426cf4d2cd
- Add src/university_scraper module with scraper, analyzer, and CLI - Add backend FastAPI service with API endpoints and database models - Add frontend React app with university management pages - Add configs for Harvard, Manchester, and UCL universities - Add artifacts with various scraper implementations - Add Docker compose configuration for deployment - Update .gitignore to exclude generated files 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
84 lines
3.0 KiB
Python
84 lines
3.0 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
调试Computer Science的Faculty页面
|
|
"""
|
|
|
|
import asyncio
|
|
from playwright.async_api import async_playwright
|
|
|
|
|
|
async def debug_cs():
|
|
async with async_playwright() as p:
|
|
browser = await p.chromium.launch(headless=False)
|
|
page = await browser.new_page()
|
|
|
|
# 访问Computer Science GSAS页面
|
|
gsas_url = "https://gsas.harvard.edu/program/computer-science"
|
|
print(f"访问: {gsas_url}")
|
|
|
|
await page.goto(gsas_url, wait_until="domcontentloaded", timeout=30000)
|
|
await page.wait_for_timeout(3000)
|
|
|
|
await page.screenshot(path="cs_gsas_page.png", full_page=True)
|
|
print("截图已保存: cs_gsas_page.png")
|
|
|
|
# 查找所有链接
|
|
links = await page.evaluate('''() => {
|
|
const links = [];
|
|
document.querySelectorAll('a[href]').forEach(a => {
|
|
const text = a.innerText.trim();
|
|
const href = a.href;
|
|
if (text && text.length > 2 && text.length < 100) {
|
|
links.push({text: text, href: href});
|
|
}
|
|
});
|
|
return links;
|
|
}''')
|
|
|
|
print(f"\n页面上的所有链接 ({len(links)} 个):")
|
|
for link in links:
|
|
print(f" - {link['text'][:60]} -> {link['href']}")
|
|
|
|
# 查找可能的Faculty或People链接
|
|
print("\n\n查找Faculty/People相关链接:")
|
|
for link in links:
|
|
text_lower = link['text'].lower()
|
|
href_lower = link['href'].lower()
|
|
if 'faculty' in text_lower or 'people' in href_lower or 'faculty' in href_lower or 'website' in text_lower:
|
|
print(f" * {link['text']} -> {link['href']}")
|
|
|
|
# 尝试访问SEAS (School of Engineering)
|
|
print("\n\n尝试访问SEAS Computer Science页面...")
|
|
seas_url = "https://seas.harvard.edu/computer-science"
|
|
await page.goto(seas_url, wait_until="domcontentloaded", timeout=30000)
|
|
await page.wait_for_timeout(2000)
|
|
|
|
await page.screenshot(path="seas_cs_page.png", full_page=True)
|
|
print("截图已保存: seas_cs_page.png")
|
|
|
|
seas_links = await page.evaluate('''() => {
|
|
const links = [];
|
|
document.querySelectorAll('a[href]').forEach(a => {
|
|
const text = a.innerText.trim();
|
|
const href = a.href;
|
|
const lowerText = text.toLowerCase();
|
|
const lowerHref = href.toLowerCase();
|
|
if ((lowerText.includes('faculty') || lowerText.includes('people') ||
|
|
lowerHref.includes('faculty') || lowerHref.includes('people')) &&
|
|
text.length > 2) {
|
|
links.push({text: text, href: href});
|
|
}
|
|
});
|
|
return links;
|
|
}''')
|
|
|
|
print(f"\nSEAS页面上的Faculty/People链接:")
|
|
for link in seas_links:
|
|
print(f" * {link['text']} -> {link['href']}")
|
|
|
|
await browser.close()
|
|
|
|
|
|
if __name__ == "__main__":
|
|
asyncio.run(debug_cs())
|