如何在R中从网站上抓取的书名中查找词频

library(rvest)
library(stringr)
library(tm)
library(wordcloud)

# 抓取网页内容
url <- "https://example.com"  # 替换为实际的网址
page <- read_html(url)

# 提取书名数据
book_titles <- page %>% html_nodes(".book-title") %>% html_text()

# 分词处理
book_titles <- str_split(book_titles, "\\s+")

# 创建文本语料库
corpus <- Corpus(VectorSource(book_titles))

# 进行词频统计
tdm <- TermDocumentMatrix(corpus)
freq_terms <- findFreqTerms(tdm, lowfreq = 10)  # 设置词频阈值

# 创建词云图
wordcloud(names(freq_terms), freq_terms)

# 创建词频柱状图
freq_df <- data.frame(term = names(freq_terms), freq = freq_terms)
ggplot(freq_df, aes(x = term, y = freq)) + geom_bar(stat = "identity")