pubs-rss.qmd

---
title: "PubMed Article Replication"
output:
  quarto::pdf_document:
    latex_engine: xelatex
---

```{r setup, include=FALSE}
library(rvest)
library(quarto)
library(tidyverse)
```


```{r}

# Fetch the webpage content
url <- "https://pubmed.ncbi.nlm.nih.gov/36460922/"
page <- read_html(url)

# Extract article title
title <- page %>%
  html_nodes(".heading-title") %>%
  html_text() %>%
  str_trim()

# Extract article abstract
abstract <- page %>%
  html_nodes(".abstract-content") %>%
  html_text() %>%
  str_trim()

# Extract article authors
authors <- page %>%
  html_nodes(".authors-list") %>%
  html_text() %>%
  str_trim()

# Extract article journal and publication date
journal_date <- page %>%
  html_nodes(".journal-actions") %>%
  html_text() %>%
  str_trim()

# Print the extracted content
cat(paste("### Title:\n\n", title, "\n\n"))
cat(paste("### Authors:\n\n", authors, "\n\n"))
cat(paste("### Journal and Publication Date:\n\n", journal_date, "\n\n"))
cat(paste("### Abstract:\n\n", abstract, "\n\n"))

```

```{r}