a26ae50051
- Remove global crawl_slot gate; all CrawlJobs share only executor semaphore - max_concurrent_jobs = max(24, n_plugins+8) for crawl-all + aggregator headroom - BaseHTTPPlugin max_concurrency 3->2; fpw multi-URL plugins 4->2 - fetch_all: short random delay before each request to ease single-host pressure Made-with: Cursor
256 lines
9.6 KiB
Python
256 lines
9.6 KiB
Python
"""通用 HTTP 爬虫基类 - 为基于 HTTP 请求的插件提供封装"""
|
||
import re
|
||
import random
|
||
import asyncio
|
||
import httpx
|
||
from typing import Dict, List, Optional
|
||
from bs4 import BeautifulSoup
|
||
from app.core.plugin_system import BaseCrawlerPlugin
|
||
from app.models.domain import ProxyRaw
|
||
|
||
|
||
VALID_PROTOCOLS = ("http", "https", "socks4", "socks5")
|
||
|
||
|
||
class BaseHTTPPlugin(BaseCrawlerPlugin):
|
||
"""基于 HTTP 的爬虫插件基类"""
|
||
|
||
def __init__(self):
|
||
super().__init__()
|
||
self.user_agents = [
|
||
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
|
||
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36",
|
||
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36",
|
||
"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/121.0",
|
||
]
|
||
self.urls: List[str] = []
|
||
self.current_url: str = ""
|
||
self._client: Optional[httpx.AsyncClient] = None
|
||
self.max_concurrency: int = 2
|
||
|
||
def get_headers(self) -> dict:
|
||
return {
|
||
"User-Agent": random.choice(self.user_agents),
|
||
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
|
||
"Accept-Language": "zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2",
|
||
"Connection": "keep-alive",
|
||
}
|
||
|
||
def _get_client(self) -> httpx.AsyncClient:
|
||
"""获取或创建复用的 AsyncClient"""
|
||
if self._client is None or self._client.is_closed:
|
||
transport = httpx.AsyncHTTPTransport(retries=0)
|
||
self._client = httpx.AsyncClient(
|
||
transport=transport,
|
||
follow_redirects=True,
|
||
# 忽略系统 HTTP(S)_PROXY，避免误配导致列表站全部连接失败
|
||
trust_env=False,
|
||
)
|
||
return self._client
|
||
|
||
@staticmethod
|
||
def _http_timeout(seconds: float) -> httpx.Timeout:
|
||
"""连接阶段单独收紧，避免 AsyncClient 在部分环境下长时间卡在 connect。"""
|
||
t = max(2.0, float(seconds))
|
||
# 国际链路 / 批量爬取时 connect 过短易集体超时
|
||
c = min(12.0, max(4.0, t * 0.4))
|
||
return httpx.Timeout(t, connect=c)
|
||
|
||
@staticmethod
|
||
def _decode_response_body(response: httpx.Response) -> str:
|
||
content = response.content
|
||
encoding = response.encoding
|
||
if encoding == "utf-8" or not encoding:
|
||
try:
|
||
return content.decode("utf-8")
|
||
except UnicodeDecodeError:
|
||
return content.decode("gbk", errors="ignore")
|
||
return content.decode(encoding, errors="ignore")
|
||
|
||
def _sync_get(self, url: str, timeout: float, headers: dict) -> str:
|
||
"""同步 GET（部分站点在 Windows 上 AsyncClient 易 ConnectTimeout，同步 Client 正常）。"""
|
||
to = BaseHTTPPlugin._http_timeout(timeout)
|
||
with httpx.Client(
|
||
transport=httpx.HTTPTransport(retries=0),
|
||
follow_redirects=True,
|
||
trust_env=False,
|
||
) as c:
|
||
r = c.get(url, headers=headers, timeout=to)
|
||
if r.status_code != 200:
|
||
return ""
|
||
return self._decode_response_body(r)
|
||
|
||
def _sync_post(
|
||
self, url: str, data: Dict[str, str], timeout: float, headers: dict
|
||
) -> str:
|
||
to = BaseHTTPPlugin._http_timeout(timeout)
|
||
with httpx.Client(
|
||
transport=httpx.HTTPTransport(retries=0),
|
||
follow_redirects=True,
|
||
trust_env=False,
|
||
) as c:
|
||
r = c.post(url, headers=headers, data=data, timeout=to)
|
||
if r.status_code != 200:
|
||
return ""
|
||
return self._decode_response_body(r)
|
||
|
||
async def fetch(
|
||
self,
|
||
url: str,
|
||
timeout: float = 15.0,
|
||
retries: int = 2,
|
||
raise_for_status: bool = False,
|
||
) -> str:
|
||
"""异步抓取指定 URL 的 HTML 内容"""
|
||
from app.core.log import logger
|
||
client = self._get_client()
|
||
to = self._http_timeout(timeout)
|
||
for attempt in range(retries):
|
||
try:
|
||
response = await client.get(url, headers=self.get_headers(), timeout=to)
|
||
if raise_for_status:
|
||
response.raise_for_status()
|
||
if response.status_code == 200:
|
||
return self._decode_response_body(response)
|
||
logger.warning(f"Fetch {url} returned status {response.status_code}")
|
||
except Exception as e:
|
||
logger.warning(f"Fetch {url} failed (attempt {attempt + 1}/{retries}): {e}")
|
||
if attempt < retries - 1:
|
||
await asyncio.sleep(random.uniform(1, 3))
|
||
try:
|
||
text = await asyncio.to_thread(
|
||
self._sync_get, url, timeout, self.get_headers()
|
||
)
|
||
if text:
|
||
logger.info(f"Fetch {url} 使用同步回退成功")
|
||
return text
|
||
except Exception as e:
|
||
logger.warning(f"Fetch {url} 同步回退失败: {e}")
|
||
return ""
|
||
|
||
async def fetch_post(
|
||
self,
|
||
url: str,
|
||
data: Optional[Dict[str, str]] = None,
|
||
timeout: float = 15.0,
|
||
retries: int = 2,
|
||
) -> str:
|
||
"""POST application/x-www-form-urlencoded，用于 spys.one 等表单页。"""
|
||
from app.core.log import logger
|
||
|
||
client = self._get_client()
|
||
payload = data or {}
|
||
to = self._http_timeout(timeout)
|
||
for attempt in range(retries):
|
||
try:
|
||
response = await client.post(
|
||
url,
|
||
headers=self.get_headers(),
|
||
data=payload,
|
||
timeout=to,
|
||
)
|
||
if response.status_code == 200:
|
||
return self._decode_response_body(response)
|
||
logger.warning(f"POST {url} returned status {response.status_code}")
|
||
except Exception as e:
|
||
logger.warning(f"POST {url} failed (attempt {attempt + 1}/{retries}): {e}")
|
||
if attempt < retries - 1:
|
||
await asyncio.sleep(random.uniform(1, 3))
|
||
try:
|
||
text = await asyncio.to_thread(
|
||
self._sync_post, url, payload, timeout, self.get_headers()
|
||
)
|
||
if text:
|
||
logger.info(f"POST {url} 使用同步回退成功")
|
||
return text
|
||
except Exception as e:
|
||
logger.warning(f"POST {url} 同步回退失败: {e}")
|
||
return ""
|
||
|
||
async def fetch_all(
|
||
self,
|
||
urls: List[str],
|
||
timeout: float = 15.0,
|
||
retries: int = 2,
|
||
) -> List[str]:
|
||
"""并发抓取多个 URL，限制单个插件内部并发"""
|
||
semaphore = asyncio.Semaphore(self.max_concurrency)
|
||
|
||
async def _fetch_limited(url: str):
|
||
async with semaphore:
|
||
await asyncio.sleep(random.uniform(0.08, 0.45))
|
||
return await self.fetch(url, timeout=timeout, retries=retries)
|
||
|
||
tasks = [_fetch_limited(url) for url in urls]
|
||
return await asyncio.gather(*tasks)
|
||
|
||
def parse_text_proxies(self, text: str, protocol: str = "http") -> List[ProxyRaw]:
|
||
"""解析 ip:port 格式的文本代理列表
|
||
|
||
统一处理 \r\n、\n 两种换行以及可能存在的空行。
|
||
"""
|
||
results = []
|
||
text = text.replace("\r\n", "\n").replace("\r", "\n")
|
||
for line in text.split("\n"):
|
||
line = line.strip()
|
||
if not line or ":" not in line:
|
||
continue
|
||
ip, _, port = line.rpartition(":")
|
||
ip = ip.strip()
|
||
port = port.strip()
|
||
if ip and port.isdigit() and 1 <= int(port) <= 65535:
|
||
try:
|
||
results.append(ProxyRaw(ip, int(port), protocol))
|
||
except ValueError:
|
||
continue
|
||
return results
|
||
|
||
def parse_html_table(
|
||
self,
|
||
html: str,
|
||
column_map: dict,
|
||
protocol: str = "http",
|
||
) -> List[ProxyRaw]:
|
||
"""通用 HTML 表格解析器
|
||
|
||
Args:
|
||
html: HTML 文本
|
||
column_map: 列名到索引的映射，如 {"ip": 0, "port": 1, "protocol": 4}
|
||
protocol: 默认协议，如果表格中没有协议列则使用此值
|
||
"""
|
||
results = []
|
||
soup = BeautifulSoup(html, "lxml")
|
||
table = soup.find("table")
|
||
if not table:
|
||
return results
|
||
|
||
ip_idx = column_map.get("ip", 0)
|
||
port_idx = column_map.get("port", 1)
|
||
protocol_idx = column_map.get("protocol", -1)
|
||
|
||
for row in table.find_all("tr"):
|
||
tds = row.find_all("td")
|
||
if len(tds) <= max(ip_idx, port_idx):
|
||
continue
|
||
ip = tds[ip_idx].get_text(strip=True)
|
||
port = tds[port_idx].get_text(strip=True)
|
||
if protocol_idx >= 0 and len(tds) > protocol_idx:
|
||
proto = tds[protocol_idx].get_text(strip=True).lower()
|
||
if proto not in VALID_PROTOCOLS:
|
||
proto = protocol
|
||
else:
|
||
proto = protocol
|
||
|
||
if re.match(r"^\d+\.\d+\.\d+\.\d+$", ip) and port.isdigit() and 1 <= int(port) <= 65535:
|
||
try:
|
||
results.append(ProxyRaw(ip, int(port), proto))
|
||
except ValueError:
|
||
continue
|
||
return results
|
||
|
||
async def close(self):
|
||
"""关闭复用的 HTTP 客户端"""
|
||
if self._client and not self._client.is_closed:
|
||
await self._client.aclose()
|
||
self._client = None
|