OpenICLR/example.py at main · wonvicky/OpenICLR · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
"""
使用示例
演示如何使用ICLR爬虫
"""

from iclr_scraper import ICLRScraper
from data_storage import DataStorage

# 示例1: 爬取ICLR 2024的完整数据
def example_full_scrape():
    """爬取完整数据（论文+评审+审稿人）"""
    scraper = ICLRScraper(delay=1.0)  # 设置1秒延迟
    storage = DataStorage(output_dir="data")

    # 爬取2024年数据
    data = scraper.scrape_iclr_data(
        year=2024,
        include_reviews=True,
        include_reviewers=True
    )

    # 保存数据
    storage.save_iclr_data(data, 2024)
    print(f"爬取完成！论文数: {data['total_papers']}")


# 示例2: 只爬取论文数据（不包含评审和审稿人）
def example_papers_only():
    """只爬取论文数据"""
    scraper = ICLRScraper(delay=1.0)
    storage = DataStorage(output_dir="data")

    data = scraper.scrape_iclr_data(
        year=2024,
        include_reviews=False,
        include_reviewers=False
    )

    storage.save_iclr_data(data, 2024)


# 示例3: 获取单篇论文的详细信息
def example_single_paper():
    """获取单篇论文的详细信息"""
    scraper = ICLRScraper()

    # 获取论文列表
    submissions = scraper.get_iclr_submissions(year=2024, limit=10)

    if submissions:
        # 获取第一篇论文的详细信息
        paper_id = submissions[0]['id']
        print(f"论文ID: {paper_id}")
        print(f"标题: {submissions[0].get('content', {}).get('title', '')}")

        # 获取评审
        reviews = scraper.get_reviews(paper_id)
        print(f"评审数量: {len(reviews)}")

        # 获取决策
        decision = scraper.get_decision(paper_id)
        if decision:
            print(f"决策: {decision.get('content', {}).get('decision', '')}")


if __name__ == '__main__':
    # 运行示例（取消注释以运行）
    # example_full_scrape()
    # example_papers_only()
    # example_single_paper()
    pass