checkpoint: pipeline + 27k/h baseline before sitemap discovery
This commit is contained in:
42
_diag_vps.sh
Normal file
42
_diag_vps.sh
Normal file
@@ -0,0 +1,42 @@
|
||||
#!/bin/bash
|
||||
echo "=========================================="
|
||||
echo "== 1. PROXY/HTTP CONFIG в .env =="
|
||||
echo "=========================================="
|
||||
cd /root/iaai_scraper_project
|
||||
grep -iE "PROXY|HTTP_MODE|USER_AGENT|IAAI_BASE|IAAI_.*URL|BRIGHT" .env | grep -v "^#"
|
||||
echo ""
|
||||
echo "=========================================="
|
||||
echo "== 2. ВНЕШНИЙ IP VPS =="
|
||||
echo "=========================================="
|
||||
curl -s --max-time 10 https://api.ipify.org; echo ""
|
||||
echo ""
|
||||
echo "=========================================="
|
||||
echo "== 3. ПРЯМОЙ ЗАПРОС IAAI (без прокси) =="
|
||||
echo "=========================================="
|
||||
curl -s -o /dev/null -w "HTTP=%{http_code} time=%{time_total}s size=%{size_download}\n" --max-time 20 "https://www.iaai.com/"
|
||||
curl -s -o /tmp/iaai_root.html -w "HTTP=%{http_code} size=%{size_download}\n" --max-time 20 -A "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36" "https://www.iaai.com/"
|
||||
echo "--- первые 400 байт ответа ---"
|
||||
head -c 400 /tmp/iaai_root.html; echo ""
|
||||
echo "--- признак Incapsula/bot-check ---"
|
||||
grep -oiE "incapsula|_Incapsula_|captcha|access denied|bot|cloudflare" /tmp/iaai_root.html | sort -u
|
||||
echo ""
|
||||
echo "=========================================="
|
||||
echo "== 4. POST /Search (как это делает парсер) =="
|
||||
echo "=========================================="
|
||||
curl -s -o /tmp/iaai_search.html -w "HTTP=%{http_code} size=%{size_download}\n" --max-time 20 \
|
||||
-H "Content-Type: application/x-www-form-urlencoded" \
|
||||
-H "Accept: application/json, text/html, */*" \
|
||||
-A "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36" \
|
||||
-X POST "https://www.iaai.com/Search" \
|
||||
--data "Make=TOYOTA&YearMin=1900&YearMax=2012&Page=1"
|
||||
head -c 400 /tmp/iaai_search.html; echo ""
|
||||
echo ""
|
||||
echo "=========================================="
|
||||
echo "== 5. PROXY env внутри worker-контейнера =="
|
||||
echo "=========================================="
|
||||
docker exec iaai-worker env | grep -iE "PROXY|IAAI|HTTP_" | sort
|
||||
echo ""
|
||||
echo "=========================================="
|
||||
echo "== 6. Последние ERROR-логи worker =="
|
||||
echo "=========================================="
|
||||
docker logs iaai-worker --tail 200 2>&1 | grep -iE "proxy|bright|incapsula|403|500|429|blocked" | tail -15
|
||||
Reference in New Issue
Block a user