si-meng-spec/ProxyPool
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(plugins): fpw parsers for JSON API, mirrors, and looser HTML

Browse Source 
- fpw_proxy_list_download: parse JSON list/proxies bodies; jsDelivr monosans tier; crawl timeout 300s
- fpw_socks_ssl: try parse_html_table before regex
- fpw_hidemy: loose row scan when fixed columns fail
- fpw_proxynova: plain IP/port row fallback
- fpw_spys_one: HTTPS endpoints; crawl timeout 180s
- fpw_gatherproxy: HTTPS + extra JSON key patterns
- fpw_checkerproxy: lower min HTML length for parse
- fpw_premproxy: ip:port regex fallback when few table rows

Made-with: Cursor
This commit is contained in:
祀梦
2026-04-05 14:16:03 +08:00
parent a26ae50051
commit e582067316
8 changed files with 193 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

90
app/plugins/fpw_proxy_list_download.py
View File

@@ -1,5 +1,6 @@
"""www.proxy-list.download 公开 API（README: Free_Proxy_Website）。"""
from typing import List
"""www.proxy-list.download 公开 API（常见为 JSON，内含 list 字段的 ip:port 文本）。"""
import json
from typing import Any, List
from app.core.plugin_system import ProxyRaw
from app.plugins.base import BaseHTTPPlugin
@@ -10,6 +11,7 @@ class FpwProxyListDownloadPlugin(BaseHTTPPlugin):
name = "fpw_proxy_list_download"
display_name = "Proxy-List.download"
description = "proxy-list.download 官方 API（http/https/socks4/socks5）"
crawl_timeout_seconds = 300.0
def __init__(self):
super().__init__()
@@ -20,6 +22,9 @@ class FpwProxyListDownloadPlugin(BaseHTTPPlugin):
("socks4", "https://www.proxy-list.download/api/v1/get?type=socks4"),
("socks5", "https://www.proxy-list.download/api/v1/get?type=socks5"),
]
self._mirror_prefix = (
"https://cdn.jsdelivr.net/gh/monosans/proxy-list@main/proxies/"
)
self.fallback_pairs = [
("http", "https://api.proxyscrape.com/v2/?request=get&protocol=http&timeout=10000&country=all&ssl=all&anonymity=all"),
("https", "https://api.proxyscrape.com/v2/?request=get&protocol=https&timeout=10000&country=all&ssl=all&anonymity=all"),
@@ -27,28 +32,93 @@ class FpwProxyListDownloadPlugin(BaseHTTPPlugin):
("socks5", "https://api.proxyscrape.com/v2/?request=get&protocol=socks5&timeout=10000&country=all&ssl=all&anonymity=all"),
]
def _items_to_proxies(self, items: List[Any], protocol: str) -> List[ProxyRaw]:
out: List[ProxyRaw] = []
for it in items:
if isinstance(it, dict):
ip = str(
it.get("ip")
or it.get("IP")
or it.get("host")
or it.get("Host")
or ""
).strip()
port = it.get("port") or it.get("Port")
if not ip or port is None:
continue
ps = str(port).strip()
if not ps.isdigit() or not (1 <= int(ps) <= 65535):
continue
try:
out.append(ProxyRaw(ip, int(ps), protocol))
except ValueError:
continue
elif isinstance(it, str) and ":" in it:
out.extend(self.parse_text_proxies(it, protocol))
return out
def _parse_api_body(self, text: str, protocol: str) -> List[ProxyRaw]:
text = (text or "").strip()
if not text:
return []
if text[0] in "{[":
try:
data = json.loads(text)
except json.JSONDecodeError:
return self.parse_text_proxies(text, protocol)
if isinstance(data, list):
return self._items_to_proxies(data, protocol)
if isinstance(data, dict):
for key in ("list", "LIST", "data", "Data", "proxies", "Proxies"):
raw = data.get(key)
if isinstance(raw, str) and raw.strip():
return self.parse_text_proxies(raw, protocol)
if isinstance(raw, list):
return self._items_to_proxies(raw, protocol)
return []
return []
return self.parse_text_proxies(text, protocol)
async def crawl(self) -> List[ProxyRaw]:
results: List[ProxyRaw] = []
t_req, n_try = 18.0, 1
urls = [u for _, u in self.api_pairs]
htmls = await self.fetch_all(urls, timeout=25, retries=2)
htmls = await self.fetch_all(urls, timeout=t_req, retries=n_try)
for (protocol, _), text in zip(self.api_pairs, htmls):
if not text:
continue
batch = self.parse_text_proxies(text, protocol)
batch = self._parse_api_body(text, protocol)
if batch:
results.extend(batch)
logger.info(f"{self.display_name} {protocol}: {len(batch)} 条")
logger.info(f"{self.display_name} API {protocol}: {len(batch)} 条")
if not results:
logger.warning(f"{self.display_name} 主 API 无数据，尝试 ProxyScrape 备用")
fb_urls = [u for _, u in self.fallback_pairs]
fb_htmls = await self.fetch_all(fb_urls, timeout=25, retries=2)
for (protocol, _), text in zip(self.fallback_pairs, fb_htmls):
logger.warning(f"{self.display_name} 主 API 无数据，尝试 jsDelivr 文本镜像")
mirror_pairs = [
(p, f"{self._mirror_prefix}{p}.txt")
for p in ("http", "https", "socks4", "socks5")
]
m_urls = [u for _, u in mirror_pairs]
m_htmls = await self.fetch_all(m_urls, timeout=22.0, retries=2)
for (protocol, _), text in zip(mirror_pairs, m_htmls):
if not text:
continue
batch = self.parse_text_proxies(text, protocol)
if batch:
results.extend(batch)
logger.info(f"{self.display_name} fallback {protocol}: {len(batch)} 条")
logger.info(f"{self.display_name} 镜像 {protocol}: {len(batch)} 条")
if not results:
logger.warning(f"{self.display_name} 镜像无数据，尝试 ProxyScrape API")
fb_urls = [u for _, u in self.fallback_pairs]
fb_htmls = await self.fetch_all(fb_urls, timeout=20.0, retries=1)
for (protocol, _), text in zip(self.fallback_pairs, fb_htmls):
if not text:
continue
batch = self._parse_api_body(text, protocol)
if not batch:
batch = self.parse_text_proxies(text, protocol)
if batch:
results.extend(batch)
logger.info(f"{self.display_name} ProxyScrape {protocol}: {len(batch)} 条")
if results:
logger.info(f"{self.display_name} 合计 {len(results)} 条")
return results