Add maxlaw PC spider and shared proxy limiter

This commit is contained in:
hello-dd-code
2026-04-03 16:06:28 +08:00
parent ff5e04d986
commit ba04fe42fc
9 changed files with 651 additions and 78 deletions
+5 -2
View File
@@ -20,6 +20,7 @@ from request.proxy_config import get_proxies, report_proxy_status
from Db import Db
from config import HEADERS
from utils.rate_limiter import request_slot
LIST_URL = "https://m.66law.cn/findlawyer/rpc/loadlawyerlist/"
DOMAIN = "华律"
@@ -100,7 +101,8 @@ class HualvSpider:
def _post(self, data: Dict[str, str], max_retries: int = 3) -> Optional[Dict]:
for attempt in range(max_retries):
try:
resp = self.session.post(LIST_URL, data=data, timeout=20, verify=False)
with request_slot():
resp = self.session.post(LIST_URL, data=data, timeout=20, verify=False)
status_code = resp.status_code
text = resp.text
resp.close()
@@ -272,7 +274,8 @@ class HualvSpider:
def _get_detail(self, url: str, max_retries: int = 3) -> Optional[str]:
for attempt in range(max_retries):
try:
resp = self.session.get(url, timeout=15, verify=False)
with request_slot():
resp = self.session.get(url, timeout=15, verify=False)
status_code = resp.status_code
text = resp.text
resp.close()