:::
---
## Other Publications from PubMed Feed
```{code-cell} python
:tags: [remove-input]
from IPython.display import display, Markdown, HTML
import feedparser
from dateutil import parser as dateparser
import re
import html
rss_url = "https://pubmed.ncbi.nlm.nih.gov/rss/search/1b_xvYg-6HN0FKdpXW1N__SKCt4EGO7EaY44wp81q6vp5tMsAO/?limit=20&utm_campaign=pubmed-2&fc=20250724150114"
feed = feedparser.parse(rss_url)
def format_authors(authors_list):
if not authors_list:
return "Unknown author"
names = [author["name"] for author in authors_list]
if len(names) > 10:
return f"{names[0]} et al."
return ", ".join(names)
def get_tag(authors_list, year):
if not authors_list or not year:
return "[UNKXX]"
last = authors_list[0]["name"].split()[-1]
return f"[{last[:3].upper()}{year[-2:] if year.isdigit() else 'XX'}]"
def extract_doi(entry):
dc_id = entry.get("dc_identifier", "")
if isinstance(dc_id, str) and dc_id.lower().startswith("doi:"):
return dc_id[4:]
content = entry.get("content", [])
if content and "value" in content[0]:
value = html.unescape(content[0]["value"])
match = re.search(r'https?://doi\.org/(10\.\d{4,9}/[-._;()/:A-Z0-9]+)', value, re.IGNORECASE)
if match:
return match.group(1)
return None
for entry in feed.entries:
try:
title = entry.title.strip()
year = str(dateparser.parse(entry.get("published", "")).year)
authors_list = entry.get("authors", [])
authors = format_authors(authors_list)
journal = entry.get("dc_source") or "Unknown journal"
tag = get_tag(authors_list, year)
doi = extract_doi(entry)
link_line = f"🔗 [https://doi.org/{doi}](https://doi.org/{doi})" if doi else "🔗 DOI not found"
display(HTML(
f"""