data(stop_words) # from tidytext
tsl_opinion_titles |>
  tidytext::unnest_tokens(word, title) |>
  anti_join(stop_words) |>
  count(word, sort = TRUE) |>
  slice_head(n = 20) |>
  mutate(word = fct_reorder(word, n)) |>
  ggplot(aes(y = word, x = n, fill = log(n))) +
  geom_col(show.legend = FALSE) +
  theme_minimal(base_size = 16) +
  labs(
    x = "Number of mentions",
    y = "Word",
    title = "The Student Life - Opinion pieces",
    subtitle = "Common words in the 500 most recent opinion pieces",
    caption = "Source: Data scraped from The Student Life on November 8, 2026"
  ) +
  theme(
    plot.title.position = "plot",
    plot.caption = element_text(color = "gray30")
  )

afinn_sentiments <- get_sentiments("afinn") # need tidytext and textdata
tsl_opinion_titles |>
  tidytext::unnest_tokens(word, first_p) |>
  anti_join(stop_words) |>
  left_join(afinn_sentiments) |>
  group_by(authors, title) |>
  summarize(total_sentiment = sum(value, na.rm = TRUE), .groups = "drop") |>
  group_by(authors) |>
  summarize(
    n_articles = n(),
    avg_sentiment = mean(total_sentiment, na.rm = TRUE),
  ) |>
  filter(n_articles > 1 & !is.na(authors)) |>
  arrange(desc(avg_sentiment)) |>
  slice(c(1:10, 69:78)) |>
  mutate(
    authors = fct_reorder(authors, avg_sentiment),
    neg_pos = if_else(avg_sentiment < 0, "neg", "pos"),
    label_position = if_else(neg_pos == "neg", 0.25, -0.25)
  ) |>
  ggplot(aes(y = authors, x = avg_sentiment)) +
  geom_col(aes(fill = neg_pos), show.legend = FALSE) +
  geom_text(
    aes(x = label_position, label = authors, color = neg_pos),
    hjust = c(rep(1, 10), rep(0, 10)),
    show.legend = FALSE,
    fontface = "bold"
  ) +
  geom_text(
    aes(label = round(avg_sentiment, 1)),
    hjust = c(rep(1.25, 10), rep(-0.25, 10)),
    color = "white",
    fontface = "bold"
  ) +
  scale_fill_manual(values = c("neg" = "#4d4009", "pos" = "#FF4B91")) +
  scale_color_manual(values = c("neg" = "#4d4009", "pos" = "#FF4B91")) +
  scale_x_continuous(breaks = -5:5, minor_breaks = NULL) +
  scale_y_discrete(breaks = NULL) +
  coord_cartesian(xlim = c(-5, 5)) +
  labs(
    x = "negative  ←     Average sentiment score (AFINN)     →  positive",
    y = NULL,
    title = "The Student Life - Opinion pieces\nAverage sentiment scores of first paragraph by author",
    subtitle = "Top 10 average positive and negative scores",
    caption = "Source: Data scraped from The Student Life on November 8, 2026"
  ) +
  theme_void(base_size = 16) +
  theme(
    plot.title = element_text(hjust = 0.5),
    plot.subtitle = element_text(
      hjust = 0.5,
      margin = unit(c(0.5, 0, 1, 0), "lines")
    ),
    axis.text.y = element_blank(),
    plot.caption = element_text(color = "gray30")
  )

html <-
  '<html>
  <head>
    <title>This is a title</title>
  </head>
  <body>
    <p align="center">Hello world!</p>
    <br>
    <div class="name" id="first">John</div>
    <div class="name" id="last">Doe</div>
    <div class="contact">
      <div class="home">555-555-1234</div>
      <div class="home">555-555-2345</div>
      <div class="work">555-555-9999</div>
      <div class="fax">555-555-8888</div>
    </div>
  </body>
</html>'

read_html(html) |> html_elements(".name")

html_table <-
  '<html>
  <head>
    <title>This is a title</title>
  </head>
  <body>
    <table>
      <tr> <th>a</th> <th>b</th> <th>c</th> </tr>
      <tr> <td>1</td> <td>2</td> <td>3</td> </tr>
      <tr> <td>2</td> <td>3</td> <td>4</td> </tr>
      <tr> <td>3</td> <td>4</td> <td>5</td> </tr>
    </table>
  </body>
</html>'

tsl_page <- read_html("https://tsl.news/category/opinions/")
tsl_page

tsl_page |>
  html_elements(".entry-title a")

tsl_opinion <- tibble(
  title,
  author,
  date
)

tsl_opinion