1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
| import asyncio
import aiohttp
import weakref
from contextlib import asynccontextmanager
from typing import AsyncGenerator, Optional
import logging
class OptimizedSpider:
"""优化后的爬虫实现"""
def __init__(self, max_concurrent: int = 200):
self.max_concurrent = max_concurrent
self.semaphore = asyncio.Semaphore(max_concurrent)
self.stats = {
"processed_pages": 0,
"failed_pages": 0,
"current_memory_mb": 0
}
@asynccontextmanager
async def get_session(self) -> AsyncGenerator[aiohttp.ClientSession, None]:
"""会话上下文管理器"""
connector = aiohttp.TCPConnector(
limit=100,
limit_per_host=20,
ttl_dns_cache=300,
use_dns_cache=True,
)
timeout = aiohttp.ClientTimeout(total=30, connect=10)
session = aiohttp.ClientSession(
connector=connector,
timeout=timeout
)
try:
yield session
finally:
await session.close()
await asyncio.sleep(0.1)
async def crawl_website(self, base_url: str, urls: List[str],
callback=None) -> Dict:
"""爬取网站 - 优化版本"""
async with self.get_session() as session:
batch_size = 50
results = {
"processed": 0,
"failed": 0,
"success": 0
}
for i in range(0, len(urls), batch_size):
batch_urls = urls[i:i + batch_size]
batch_tasks = []
for url in batch_urls:
task = self._crawl_page_optimized(session, url, callback)
batch_tasks.append(task)
batch_results = await asyncio.gather(*batch_tasks, return_exceptions=True)
for result in batch_results:
if isinstance(result, Exception):
results["failed"] += 1
logging.error(f"批次处理异常: {result}")
else:
results["processed"] += 1
if result.get("success"):
results["success"] += 1
del batch_tasks
del batch_results
gc.collect()
self.stats["processed_pages"] += len(batch_urls)
current_memory = psutil.Process().memory_info().rss / 1024 / 1024
self.stats["current_memory_mb"] = current_memory
if i % (batch_size * 10) == 0:
logging.info(f"处理进度: {i}/{len(urls)}, 内存使用: {current_memory:.1f}MB")
return results
async def _crawl_page_optimized(self, session: aiohttp.ClientSession,
url: str, callback=None) -> Dict:
"""优化的页面爬取方法"""
async with self.semaphore:
try:
async with session.get(url) as response:
if response.status != 200:
return {"url": url, "success": False, "error": f"HTTP {response.status}"}
content = await response.text()
parsed_data = await self._parse_page_lightweight(content)
if callback:
await callback(url, parsed_data)
return {
"url": url,
"success": True,
"content_length": len(content),
"parsed_items": len(parsed_data)
}
except asyncio.TimeoutError:
return {"url": url, "success": False, "error": "timeout"}
except Exception as e:
return {"url": url, "success": False, "error": str(e)}
async def _parse_page_lightweight(self, content: str) -> List[Dict]:
"""轻量级页面解析"""
try:
from lxml import html
tree = html.fromstring(content)
products = []
product_elements = tree.xpath('//div[@class="product-item"]')
for element in product_elements:
try:
product = {
"title": element.xpath('.//h3/text()')[0] if element.xpath('.//h3/text()') else "",
"price": element.xpath('.//span[@class="price"]/text()')[0] if element.xpath('.//span[@class="price"]/text()') else "",
"link": element.xpath('.//a/@href')[0] if element.xpath('.//a/@href') else ""
}
if product["title"]:
products.append(product)
except Exception as e:
logging.debug(f"解析产品元素失败: {e}")
continue
return products
except ImportError:
from bs4 import BeautifulSoup
soup = BeautifulSoup(content, 'lxml')
products = []
product_containers = soup.find_all('div', class_='product-item')[:50]
for container in product_containers:
try:
title_elem = container.find('h3')
price_elem = container.find('span', class_='price')
link_elem = container.find('a')
product = {
"title": title_elem.get_text(strip=True) if title_elem else "",
"price": price_elem.get_text(strip=True) if price_elem else "",
"link": link_elem.get('href', '') if link_elem else ""
}
if product["title"]:
products.append(product)
except Exception as e:
logging.debug(f"BeautifulSoup解析失败: {e}")
continue
del soup
return products
async def save_data_callback(url: str, products: List[Dict]):
"""数据保存回调 - 流式处理"""
if not products:
return
try:
import aiofiles
import json
filename = f"data/{url.replace('/', '_').replace(':', '')}.json"
async with aiofiles.open(filename, 'w', encoding='utf-8') as f:
await f.write(json.dumps(products, ensure_ascii=False, indent=2))
logging.info(f"保存数据成功: {url}, 产品数: {len(products)}")
except Exception as e:
logging.error(f"保存数据失败: {url}, 错误: {e}")
|
