From b30866992b9ee2b2f315682201aea2978620e489 Mon Sep 17 00:00:00 2001 From: DmitryRyumin Date: Fri, 19 Jan 2024 14:22:45 +0000 Subject: [PATCH] Copy Parse Markdown and Generate JSON from Source Repo --- code/markdown_to_json_parser.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/code/markdown_to_json_parser.py b/code/markdown_to_json_parser.py index eb16c48..f782408 100644 --- a/code/markdown_to_json_parser.py +++ b/code/markdown_to_json_parser.py @@ -345,7 +345,8 @@ def parse_paper_links(html): def extract_paper_data(paper_section, columns): title_column = columns[0] - title = title_column.get_text(strip=True) + # title = title_column.get_text(strip=True) + title = title_column.a.encode_contents().decode("utf-8") title_link = title_column.find("a") title_page = title_link["href"] if title_link else None