#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""抓取 GMI 中国分子诊断市场原始页面并存为 PDF + 文本"""
import os

from playwright.sync_api import sync_playwright

OUT_DIR = '/Users/liuxinyuan/Desktop/Hermes输出-工作类/资料/文献与专利/2025-2027/market'
URL = 'https://www.gminsights.com/industry-analysis/china-molecular-diagnostics-market'
os.makedirs(OUT_DIR, exist_ok=True)

with sync_playwright() as p:
    br = p.chromium.launch(channel='chrome')
    pg = br.new_page(viewport={'width': 1280, 'height': 1600})
    pg.goto(URL, wait_until='domcontentloaded', timeout=90000)
    pg.wait_for_timeout(4000)
    text = pg.inner_text('body')
    open(os.path.join(OUT_DIR, 'GMI_China_MDx_2025-2034.txt'), 'w', encoding='utf-8').write(text)
    pg.pdf(path=os.path.join(OUT_DIR, 'GMI_China_MDx_2025-2034.pdf'),
           format='A4', print_background=True)
    pg.screenshot(path=os.path.join(OUT_DIR, 'GMI_China_MDx_2025-2034.png'), full_page=False)
    print('标题:', pg.title())
    print('文本长度:', len(text))
    br.close()
print('输出目录:', OUT_DIR)