diff --git a/docs/coverage/iclr-archive-2014-2016.md b/docs/coverage/iclr-archive-2014-2016.md index 958a8be..36f92f1 100644 --- a/docs/coverage/iclr-archive-2014-2016.md +++ b/docs/coverage/iclr-archive-2014-2016.md @@ -10,7 +10,7 @@ 2015 的 11 篇 oral 全部再次出现在 poster 段落中。相同年份、轨道及 arXiv 标识的重复展示只生成一条来源记录,但每次展示的标题、作者显示字符串、链接、版本和段落均保留在 `source_variants`。两处标题或解析作者冲突时停止采集、等待人工核查。不同年份或不同轨道不合并投稿。 -2014 的作者以分号列出,一条有末尾分号,一条标题不在普通段落中,部分作者段落拆成多个格式片段;必须读取完整作者段落,不能只读首个斜体片段。2016 的代码链接不属于作者。保留原文,解析结果不替代来源证据。oral、poster 作为 `iclr_archive:presentation` 标签,不改成独立投稿轨道。arXiv 版本留在来源变体中,稳定标识使用去版本号的编号。 +2014 的作者以分号列出,一条有末尾分号,一条标题和作者斜体块不在普通段落中,部分作者段落拆成多个格式片段;必须读取完整作者段落或独立斜体块,不能只读首个格式片段。2016 的代码链接不属于作者。保留原文,解析结果不替代来源证据。oral、poster 作为 `iclr_archive:presentation` 标签,不改成独立投稿轨道。arXiv 版本留在来源变体中,稳定标识使用去版本号的编号。 ## 来源快照与运行 diff --git a/paper_atlas/collectors/iclr_archive.py b/paper_atlas/collectors/iclr_archive.py index 62c060e..98326c5 100644 --- a/paper_atlas/collectors/iclr_archive.py +++ b/paper_atlas/collectors/iclr_archive.py @@ -81,9 +81,9 @@ def parse_page(html, year, evidence): for following in nodes[index+sum(1 for _ in link.walk()):]: if following.tag == 'a' and arxiv_link(following.attrs.get('href', '')): break - if following.tag == 'p' and any( + if following.tag in ('i', 'em') or (following.tag == 'p' and any( n.tag in ('i', 'em') or 'font-style:italic' in n.attrs.get('style', '').replace(' ', '') - for n in following.walk()): + for n in following.walk())): text = clean(following.text()) if text: display = text diff --git a/tests/test_iclr_archive.py b/tests/test_iclr_archive.py index bf26990..94e4407 100644 --- a/tests/test_iclr_archive.py +++ b/tests/test_iclr_archive.py @@ -50,12 +50,15 @@ class IclrArchiveTests(unittest.TestCase): html = ('

Conference Proceedings

conference papers accepted

' '
A research title
' '

Jane Doe; ' - 'Bob Smith; Carol Wu;

') - row, = archive.parse_page(html, 2014, {'observed_at': OBSERVED}) + 'Bob Smith; Carol Wu;

' + '
Another title' + '
First Author; Second Author
') + row, unwrapped = archive.parse_page(html, 2014, {'observed_at': OBSERVED}) self.assertEqual(row['title'], 'A research title') self.assertEqual(row['authors'], ['Jane Doe', 'Bob Smith', 'Carol Wu']) self.assertEqual(row['metadata']['source_variants'][0]['authors_display'], 'Jane Doe; Bob Smith; Carol Wu;') self.assertEqual(row['track'], 'main') + self.assertEqual(unwrapped['authors'], ['First Author', 'Second Author']) def test_same_arxiv_in_different_tracks_keeps_separate_source_attempts(self): html = page2015().replace('1412.0002', '1412.0001v3')