crawlo 1.1.8__py3-none-any.whl → 1.1.9__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 +65 -65
- crawlo/commands/__init__.py +14 -14
- crawlo/commands/check.py +594 -594
- crawlo/commands/genspider.py +151 -151
- crawlo/commands/help.py +132 -132
- 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 +345 -345
- crawlo/core/processor.py +40 -40
- crawlo/core/scheduler.py +136 -136
- 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 +32 -32
- crawlo/middleware/download_delay.py +28 -28
- crawlo/middleware/middleware_manager.py +135 -135
- crawlo/middleware/proxy.py +272 -272
- 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 +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 +334 -334
- crawlo/queue/redis_priority_queue.py +298 -298
- crawlo/settings/__init__.py +7 -7
- crawlo/settings/default_settings.py +219 -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 +109 -109
- crawlo/templates/project/pipelines.py.tmpl +96 -96
- crawlo/templates/project/run.py.tmpl +45 -45
- crawlo/templates/project/settings.py.tmpl +326 -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 +141 -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-1.1.8.dist-info → crawlo-1.1.9.dist-info}/METADATA +626 -626
- crawlo-1.1.9.dist-info/RECORD +190 -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 +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_date_tools.py +123 -123
- tests/test_double_crawlo_fix.py +207 -207
- tests/test_double_crawlo_fix_simple.py +124 -124
- 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_parsel.py +29 -29
- tests/test_performance.py +327 -327
- 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_double_crawlo.py +230 -230
- tests/test_queue_manager_redis_key.py +176 -176
- 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_serialization.py +70 -70
- tests/test_response_improvements.py +152 -152
- 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-1.1.8.dist-info/RECORD +0 -190
- {crawlo-1.1.8.dist-info → crawlo-1.1.9.dist-info}/WHEEL +0 -0
- {crawlo-1.1.8.dist-info → crawlo-1.1.9.dist-info}/entry_points.txt +0 -0
- {crawlo-1.1.8.dist-info → crawlo-1.1.9.dist-info}/top_level.txt +0 -0
crawlo/tools/anti_crawler.py
CHANGED
|
@@ -1,269 +1,269 @@
|
|
|
1
|
-
#!/usr/bin/python
|
|
2
|
-
# -*- coding: UTF-8 -*-
|
|
3
|
-
"""
|
|
4
|
-
# @Time : 2025-09-10 22:00
|
|
5
|
-
# @Author : crawl-coder
|
|
6
|
-
# @Desc : 反爬虫应对工具
|
|
7
|
-
"""
|
|
8
|
-
|
|
9
|
-
import asyncio
|
|
10
|
-
import random
|
|
11
|
-
import time
|
|
12
|
-
from typing import Dict, Any, Optional, List, Callable
|
|
13
|
-
|
|
14
|
-
|
|
15
|
-
class ProxyPoolManager:
|
|
16
|
-
"""代理池管理器类"""
|
|
17
|
-
|
|
18
|
-
def __init__(self, proxies: Optional[List[Dict[str, str]]] = None):
|
|
19
|
-
"""
|
|
20
|
-
初始化代理池管理器
|
|
21
|
-
|
|
22
|
-
Args:
|
|
23
|
-
proxies (Optional[List[Dict[str, str]]]): 代理列表
|
|
24
|
-
"""
|
|
25
|
-
self.proxies = proxies or [
|
|
26
|
-
{"http": "http://proxy1.example.com:8080", "https": "https://proxy1.example.com:8080"},
|
|
27
|
-
{"http": "http://proxy2.example.com:8080", "https": "https://proxy2.example.com:8080"},
|
|
28
|
-
{"http": "http://proxy3.example.com:8080", "https": "https://proxy3.example.com:8080"}
|
|
29
|
-
]
|
|
30
|
-
self.proxy_status = {id(proxy): {"last_used": 0, "success_count": 0, "fail_count": 0}
|
|
31
|
-
for proxy in self.proxies}
|
|
32
|
-
|
|
33
|
-
def get_random_proxy(self) -> Dict[str, str]:
|
|
34
|
-
"""
|
|
35
|
-
获取随机代理
|
|
36
|
-
|
|
37
|
-
Returns:
|
|
38
|
-
Dict[str, str]: 代理配置
|
|
39
|
-
"""
|
|
40
|
-
return random.choice(self.proxies)
|
|
41
|
-
|
|
42
|
-
def get_best_proxy(self) -> Dict[str, str]:
|
|
43
|
-
"""
|
|
44
|
-
根据成功率获取最佳代理
|
|
45
|
-
|
|
46
|
-
Returns:
|
|
47
|
-
Dict[str, str]: 代理配置
|
|
48
|
-
"""
|
|
49
|
-
if not self.proxy_status:
|
|
50
|
-
return self.get_random_proxy()
|
|
51
|
-
|
|
52
|
-
# 计算每个代理的成功率
|
|
53
|
-
proxy_scores = []
|
|
54
|
-
for proxy in self.proxies:
|
|
55
|
-
proxy_id = id(proxy)
|
|
56
|
-
status = self.proxy_status.get(proxy_id, {"success_count": 0, "fail_count": 0})
|
|
57
|
-
total = status["success_count"] + status["fail_count"]
|
|
58
|
-
|
|
59
|
-
if total == 0:
|
|
60
|
-
score = 0.5 # 默认成功率
|
|
61
|
-
else:
|
|
62
|
-
score = status["success_count"] / total
|
|
63
|
-
|
|
64
|
-
proxy_scores.append((proxy, score))
|
|
65
|
-
|
|
66
|
-
# 按成功率排序,返回成功率最高的代理
|
|
67
|
-
proxy_scores.sort(key=lambda x: x[1], reverse=True)
|
|
68
|
-
return proxy_scores[0][0]
|
|
69
|
-
|
|
70
|
-
def report_proxy_result(self, proxy: Dict[str, str], success: bool) -> None:
|
|
71
|
-
"""
|
|
72
|
-
报告代理使用结果
|
|
73
|
-
|
|
74
|
-
Args:
|
|
75
|
-
proxy (Dict[str, str]): 代理配置
|
|
76
|
-
success (bool): 是否成功
|
|
77
|
-
"""
|
|
78
|
-
proxy_id = id(proxy)
|
|
79
|
-
if proxy_id not in self.proxy_status:
|
|
80
|
-
self.proxy_status[proxy_id] = {"last_used": 0, "success_count": 0, "fail_count": 0}
|
|
81
|
-
|
|
82
|
-
status = self.proxy_status[proxy_id]
|
|
83
|
-
status["last_used"] = time.time()
|
|
84
|
-
|
|
85
|
-
if success:
|
|
86
|
-
status["success_count"] += 1
|
|
87
|
-
else:
|
|
88
|
-
status["fail_count"] += 1
|
|
89
|
-
|
|
90
|
-
def remove_invalid_proxy(self, proxy: Dict[str, str]) -> None:
|
|
91
|
-
"""
|
|
92
|
-
移除无效代理
|
|
93
|
-
|
|
94
|
-
Args:
|
|
95
|
-
proxy (Dict[str, str]): 代理配置
|
|
96
|
-
"""
|
|
97
|
-
if proxy in self.proxies:
|
|
98
|
-
self.proxies.remove(proxy)
|
|
99
|
-
proxy_id = id(proxy)
|
|
100
|
-
if proxy_id in self.proxy_status:
|
|
101
|
-
del self.proxy_status[proxy_id]
|
|
102
|
-
|
|
103
|
-
|
|
104
|
-
class CaptchaHandler:
|
|
105
|
-
"""验证码处理器类"""
|
|
106
|
-
|
|
107
|
-
def __init__(self, captcha_service: Optional[Callable] = None):
|
|
108
|
-
"""
|
|
109
|
-
初始化验证码处理器
|
|
110
|
-
|
|
111
|
-
Args:
|
|
112
|
-
captcha_service (Optional[Callable]): 验证码识别服务
|
|
113
|
-
"""
|
|
114
|
-
self.captcha_service = captcha_service
|
|
115
|
-
|
|
116
|
-
async def recognize_captcha(self, image_data: bytes,
|
|
117
|
-
captcha_type: str = "image") -> Optional[str]:
|
|
118
|
-
"""
|
|
119
|
-
识别验证码
|
|
120
|
-
|
|
121
|
-
Args:
|
|
122
|
-
image_data (bytes): 验证码图片数据
|
|
123
|
-
captcha_type (str): 验证码类型
|
|
124
|
-
|
|
125
|
-
Returns:
|
|
126
|
-
Optional[str]: 识别结果
|
|
127
|
-
"""
|
|
128
|
-
if self.captcha_service:
|
|
129
|
-
try:
|
|
130
|
-
return await self.captcha_service(image_data, captcha_type)
|
|
131
|
-
except Exception:
|
|
132
|
-
return None
|
|
133
|
-
else:
|
|
134
|
-
# 如果没有配置验证码服务,返回None
|
|
135
|
-
return None
|
|
136
|
-
|
|
137
|
-
async def handle_manual_captcha(self, prompt: str = "请输入验证码: ") -> str:
|
|
138
|
-
"""
|
|
139
|
-
处理手动验证码输入
|
|
140
|
-
|
|
141
|
-
Args:
|
|
142
|
-
prompt (str): 提示信息
|
|
143
|
-
|
|
144
|
-
Returns:
|
|
145
|
-
str: 用户输入的验证码
|
|
146
|
-
"""
|
|
147
|
-
# 在实际应用中,这里可能需要与用户界面交互
|
|
148
|
-
# 为了演示目的,我们模拟用户输入
|
|
149
|
-
print(prompt)
|
|
150
|
-
return input() if not asyncio.get_event_loop().is_running() else ""
|
|
151
|
-
|
|
152
|
-
|
|
153
|
-
class AntiCrawler:
|
|
154
|
-
"""反爬虫应对工具类"""
|
|
155
|
-
|
|
156
|
-
def __init__(self, proxies: Optional[List[Dict[str, str]]] = None,
|
|
157
|
-
captcha_service: Optional[Callable] = None):
|
|
158
|
-
"""
|
|
159
|
-
初始化反爬虫应对工具
|
|
160
|
-
|
|
161
|
-
Args:
|
|
162
|
-
proxies (Optional[List[Dict[str, str]]]): 代理列表
|
|
163
|
-
captcha_service (Optional[Callable]): 验证码识别服务
|
|
164
|
-
"""
|
|
165
|
-
self.proxy_manager = ProxyPoolManager(proxies)
|
|
166
|
-
self.captcha_handler = CaptchaHandler(captcha_service)
|
|
167
|
-
|
|
168
|
-
def get_random_user_agent(self) -> str:
|
|
169
|
-
"""
|
|
170
|
-
获取随机User-Agent
|
|
171
|
-
|
|
172
|
-
Returns:
|
|
173
|
-
str: 随机User-Agent
|
|
174
|
-
"""
|
|
175
|
-
user_agents = [
|
|
176
|
-
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36",
|
|
177
|
-
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36",
|
|
178
|
-
"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:89.0) Gecko/20100101 Firefox/89.0",
|
|
179
|
-
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.1.1 Safari/605.1.15",
|
|
180
|
-
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Edge/91.0.864.59",
|
|
181
|
-
"Mozilla/5.0 (iPhone; CPU iPhone OS 14_6 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.0 Mobile/15E148 Safari/604.1",
|
|
182
|
-
"Mozilla/5.0 (Linux; Android 11; Pixel 5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Mobile Safari/537.36"
|
|
183
|
-
]
|
|
184
|
-
return random.choice(user_agents)
|
|
185
|
-
|
|
186
|
-
def rotate_proxy(self) -> Dict[str, str]:
|
|
187
|
-
"""
|
|
188
|
-
轮换代理
|
|
189
|
-
|
|
190
|
-
Returns:
|
|
191
|
-
Dict[str, str]: 代理配置
|
|
192
|
-
"""
|
|
193
|
-
return self.proxy_manager.get_best_proxy()
|
|
194
|
-
|
|
195
|
-
def handle_captcha(self, response_text: str) -> bool:
|
|
196
|
-
"""
|
|
197
|
-
检测是否遇到验证码
|
|
198
|
-
|
|
199
|
-
Args:
|
|
200
|
-
response_text (str): 响应文本
|
|
201
|
-
|
|
202
|
-
Returns:
|
|
203
|
-
bool: 是否遇到验证码
|
|
204
|
-
"""
|
|
205
|
-
captcha_keywords = ["captcha", "verify", "验证", "验证码", "human verification"]
|
|
206
|
-
return any(keyword in response_text.lower() for keyword in captcha_keywords)
|
|
207
|
-
|
|
208
|
-
def detect_rate_limiting(self, status_code: int, response_headers: Dict[str, Any]) -> bool:
|
|
209
|
-
"""
|
|
210
|
-
检测是否遇到频率限制
|
|
211
|
-
|
|
212
|
-
Args:
|
|
213
|
-
status_code (int): HTTP状态码
|
|
214
|
-
response_headers (Dict[str, Any]): 响应头
|
|
215
|
-
|
|
216
|
-
Returns:
|
|
217
|
-
bool: 是否遇到频率限制
|
|
218
|
-
"""
|
|
219
|
-
# 检查状态码
|
|
220
|
-
if status_code in [429, 503]:
|
|
221
|
-
return True
|
|
222
|
-
|
|
223
|
-
# 检查响应头
|
|
224
|
-
rate_limit_headers = ["x-ratelimit-remaining", "retry-after", "x-ratelimit-reset"]
|
|
225
|
-
return any(header.lower() in [k.lower() for k in response_headers.keys()]
|
|
226
|
-
for header in rate_limit_headers)
|
|
227
|
-
|
|
228
|
-
def random_delay(self, min_delay: float = 1.0, max_delay: float = 3.0) -> None:
|
|
229
|
-
"""
|
|
230
|
-
随机延迟,避免请求过于频繁
|
|
231
|
-
|
|
232
|
-
Args:
|
|
233
|
-
min_delay (float): 最小延迟时间(秒)
|
|
234
|
-
max_delay (float): 最大延迟时间(秒)
|
|
235
|
-
"""
|
|
236
|
-
delay = random.uniform(min_delay, max_delay)
|
|
237
|
-
time.sleep(delay)
|
|
238
|
-
|
|
239
|
-
async def async_random_delay(self, min_delay: float = 1.0, max_delay: float = 3.0) -> None:
|
|
240
|
-
"""
|
|
241
|
-
异步随机延迟,避免请求过于频繁
|
|
242
|
-
|
|
243
|
-
Args:
|
|
244
|
-
min_delay (float): 最小延迟时间(秒)
|
|
245
|
-
max_delay (float): 最大延迟时间(秒)
|
|
246
|
-
"""
|
|
247
|
-
delay = random.uniform(min_delay, max_delay)
|
|
248
|
-
await asyncio.sleep(delay)
|
|
249
|
-
|
|
250
|
-
|
|
251
|
-
# 便捷函数
|
|
252
|
-
def get_random_user_agent() -> str:
|
|
253
|
-
"""获取随机User-Agent"""
|
|
254
|
-
return AntiCrawler().get_random_user_agent()
|
|
255
|
-
|
|
256
|
-
|
|
257
|
-
def rotate_proxy(proxies: Optional[List[Dict[str, str]]] = None) -> Dict[str, str]:
|
|
258
|
-
"""轮换代理"""
|
|
259
|
-
return AntiCrawler(proxies).rotate_proxy()
|
|
260
|
-
|
|
261
|
-
|
|
262
|
-
def handle_captcha(response_text: str) -> bool:
|
|
263
|
-
"""检测是否遇到验证码"""
|
|
264
|
-
return AntiCrawler().handle_captcha(response_text)
|
|
265
|
-
|
|
266
|
-
|
|
267
|
-
def detect_rate_limiting(status_code: int, response_headers: Dict[str, Any]) -> bool:
|
|
268
|
-
"""检测是否遇到频率限制"""
|
|
1
|
+
#!/usr/bin/python
|
|
2
|
+
# -*- coding: UTF-8 -*-
|
|
3
|
+
"""
|
|
4
|
+
# @Time : 2025-09-10 22:00
|
|
5
|
+
# @Author : crawl-coder
|
|
6
|
+
# @Desc : 反爬虫应对工具
|
|
7
|
+
"""
|
|
8
|
+
|
|
9
|
+
import asyncio
|
|
10
|
+
import random
|
|
11
|
+
import time
|
|
12
|
+
from typing import Dict, Any, Optional, List, Callable
|
|
13
|
+
|
|
14
|
+
|
|
15
|
+
class ProxyPoolManager:
|
|
16
|
+
"""代理池管理器类"""
|
|
17
|
+
|
|
18
|
+
def __init__(self, proxies: Optional[List[Dict[str, str]]] = None):
|
|
19
|
+
"""
|
|
20
|
+
初始化代理池管理器
|
|
21
|
+
|
|
22
|
+
Args:
|
|
23
|
+
proxies (Optional[List[Dict[str, str]]]): 代理列表
|
|
24
|
+
"""
|
|
25
|
+
self.proxies = proxies or [
|
|
26
|
+
{"http": "http://proxy1.example.com:8080", "https": "https://proxy1.example.com:8080"},
|
|
27
|
+
{"http": "http://proxy2.example.com:8080", "https": "https://proxy2.example.com:8080"},
|
|
28
|
+
{"http": "http://proxy3.example.com:8080", "https": "https://proxy3.example.com:8080"}
|
|
29
|
+
]
|
|
30
|
+
self.proxy_status = {id(proxy): {"last_used": 0, "success_count": 0, "fail_count": 0}
|
|
31
|
+
for proxy in self.proxies}
|
|
32
|
+
|
|
33
|
+
def get_random_proxy(self) -> Dict[str, str]:
|
|
34
|
+
"""
|
|
35
|
+
获取随机代理
|
|
36
|
+
|
|
37
|
+
Returns:
|
|
38
|
+
Dict[str, str]: 代理配置
|
|
39
|
+
"""
|
|
40
|
+
return random.choice(self.proxies)
|
|
41
|
+
|
|
42
|
+
def get_best_proxy(self) -> Dict[str, str]:
|
|
43
|
+
"""
|
|
44
|
+
根据成功率获取最佳代理
|
|
45
|
+
|
|
46
|
+
Returns:
|
|
47
|
+
Dict[str, str]: 代理配置
|
|
48
|
+
"""
|
|
49
|
+
if not self.proxy_status:
|
|
50
|
+
return self.get_random_proxy()
|
|
51
|
+
|
|
52
|
+
# 计算每个代理的成功率
|
|
53
|
+
proxy_scores = []
|
|
54
|
+
for proxy in self.proxies:
|
|
55
|
+
proxy_id = id(proxy)
|
|
56
|
+
status = self.proxy_status.get(proxy_id, {"success_count": 0, "fail_count": 0})
|
|
57
|
+
total = status["success_count"] + status["fail_count"]
|
|
58
|
+
|
|
59
|
+
if total == 0:
|
|
60
|
+
score = 0.5 # 默认成功率
|
|
61
|
+
else:
|
|
62
|
+
score = status["success_count"] / total
|
|
63
|
+
|
|
64
|
+
proxy_scores.append((proxy, score))
|
|
65
|
+
|
|
66
|
+
# 按成功率排序,返回成功率最高的代理
|
|
67
|
+
proxy_scores.sort(key=lambda x: x[1], reverse=True)
|
|
68
|
+
return proxy_scores[0][0]
|
|
69
|
+
|
|
70
|
+
def report_proxy_result(self, proxy: Dict[str, str], success: bool) -> None:
|
|
71
|
+
"""
|
|
72
|
+
报告代理使用结果
|
|
73
|
+
|
|
74
|
+
Args:
|
|
75
|
+
proxy (Dict[str, str]): 代理配置
|
|
76
|
+
success (bool): 是否成功
|
|
77
|
+
"""
|
|
78
|
+
proxy_id = id(proxy)
|
|
79
|
+
if proxy_id not in self.proxy_status:
|
|
80
|
+
self.proxy_status[proxy_id] = {"last_used": 0, "success_count": 0, "fail_count": 0}
|
|
81
|
+
|
|
82
|
+
status = self.proxy_status[proxy_id]
|
|
83
|
+
status["last_used"] = time.time()
|
|
84
|
+
|
|
85
|
+
if success:
|
|
86
|
+
status["success_count"] += 1
|
|
87
|
+
else:
|
|
88
|
+
status["fail_count"] += 1
|
|
89
|
+
|
|
90
|
+
def remove_invalid_proxy(self, proxy: Dict[str, str]) -> None:
|
|
91
|
+
"""
|
|
92
|
+
移除无效代理
|
|
93
|
+
|
|
94
|
+
Args:
|
|
95
|
+
proxy (Dict[str, str]): 代理配置
|
|
96
|
+
"""
|
|
97
|
+
if proxy in self.proxies:
|
|
98
|
+
self.proxies.remove(proxy)
|
|
99
|
+
proxy_id = id(proxy)
|
|
100
|
+
if proxy_id in self.proxy_status:
|
|
101
|
+
del self.proxy_status[proxy_id]
|
|
102
|
+
|
|
103
|
+
|
|
104
|
+
class CaptchaHandler:
|
|
105
|
+
"""验证码处理器类"""
|
|
106
|
+
|
|
107
|
+
def __init__(self, captcha_service: Optional[Callable] = None):
|
|
108
|
+
"""
|
|
109
|
+
初始化验证码处理器
|
|
110
|
+
|
|
111
|
+
Args:
|
|
112
|
+
captcha_service (Optional[Callable]): 验证码识别服务
|
|
113
|
+
"""
|
|
114
|
+
self.captcha_service = captcha_service
|
|
115
|
+
|
|
116
|
+
async def recognize_captcha(self, image_data: bytes,
|
|
117
|
+
captcha_type: str = "image") -> Optional[str]:
|
|
118
|
+
"""
|
|
119
|
+
识别验证码
|
|
120
|
+
|
|
121
|
+
Args:
|
|
122
|
+
image_data (bytes): 验证码图片数据
|
|
123
|
+
captcha_type (str): 验证码类型
|
|
124
|
+
|
|
125
|
+
Returns:
|
|
126
|
+
Optional[str]: 识别结果
|
|
127
|
+
"""
|
|
128
|
+
if self.captcha_service:
|
|
129
|
+
try:
|
|
130
|
+
return await self.captcha_service(image_data, captcha_type)
|
|
131
|
+
except Exception:
|
|
132
|
+
return None
|
|
133
|
+
else:
|
|
134
|
+
# 如果没有配置验证码服务,返回None
|
|
135
|
+
return None
|
|
136
|
+
|
|
137
|
+
async def handle_manual_captcha(self, prompt: str = "请输入验证码: ") -> str:
|
|
138
|
+
"""
|
|
139
|
+
处理手动验证码输入
|
|
140
|
+
|
|
141
|
+
Args:
|
|
142
|
+
prompt (str): 提示信息
|
|
143
|
+
|
|
144
|
+
Returns:
|
|
145
|
+
str: 用户输入的验证码
|
|
146
|
+
"""
|
|
147
|
+
# 在实际应用中,这里可能需要与用户界面交互
|
|
148
|
+
# 为了演示目的,我们模拟用户输入
|
|
149
|
+
print(prompt)
|
|
150
|
+
return input() if not asyncio.get_event_loop().is_running() else ""
|
|
151
|
+
|
|
152
|
+
|
|
153
|
+
class AntiCrawler:
|
|
154
|
+
"""反爬虫应对工具类"""
|
|
155
|
+
|
|
156
|
+
def __init__(self, proxies: Optional[List[Dict[str, str]]] = None,
|
|
157
|
+
captcha_service: Optional[Callable] = None):
|
|
158
|
+
"""
|
|
159
|
+
初始化反爬虫应对工具
|
|
160
|
+
|
|
161
|
+
Args:
|
|
162
|
+
proxies (Optional[List[Dict[str, str]]]): 代理列表
|
|
163
|
+
captcha_service (Optional[Callable]): 验证码识别服务
|
|
164
|
+
"""
|
|
165
|
+
self.proxy_manager = ProxyPoolManager(proxies)
|
|
166
|
+
self.captcha_handler = CaptchaHandler(captcha_service)
|
|
167
|
+
|
|
168
|
+
def get_random_user_agent(self) -> str:
|
|
169
|
+
"""
|
|
170
|
+
获取随机User-Agent
|
|
171
|
+
|
|
172
|
+
Returns:
|
|
173
|
+
str: 随机User-Agent
|
|
174
|
+
"""
|
|
175
|
+
user_agents = [
|
|
176
|
+
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36",
|
|
177
|
+
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36",
|
|
178
|
+
"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:89.0) Gecko/20100101 Firefox/89.0",
|
|
179
|
+
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.1.1 Safari/605.1.15",
|
|
180
|
+
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Edge/91.0.864.59",
|
|
181
|
+
"Mozilla/5.0 (iPhone; CPU iPhone OS 14_6 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.0 Mobile/15E148 Safari/604.1",
|
|
182
|
+
"Mozilla/5.0 (Linux; Android 11; Pixel 5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Mobile Safari/537.36"
|
|
183
|
+
]
|
|
184
|
+
return random.choice(user_agents)
|
|
185
|
+
|
|
186
|
+
def rotate_proxy(self) -> Dict[str, str]:
|
|
187
|
+
"""
|
|
188
|
+
轮换代理
|
|
189
|
+
|
|
190
|
+
Returns:
|
|
191
|
+
Dict[str, str]: 代理配置
|
|
192
|
+
"""
|
|
193
|
+
return self.proxy_manager.get_best_proxy()
|
|
194
|
+
|
|
195
|
+
def handle_captcha(self, response_text: str) -> bool:
|
|
196
|
+
"""
|
|
197
|
+
检测是否遇到验证码
|
|
198
|
+
|
|
199
|
+
Args:
|
|
200
|
+
response_text (str): 响应文本
|
|
201
|
+
|
|
202
|
+
Returns:
|
|
203
|
+
bool: 是否遇到验证码
|
|
204
|
+
"""
|
|
205
|
+
captcha_keywords = ["captcha", "verify", "验证", "验证码", "human verification"]
|
|
206
|
+
return any(keyword in response_text.lower() for keyword in captcha_keywords)
|
|
207
|
+
|
|
208
|
+
def detect_rate_limiting(self, status_code: int, response_headers: Dict[str, Any]) -> bool:
|
|
209
|
+
"""
|
|
210
|
+
检测是否遇到频率限制
|
|
211
|
+
|
|
212
|
+
Args:
|
|
213
|
+
status_code (int): HTTP状态码
|
|
214
|
+
response_headers (Dict[str, Any]): 响应头
|
|
215
|
+
|
|
216
|
+
Returns:
|
|
217
|
+
bool: 是否遇到频率限制
|
|
218
|
+
"""
|
|
219
|
+
# 检查状态码
|
|
220
|
+
if status_code in [429, 503]:
|
|
221
|
+
return True
|
|
222
|
+
|
|
223
|
+
# 检查响应头
|
|
224
|
+
rate_limit_headers = ["x-ratelimit-remaining", "retry-after", "x-ratelimit-reset"]
|
|
225
|
+
return any(header.lower() in [k.lower() for k in response_headers.keys()]
|
|
226
|
+
for header in rate_limit_headers)
|
|
227
|
+
|
|
228
|
+
def random_delay(self, min_delay: float = 1.0, max_delay: float = 3.0) -> None:
|
|
229
|
+
"""
|
|
230
|
+
随机延迟,避免请求过于频繁
|
|
231
|
+
|
|
232
|
+
Args:
|
|
233
|
+
min_delay (float): 最小延迟时间(秒)
|
|
234
|
+
max_delay (float): 最大延迟时间(秒)
|
|
235
|
+
"""
|
|
236
|
+
delay = random.uniform(min_delay, max_delay)
|
|
237
|
+
time.sleep(delay)
|
|
238
|
+
|
|
239
|
+
async def async_random_delay(self, min_delay: float = 1.0, max_delay: float = 3.0) -> None:
|
|
240
|
+
"""
|
|
241
|
+
异步随机延迟,避免请求过于频繁
|
|
242
|
+
|
|
243
|
+
Args:
|
|
244
|
+
min_delay (float): 最小延迟时间(秒)
|
|
245
|
+
max_delay (float): 最大延迟时间(秒)
|
|
246
|
+
"""
|
|
247
|
+
delay = random.uniform(min_delay, max_delay)
|
|
248
|
+
await asyncio.sleep(delay)
|
|
249
|
+
|
|
250
|
+
|
|
251
|
+
# 便捷函数
|
|
252
|
+
def get_random_user_agent() -> str:
|
|
253
|
+
"""获取随机User-Agent"""
|
|
254
|
+
return AntiCrawler().get_random_user_agent()
|
|
255
|
+
|
|
256
|
+
|
|
257
|
+
def rotate_proxy(proxies: Optional[List[Dict[str, str]]] = None) -> Dict[str, str]:
|
|
258
|
+
"""轮换代理"""
|
|
259
|
+
return AntiCrawler(proxies).rotate_proxy()
|
|
260
|
+
|
|
261
|
+
|
|
262
|
+
def handle_captcha(response_text: str) -> bool:
|
|
263
|
+
"""检测是否遇到验证码"""
|
|
264
|
+
return AntiCrawler().handle_captcha(response_text)
|
|
265
|
+
|
|
266
|
+
|
|
267
|
+
def detect_rate_limiting(status_code: int, response_headers: Dict[str, Any]) -> bool:
|
|
268
|
+
"""检测是否遇到频率限制"""
|
|
269
269
|
return AntiCrawler().detect_rate_limiting(status_code, response_headers)
|