
|
3
|
-
"""
|
|
4
|
-
带认证代理使用示例
|
|
5
|
-
================
|
|
6
|
-
展示如何在Crawlo框架中使用带用户名密码认证的代理和非认证代理
|
|
7
|
-
|
|
8
|
-
支持的代理类型:
|
|
9
|
-
1. 带认证的HTTP/HTTPS代理
|
|
10
|
-
2. 不带认证的HTTP/HTTPS代理
|
|
11
|
-
3. SOCKS代理(带或不带认证)
|
|
12
|
-
"""
|
|
13
|
-
|
|
14
|
-
from crawlo import Spider, Request
|
|
15
|
-
from crawlo.tools import (
|
|
16
|
-
AuthenticatedProxy,
|
|
17
|
-
create_proxy_config,
|
|
18
|
-
format_proxy_for_request,
|
|
19
|
-
get_proxy_info,
|
|
20
|
-
validate_proxy_url
|
|
21
|
-
)
|
|
22
|
-
|
|
23
|
-
|
|
24
|
-
def demo_proxy_parsing():
|
|
25
|
-
"""演示代理URL解析"""
|
|
26
|
-
print("=== 代理URL解析演示 ===\n")
|
|
27
|
-
|
|
28
|
-
# 测试不同类型的代理URL
|
|
29
|
-
proxy_urls = [
|
|
30
|
-
# 带认证的HTTP代理
|
|
31
|
-
"http://username:password@proxy.example.com:8080",
|
|
32
|
-
# 不带认证的HTTP代理
|
|
33
|
-
"http://proxy.example.com:8080",
|
|
34
|
-
# 带认证的HTTPS代理
|
|
35
|
-
"https://user123:pass456@secure-proxy.com:443",
|
|
36
|
-
# SOCKS5代理
|
|
37
|
-
"socks5://socks-user:socks-pass@socks-proxy.com:1080",
|
|
38
|
-
# 不带认证的SOCKS4代理
|
|
39
|
-
"socks4://socks4-proxy.com:1080"
|
|
40
|
-
]
|
|
41
|
-
|
|
42
|
-
for proxy_url in proxy_urls:
|
|
43
|
-
print(f"解析代理URL: {proxy_url}")
|
|
44
|
-
|
|
45
|
-
# 验证代理URL
|
|
46
|
-
is_valid = validate_proxy_url(proxy_url)
|
|
47
|
-
print(f" 有效性: {'有效' if is_valid else '无效'}")
|
|
48
|
-
|
|
49
|
-
if is_valid:
|
|
50
|
-
# 获取代理详细信息
|
|
51
|
-
proxy_info = get_proxy_info(proxy_url)
|
|
52
|
-
print(f" 协议: {proxy_info['scheme']}")
|
|
53
|
-
print(f" 主机: {proxy_info['hostname']}")
|
|
54
|
-
print(f" 端口: {proxy_info['port']}")
|
|
55
|
-
print(f" 有认证: {'是' if proxy_info['has_auth'] else '否'}")
|
|
56
|
-
if proxy_info['has_auth']:
|
|
57
|
-
print(f" 用户名: {proxy_info['username']}")
|
|
58
|
-
|
|
59
|
-
# 创建代理配置
|
|
60
|
-
proxy_config = create_proxy_config(proxy_url)
|
|
61
|
-
print(f" 代理配置: {proxy_config}")
|
|
62
|
-
|
|
63
|
-
# 格式化为不同下载器的配置
|
|
64
|
-
for downloader in ["aiohttp", "httpx", "curl_cffi"]:
|
|
65
|
-
formatted = format_proxy_for_request(proxy_config, downloader)
|
|
66
|
-
print(f" {downloader}格式: {formatted}")
|
|
67
|
-
|
|
68
|
-
print()
|
|
69
|
-
|
|
70
|
-
|
|
71
|
-
def demo_authenticated_proxy_class():
|
|
72
|
-
"""演示AuthenticatedProxy类的使用"""
|
|
73
|
-
print("=== AuthenticatedProxy类演示 ===\n")
|
|
74
|
-
|
|
75
|
-
# 带认证的代理
|
|
76
|
-
auth_proxy = AuthenticatedProxy("http://myuser:mypass@proxy.company.com:8080")
|
|
77
|
-
print(f"代理URL: {auth_proxy}")
|
|
78
|
-
print(f"清洁URL: {auth_proxy.clean_url}")
|
|
79
|
-
print(f"用户名: {auth_proxy.username}")
|
|
80
|
-
print(f"密码: {auth_proxy.password}")
|
|
81
|
-
print(f"代理字典: {auth_proxy.proxy_dict}")
|
|
82
|
-
print(f"认证凭据: {auth_proxy.get_auth_credentials()}")
|
|
83
|
-
print(f"认证头: {auth_proxy.get_auth_header()}")
|
|
84
|
-
print(f"是否有效: {auth_proxy.is_valid()}")
|
|
85
|
-
print()
|
|
86
|
-
|
|
87
|
-
# 不带认证的代理
|
|
88
|
-
no_auth_proxy = AuthenticatedProxy("http://public.proxy.com:8080")
|
|
89
|
-
print(f"代理URL: {no_auth_proxy}")
|
|
90
|
-
print(f"清洁URL: {no_auth_proxy.clean_url}")
|
|
91
|
-
print(f"用户名: {no_auth_proxy.username}")
|
|
92
|
-
print(f"密码: {no_auth_proxy.password}")
|
|
93
|
-
print(f"代理字典: {no_auth_proxy.proxy_dict}")
|
|
94
|
-
print(f"认证凭据: {no_auth_proxy.get_auth_credentials()}")
|
|
95
|
-
print(f"认证头: {no_auth_proxy.get_auth_header()}")
|
|
96
|
-
print(f"是否有效: {no_auth_proxy.is_valid()}")
|
|
97
|
-
print()
|
|
98
|
-
|
|
99
|
-
|
|
100
|
-
class ProxySpider(Spider):
|
|
101
|
-
"""使用代理的爬虫示例"""
|
|
102
|
-
name = 'proxy_spider'
|
|
103
|
-
|
|
104
|
-
def __init__(self):
|
|
105
|
-
super().__init__()
|
|
106
|
-
# 代理列表
|
|
107
|
-
self.proxies = [
|
|
108
|
-
"http://user1:pass1@proxy1.example.com:8080",
|
|
109
|
-
"http://user2:pass2@proxy2.example.com:8080",
|
|
110
|
-
"http://proxy3.example.com:8080", # 不带认证
|
|
111
|
-
"https://secureuser:securepass@secure.proxy.com:443"
|
|
112
|
-
]
|
|
113
|
-
self.current_proxy_index = 0
|
|
114
|
-
|
|
115
|
-
def get_next_proxy(self):
|
|
116
|
-
"""获取下一个代理"""
|
|
117
|
-
proxy_url = self.proxies[self.current_proxy_index]
|
|
118
|
-
self.current_proxy_index = (self.current_proxy_index + 1) % len(self.proxies)
|
|
119
|
-
return proxy_url
|
|
120
|
-
|
|
121
|
-
def start_requests(self):
|
|
122
|
-
urls = [
|
|
123
|
-
'https://httpbin.org/ip', # 查看IP地址
|
|
124
|
-
'https://httpbin.org/headers', # 查看请求头
|
|
125
|
-
'https://example.com', # 普通网站
|
|
126
|
-
]
|
|
127
|
-
|
|
128
|
-
for url in urls:
|
|
129
|
-
# 获取代理
|
|
130
|
-
proxy_url = self.get_next_proxy()
|
|
131
|
-
proxy = AuthenticatedProxy(proxy_url)
|
|
132
|
-
|
|
133
|
-
# 创建请求
|
|
134
|
-
request = Request(url=url, callback=self.parse)
|
|
135
|
-
|
|
136
|
-
# 根据不同下载器设置代理
|
|
137
|
-
# 这里以AioHttp为例
|
|
138
|
-
if self.crawler.settings.get("DOWNLOADER_TYPE") == "aiohttp":
|
|
139
|
-
request.proxy = proxy.clean_url
|
|
140
|
-
auth = proxy.get_auth_credentials()
|
|
141
|
-
if auth:
|
|
142
|
-
# AioHttp需要在下载器中处理认证
|
|
143
|
-
request.meta["proxy_auth"] = auth
|
|
144
|
-
else:
|
|
145
|
-
# 其他下载器
|
|
146
|
-
request.proxy = proxy.proxy_dict
|
|
147
|
-
|
|
148
|
-
yield request
|
|
149
|
-
|
|
150
|
-
def parse(self, response):
|
|
151
|
-
"""解析响应"""
|
|
152
|
-
print(f"成功访问: {response.url}")
|
|
153
|
-
print(f"状态码: {response.status_code}")
|
|
154
|
-
# 显示前200个字符
|
|
155
|
-
print(f"响应内容: {response.text[:200]}...\n")
|
|
156
|
-
yield {"url": response.url, "status": response.status_code}
|
|
157
|
-
|
|
158
|
-
|
|
159
|
-
def demo_in_spider():
|
|
160
|
-
"""演示在爬虫中使用代理"""
|
|
161
|
-
print("=== 在爬虫中使用代理 ===\n")
|
|
162
|
-
print("在爬虫项目中,您可以这样使用带认证的代理:")
|
|
163
|
-
print("""
|
|
164
|
-
from crawlo import Spider, Request
|
|
165
|
-
from crawlo.tools import AuthenticatedProxy
|
|
166
|
-
|
|
167
|
-
class MySpider(Spider):
|
|
168
|
-
name = 'my_spider'
|
|
169
|
-
|
|
170
|
-
def __init__(self):
|
|
171
|
-
super().__init__()
|
|
172
|
-
self.proxy_urls = [
|
|
173
|
-
"http://username:password@proxy1.example.com:8080",
|
|
174
|
-
"http://user:pass@proxy2.example.com:8080",
|
|
175
|
-
"http://proxy3.example.com:8080" # 不带认证
|
|
176
|
-
]
|
|
177
|
-
|
|
178
|
-
def start_requests(self):
|
|
179
|
-
urls = ['https://httpbin.org/ip', 'https://example.com']
|
|
180
|
-
|
|
181
|
-
for i, url in enumerate(urls):
|
|
182
|
-
# 选择代理
|
|
183
|
-
proxy_url = self.proxy_urls[i % len(self.proxy_urls)]
|
|
184
|
-
proxy = AuthenticatedProxy(proxy_url)
|
|
185
|
-
|
|
186
|
-
# 创建请求
|
|
187
|
-
request = Request(url=url, callback=self.parse)
|
|
188
|
-
|
|
189
|
-
# 设置代理(根据不同下载器)
|
|
190
|
-
downloader_type = self.crawler.settings.get("DOWNLOADER_TYPE", "aiohttp")
|
|
191
|
-
|
|
192
|
-
if downloader_type == "aiohttp":
|
|
193
|
-
# AioHttp下载器
|
|
194
|
-
request.proxy = proxy.clean_url
|
|
195
|
-
auth = proxy.get_auth_credentials()
|
|
196
|
-
if auth:
|
|
197
|
-
request.meta["proxy_auth"] = auth
|
|
198
|
-
elif downloader_type == "httpx":
|
|
199
|
-
# HttpX下载器
|
|
200
|
-
request.proxy = proxy.clean_url
|
|
201
|
-
elif downloader_type == "curl_cffi":
|
|
202
|
-
# CurlCffi下载器
|
|
203
|
-
request.proxy = proxy.proxy_dict
|
|
204
|
-
# 认证信息在URL中或通过headers传递
|
|
205
|
-
auth_header = proxy.get_auth_header()
|
|
206
|
-
if auth_header:
|
|
207
|
-
request.headers["Proxy-Authorization"] = auth_header
|
|
208
|
-
|
|
209
|
-
yield request
|
|
210
|
-
|
|
211
|
-
def parse(self, response):
|
|
212
|
-
# 处理响应
|
|
213
|
-
yield {"url": response.url, "title": response.css('title::text').get()}
|
|
214
|
-
""")
|
|
215
|
-
|
|
216
|
-
|
|
217
|
-
if __name__ == '__main__':
|
|
218
|
-
# 运行演示
|
|
219
|
-
demo_proxy_parsing()
|
|
220
|
-
demo_authenticated_proxy_class()
|
|
221
|
-
demo_in_spider()
|
|
222
|
-
|
|
223
|
-
print("\n=== 配置说明 ===")
|
|
224
|
-
print("在settings.py中配置代理:")
|
|
225
|
-
print("""
|
|
226
|
-
# 启用代理中间件
|
|
227
|
-
MIDDLEWARES = [
|
|
228
|
-
# ... 其他中间件 ...
|
|
229
|
-
'crawlo.middleware.proxy.ProxyMiddleware',
|
|
230
|
-
]
|
|
231
|
-
|
|
232
|
-
# 代理配置
|
|
233
|
-
PROXY_ENABLED = True
|
|
234
|
-
PROXY_API_URL = "https://api.proxyprovider.com/get" # 代理API地址
|
|
235
|
-
PROXY_EXTRACTOR = "proxy" # 从API响应中提取代理的字段路径
|
|
236
|
-
PROXY_REFRESH_INTERVAL = 60 # 代理刷新间隔(秒)
|
|
1
|
+
#!/usr/bin/python
|
|
2
|
+
# -*- coding: UTF-8 -*-
|
|
3
|
+
"""
|
|
4
|
+
带认证代理使用示例
|
|
5
|
+
================
|
|
6
|
+
展示如何在Crawlo框架中使用带用户名密码认证的代理和非认证代理
|
|
7
|
+
|
|
8
|
+
支持的代理类型:
|
|
9
|
+
1. 带认证的HTTP/HTTPS代理
|
|
10
|
+
2. 不带认证的HTTP/HTTPS代理
|
|
11
|
+
3. SOCKS代理(带或不带认证)
|
|
12
|
+
"""
|
|
13
|
+
|
|
14
|
+
from crawlo import Spider, Request
|
|
15
|
+
from crawlo.tools import (
|
|
16
|
+
AuthenticatedProxy,
|
|
17
|
+
create_proxy_config,
|
|
18
|
+
format_proxy_for_request,
|
|
19
|
+
get_proxy_info,
|
|
20
|
+
validate_proxy_url
|
|
21
|
+
)
|
|
22
|
+
|
|
23
|
+
|
|
24
|
+
def demo_proxy_parsing():
|
|
25
|
+
"""演示代理URL解析"""
|
|
26
|
+
print("=== 代理URL解析演示 ===\n")
|
|
27
|
+
|
|
28
|
+
# 测试不同类型的代理URL
|
|
29
|
+
proxy_urls = [
|
|
30
|
+
# 带认证的HTTP代理
|
|
31
|
+
"http://username:password@proxy.example.com:8080",
|
|
32
|
+
# 不带认证的HTTP代理
|
|
33
|
+
"http://proxy.example.com:8080",
|
|
34
|
+
# 带认证的HTTPS代理
|
|
35
|
+
"https://user123:pass456@secure-proxy.com:443",
|
|
36
|
+
# SOCKS5代理
|
|
37
|
+
"socks5://socks-user:socks-pass@socks-proxy.com:1080",
|
|
38
|
+
# 不带认证的SOCKS4代理
|
|
39
|
+
"socks4://socks4-proxy.com:1080"
|
|
40
|
+
]
|
|
41
|
+
|
|
42
|
+
for proxy_url in proxy_urls:
|
|
43
|
+
print(f"解析代理URL: {proxy_url}")
|
|
44
|
+
|
|
45
|
+
# 验证代理URL
|
|
46
|
+
is_valid = validate_proxy_url(proxy_url)
|
|
47
|
+
print(f" 有效性: {'有效' if is_valid else '无效'}")
|
|
48
|
+
|
|
49
|
+
if is_valid:
|
|
50
|
+
# 获取代理详细信息
|
|
51
|
+
proxy_info = get_proxy_info(proxy_url)
|
|
52
|
+
print(f" 协议: {proxy_info['scheme']}")
|
|
53
|
+
print(f" 主机: {proxy_info['hostname']}")
|
|
54
|
+
print(f" 端口: {proxy_info['port']}")
|
|
55
|
+
print(f" 有认证: {'是' if proxy_info['has_auth'] else '否'}")
|
|
56
|
+
if proxy_info['has_auth']:
|
|
57
|
+
print(f" 用户名: {proxy_info['username']}")
|
|
58
|
+
|
|
59
|
+
# 创建代理配置
|
|
60
|
+
proxy_config = create_proxy_config(proxy_url)
|
|
61
|
+
print(f" 代理配置: {proxy_config}")
|
|
62
|
+
|
|
63
|
+
# 格式化为不同下载器的配置
|
|
64
|
+
for downloader in ["aiohttp", "httpx", "curl_cffi"]:
|
|
65
|
+
formatted = format_proxy_for_request(proxy_config, downloader)
|
|
66
|
+
print(f" {downloader}格式: {formatted}")
|
|
67
|
+
|
|
68
|
+
print()
|
|
69
|
+
|
|
70
|
+
|
|
71
|
+
def demo_authenticated_proxy_class():
|
|
72
|
+
"""演示AuthenticatedProxy类的使用"""
|
|
73
|
+
print("=== AuthenticatedProxy类演示 ===\n")
|
|
74
|
+
|
|
75
|
+
# 带认证的代理
|
|
76
|
+
auth_proxy = AuthenticatedProxy("http://myuser:mypass@proxy.company.com:8080")
|
|
77
|
+
print(f"代理URL: {auth_proxy}")
|
|
78
|
+
print(f"清洁URL: {auth_proxy.clean_url}")
|
|
79
|
+
print(f"用户名: {auth_proxy.username}")
|
|
80
|
+
print(f"密码: {auth_proxy.password}")
|
|
81
|
+
print(f"代理字典: {auth_proxy.proxy_dict}")
|
|
82
|
+
print(f"认证凭据: {auth_proxy.get_auth_credentials()}")
|
|
83
|
+
print(f"认证头: {auth_proxy.get_auth_header()}")
|
|
84
|
+
print(f"是否有效: {auth_proxy.is_valid()}")
|
|
85
|
+
print()
|
|
86
|
+
|
|
87
|
+
# 不带认证的代理
|
|
88
|
+
no_auth_proxy = AuthenticatedProxy("http://public.proxy.com:8080")
|
|
89
|
+
print(f"代理URL: {no_auth_proxy}")
|
|
90
|
+
print(f"清洁URL: {no_auth_proxy.clean_url}")
|
|
91
|
+
print(f"用户名: {no_auth_proxy.username}")
|
|
92
|
+
print(f"密码: {no_auth_proxy.password}")
|
|
93
|
+
print(f"代理字典: {no_auth_proxy.proxy_dict}")
|
|
94
|
+
print(f"认证凭据: {no_auth_proxy.get_auth_credentials()}")
|
|
95
|
+
print(f"认证头: {no_auth_proxy.get_auth_header()}")
|
|
96
|
+
print(f"是否有效: {no_auth_proxy.is_valid()}")
|
|
97
|
+
print()
|
|
98
|
+
|
|
99
|
+
|
|
100
|
+
class ProxySpider(Spider):
|
|
101
|
+
"""使用代理的爬虫示例"""
|
|
102
|
+
name = 'proxy_spider'
|
|
103
|
+
|
|
104
|
+
def __init__(self):
|
|
105
|
+
super().__init__()
|
|
106
|
+
# 代理列表
|
|
107
|
+
self.proxies = [
|
|
108
|
+
"http://user1:pass1@proxy1.example.com:8080",
|
|
109
|
+
"http://user2:pass2@proxy2.example.com:8080",
|
|
110
|
+
"http://proxy3.example.com:8080", # 不带认证
|
|
111
|
+
"https://secureuser:securepass@secure.proxy.com:443"
|
|
112
|
+
]
|
|
113
|
+
self.current_proxy_index = 0
|
|
114
|
+
|
|
115
|
+
def get_next_proxy(self):
|
|
116
|
+
"""获取下一个代理"""
|
|
117
|
+
proxy_url = self.proxies[self.current_proxy_index]
|
|
118
|
+
self.current_proxy_index = (self.current_proxy_index + 1) % len(self.proxies)
|
|
119
|
+
return proxy_url
|
|
120
|
+
|
|
121
|
+
def start_requests(self):
|
|
122
|
+
urls = [
|
|
123
|
+
'https://httpbin.org/ip', # 查看IP地址
|
|
124
|
+
'https://httpbin.org/headers', # 查看请求头
|
|
125
|
+
'https://example.com', # 普通网站
|
|
126
|
+
]
|
|
127
|
+
|
|
128
|
+
for url in urls:
|
|
129
|
+
# 获取代理
|
|
130
|
+
proxy_url = self.get_next_proxy()
|
|
131
|
+
proxy = AuthenticatedProxy(proxy_url)
|
|
132
|
+
|
|
133
|
+
# 创建请求
|
|
134
|
+
request = Request(url=url, callback=self.parse)
|
|
135
|
+
|
|
136
|
+
# 根据不同下载器设置代理
|
|
137
|
+
# 这里以AioHttp为例
|
|
138
|
+
if self.crawler.settings.get("DOWNLOADER_TYPE") == "aiohttp":
|
|
139
|
+
request.proxy = proxy.clean_url
|
|
140
|
+
auth = proxy.get_auth_credentials()
|
|
141
|
+
if auth:
|
|
142
|
+
# AioHttp需要在下载器中处理认证
|
|
143
|
+
request.meta["proxy_auth"] = auth
|
|
144
|
+
else:
|
|
145
|
+
# 其他下载器
|
|
146
|
+
request.proxy = proxy.proxy_dict
|
|
147
|
+
|
|
148
|
+
yield request
|
|
149
|
+
|
|
150
|
+
def parse(self, response):
|
|
151
|
+
"""解析响应"""
|
|
152
|
+
print(f"成功访问: {response.url}")
|
|
153
|
+
print(f"状态码: {response.status_code}")
|
|
154
|
+
# 显示前200个字符
|
|
155
|
+
print(f"响应内容: {response.text[:200]}...\n")
|
|
156
|
+
yield {"url": response.url, "status": response.status_code}
|
|
157
|
+
|
|
158
|
+
|
|
159
|
+
def demo_in_spider():
|
|
160
|
+
"""演示在爬虫中使用代理"""
|
|
161
|
+
print("=== 在爬虫中使用代理 ===\n")
|
|
162
|
+
print("在爬虫项目中,您可以这样使用带认证的代理:")
|
|
163
|
+
print("""
|
|
164
|
+
from crawlo import Spider, Request
|
|
165
|
+
from crawlo.tools import AuthenticatedProxy
|
|
166
|
+
|
|
167
|
+
class MySpider(Spider):
|
|
168
|
+
name = 'my_spider'
|
|
169
|
+
|
|
170
|
+
def __init__(self):
|
|
171
|
+
super().__init__()
|
|
172
|
+
self.proxy_urls = [
|
|
173
|
+
"http://username:password@proxy1.example.com:8080",
|
|
174
|
+
"http://user:pass@proxy2.example.com:8080",
|
|
175
|
+
"http://proxy3.example.com:8080" # 不带认证
|
|
176
|
+
]
|
|
177
|
+
|
|
178
|
+
def start_requests(self):
|
|
179
|
+
urls = ['https://httpbin.org/ip', 'https://example.com']
|
|
180
|
+
|
|
181
|
+
for i, url in enumerate(urls):
|
|
182
|
+
# 选择代理
|
|
183
|
+
proxy_url = self.proxy_urls[i % len(self.proxy_urls)]
|
|
184
|
+
proxy = AuthenticatedProxy(proxy_url)
|
|
185
|
+
|
|
186
|
+
# 创建请求
|
|
187
|
+
request = Request(url=url, callback=self.parse)
|
|
188
|
+
|
|
189
|
+
# 设置代理(根据不同下载器)
|
|
190
|
+
downloader_type = self.crawler.settings.get("DOWNLOADER_TYPE", "aiohttp")
|
|
191
|
+
|
|
192
|
+
if downloader_type == "aiohttp":
|
|
193
|
+
# AioHttp下载器
|
|
194
|
+
request.proxy = proxy.clean_url
|
|
195
|
+
auth = proxy.get_auth_credentials()
|
|
196
|
+
if auth:
|
|
197
|
+
request.meta["proxy_auth"] = auth
|
|
198
|
+
elif downloader_type == "httpx":
|
|
199
|
+
# HttpX下载器
|
|
200
|
+
request.proxy = proxy.clean_url
|
|
201
|
+
elif downloader_type == "curl_cffi":
|
|
202
|
+
# CurlCffi下载器
|
|
203
|
+
request.proxy = proxy.proxy_dict
|
|
204
|
+
# 认证信息在URL中或通过headers传递
|
|
205
|
+
auth_header = proxy.get_auth_header()
|
|
206
|
+
if auth_header:
|
|
207
|
+
request.headers["Proxy-Authorization"] = auth_header
|
|
208
|
+
|
|
209
|
+
yield request
|
|
210
|
+
|
|
211
|
+
def parse(self, response):
|
|
212
|
+
# 处理响应
|
|
213
|
+
yield {"url": response.url, "title": response.css('title::text').get()}
|
|
214
|
+
""")
|
|
215
|
+
|
|
216
|
+
|
|
217
|
+
if __name__ == '__main__':
|
|
218
|
+
# 运行演示
|
|
219
|
+
demo_proxy_parsing()
|
|
220
|
+
demo_authenticated_proxy_class()
|
|
221
|
+
demo_in_spider()
|
|
222
|
+
|
|
223
|
+
print("\n=== 配置说明 ===")
|
|
224
|
+
print("在settings.py中配置代理:")
|
|
225
|
+
print("""
|
|
226
|
+
# 启用代理中间件
|
|
227
|
+
MIDDLEWARES = [
|
|
228
|
+
# ... 其他中间件 ...
|
|
229
|
+
'crawlo.middleware.proxy.ProxyMiddleware',
|
|
230
|
+
]
|
|
231
|
+
|
|
232
|
+
# 代理配置
|
|
233
|
+
PROXY_ENABLED = True
|
|
234
|
+
PROXY_API_URL = "https://api.proxyprovider.com/get" # 代理API地址
|
|
235
|
+
PROXY_EXTRACTOR = "proxy" # 从API响应中提取代理的字段路径
|
|
236
|
+
PROXY_REFRESH_INTERVAL = 60 # 代理刷新间隔(秒)
|
|
237
237
|
""")
|