gfil-blog/deploy_scripts/indexnow_submit.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
IndexNow 批量提交 + Google Sitemap Ping
用法: python indexnow_submit.py
"""

import urllib.request
import urllib.parse
import sys
import io
import os
import json

sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')

SITE = 'https://blog.quant-view.xyz'
INDEXNOW_KEY = os.environ.get('INDEXNOW_KEY', 'f8a7c3e2b1d0495a8f6c7e3d2b1a0495f')  # 优先从环境变量读取

PAGES = [
    '/',
    '/gfil-boss-panel-v70-review.html',
    '/gold-xauusd-trading-2026.html',
    '/tradingview-vs-gfil-boss.html',
    '/why-retail-traders-lose-money.html',
    '/trading-activity-tracked.html',
    '/forex-scalping-2026.html',
    '/institutional-traders-see-market-moves.html',
    '/ai-driven-market-intelligence.html',
    '/wti-crude-oil-2026.html',
    '/gfil-boss-panel-faq.html',
    '/order-flow-trading.html',
    '/bloomberg-alternative.html',
    '/websocket-vs-rest-api.html',
    '/trading-signal-tracking.html',
    '/anonymous-trading-platform.html',
    '/about.html',
    '/free-ebook.html',
    '/zh/',
    '/es/',
    '/ar/',
]

# 多语言页面
for lang in ['zh', 'es', 'ar']:
    for page in PAGES[1:17]:  # 15 articles
        if page != '/' and not page.startswith('/about'):
            PAGES.append(f'/{lang}{page}')

HEADERS = {
    'Content-Type': 'application/json; charset=utf-8',
    'User-Agent': 'GFIL-Blog-IndexNow/1.0',
}


def submit_indexnow():
    """提交到 IndexNow (Bing + Yandex + Seznam)"""
    urls = [f'{SITE}{p}' for p in PAGES]
    payload = json.dumps({
        'host': 'blog.quant-view.xyz',
        'key': INDEXNOW_KEY,
        'keyLocation': f'{SITE}/{INDEXNOW_KEY}.txt',
        'urlList': urls,
    })

    endpoints = [
        ('Bing/IndexNow', 'https://api.indexnow.org/indexnow'),
        ('Bing', 'https://www.bing.com/indexnow'),
        ('Yandex', 'https://yandex.com/indexnow'),
    ]

    for name, endpoint in endpoints:
        try:
            req = urllib.request.Request(endpoint, data=payload.encode(), headers=HEADERS)
            with urllib.request.urlopen(req, timeout=15) as resp:
                body = resp.read().decode()
                print(f'  ✅ {name}: HTTP {resp.status}')
        except Exception as e:
            print(f'  ❌ {name}: {e}')


def ping_google():
    """通过 sitemap ping 通知 Google"""
    sitemap_url = f'{SITE}/sitemap.xml'
    ping_url = f'https://www.google.com/ping?sitemap={urllib.parse.quote(sitemap_url)}'

    try:
        req = urllib.request.Request(ping_url, headers={'User-Agent': 'GFIL-Blog'})
        with urllib.request.urlopen(req, timeout=15) as resp:
            print(f'  ✅ Google Sitemap Ping: HTTP {resp.status}')
    except Exception as e:
        print(f'  ❌ Google Ping: {e}')

    # Also submit news sitemap
    news_sitemap = f'{SITE}/news-sitemap.xml'
    ping2 = f'https://www.google.com/ping?sitemap={urllib.parse.quote(news_sitemap)}'
    try:
        req = urllib.request.Request(ping2, headers={'User-Agent': 'GFIL-Blog'})
        with urllib.request.urlopen(req, timeout=15) as resp:
            print(f'  ✅ Google News Sitemap Ping: HTTP {resp.status}')
    except Exception as e:
        print(f'  ❌ Google News Ping: {e}')


def check_index_status():
    """快速检查各页面 HTTP 状态"""
    print(f'\n--- SEO 健康检查 ---')
    issues = 0
    for page in PAGES[:20]:  # 只检查核心页面
        url = f'{SITE}{page}'
        try:
            req = urllib.request.Request(url, headers={'User-Agent': 'Mozilla/5.0'})
            with urllib.request.urlopen(req, timeout=10) as resp:
                html = resp.read().decode('utf-8', errors='replace')
                has_title = '<title>' in html
                has_desc = 'meta name="description"' in html
                if resp.status == 200 and has_title and has_desc:
                    print(f'  ✅ {page}')
                else:
                    issues += 1
                    print(f'  ⚠️ {page}: HTTP {resp.status}, title={has_title}, desc={has_desc}')
        except Exception as e:
            issues += 1
            print(f'  ❌ {page}: {e}')

    if issues:
        print(f'\n  ⚠️ {issues} 个页面需要关注')
    else:
        print(f'\n  ✅ 所有核心页面正常')


if __name__ == '__main__':
    print(f'=== IndexNow 批量提交 ===')
    print(f'站点: {SITE}')
    print(f'URL 数量: {len(PAGES)}')

    print(f'\n--- 提交 IndexNow ---')
    submit_indexnow()

    print(f'\n--- 通知 Google ---')
    ping_google()

    check_index_status()
    print(f'\n=== 完成 ===')