Type:	Package
Title:	Google Citation Parser
Version:	0.11.0
Description:	Scrapes Google Citation pages and creates data frames of citations over time.
License:	GPL-3
Imports:	xml2, httr, rvest, stats, pbapply, data.table, wordcloud, tm, graphics
RoxygenNote:	7.3.2
Encoding:	UTF-8
Suggests:	covr, testthat, spelling
Language:	en-US
NeedsCompilation:	no
Packaged:	2025-04-01 15:28:03 UTC; johnmuschelli
Author:	John Muschelli [aut, cre]
Maintainer:	John Muschelli <muschellij2@gmail.com>
Repository:	CRAN
Date/Publication:	2025-04-01 15:50:09 UTC

Make Wordcloud of authors from Papers

Description

Takes a vector of authors and then creates a frequency table of those words and plots a wordcloud

Usage

author_cloud(
  authors,
  addstopwords = gcite_stopwords(),
  author_pattern = NULL,
  split = ",",
  verbose = TRUE,
  colors = c("#66C2A4", "#41AE76", "#238B45", "#006D2C", "#00441B"),
  ...
)

author_frequency(
  authors,
  author_pattern = NULL,
  split = ",",
  addstopwords = gcite_stopwords(),
  verbose = TRUE
)

Arguments

Value

A data.frame of the words and the frequencies of the authors

Examples

## Not run: 
L = gcite_author_info("John Muschelli")
paper_df = L$paper_df
authors = paper_df$authors
author_cloud(authors)

## End(Not run)

Google Citations Information

Description

Wraps getting the information from Google Citations and plotting the wordcloud

Usage

gcite(
  author,
  user,
  plot_wordcloud = TRUE,
  author_args = list(),
  title_args = list(),
  warn = FALSE,
  force = FALSE,
  sleeptime = 0,
  ...
)

Arguments

Value

List from either gcite_user_info or gcite_author_info

Examples

if (!is_travis() & !is_cran()) {
res = gcite(author = "John Muschelli")
paper_df = res$paper_df
gcite_wordcloud(paper_df)
author_cloud(paper_df$authors)
}

Getting User Information from name

Description

Calls gcite_user_info after getting the user identifier

Usage

gcite_author_info(
  author,
  ask = TRUE,
  pagesize = 100,
  verbose = TRUE,
  secure = TRUE,
  force = FALSE,
  read_citations = TRUE,
  sleeptime = 0,
  ...
)

Arguments

Value

A list of citations, citation indices, and a data.frame of authors, journal, and citations, and a data.frame of the links to all paper URLs.

Examples

## Not run: 
if (!is_travis()) {
  df = gcite_author_info(author = "John Muschelli", secure = FALSE)
}

## End(Not run)
if (!is_travis() & !is_cran()) {
  df = gcite_author_info(author = "Jiawei Bai", secure = FALSE)
}

Parse Google Citation Index

Description

Parses a google citation indices (h-index, etc.) from main page

Usage

gcite_citation_index(doc, ...)

## S3 method for class 'xml_node'
gcite_citation_index(doc, ...)

## S3 method for class 'xml_document'
gcite_citation_index(doc, ...)

## S3 method for class 'character'
gcite_citation_index(doc, ...)

Arguments

Value

A matrix of indices

Examples

library(httr)
library(rvest) 
library(gcite)
url = "https://scholar.google.com/citations?user=T9eqZgMAAAAJ"
url = gcite_url(url = url, pagesize = 10, cstart = 0) 
if (!is_travis() & !is_cran()) {
ind = gcite_citation_index(url)
doc = content(httr::GET(url))
ind = gcite_citation_index(doc)
ind_nodes = rvest::html_nodes(doc, "#gsc_rsb_st")[[1]]
ind = gcite_citation_index(ind_nodes)
}

Parse Google Citation Index

Description

Parses a google citation indices (h-index, etc.) from main page

Usage

gcite_citation_page(doc, title = NULL, force = FALSE, ...)

## S3 method for class 'xml_nodeset'
gcite_citation_page(doc, title = NULL, force = FALSE, ...)

## S3 method for class 'xml_document'
gcite_citation_page(doc, title = NULL, force = FALSE, ...)

## S3 method for class 'character'
gcite_citation_page(doc, title = NULL, force = FALSE, ...)

## S3 method for class 'list'
gcite_citation_page(doc, title = NULL, force = FALSE, ...)

## Default S3 method:
gcite_citation_page(doc, title = NULL, force = FALSE, ...)

Arguments

Value

A matrix of indices

Examples

library(httr)
library(rvest)
url = paste0("https://scholar.google.com/citations?view_op=view_citation&", 
"hl=en&oe=ASCII&user=T9eqZgMAAAAJ&pagesize=100&", 
"citation_for_view=T9eqZgMAAAAJ:W7OEmFMy1HYC")
url = gcite_url(url = url, pagesize = 10, cstart = 0) 
if (!is_travis() & !is_cran()) {
ind = gcite_citation_page(url)
doc = content(httr::GET(url))
ind = gcite_citation_page(doc)
ind_nodes = html_nodes(doc, "#gsc_oci_table div")
ind_nodes = html_nodes(ind_nodes, xpath = '//div[@class = "gs_scl"]')  
ind = gcite_citation_page(ind_nodes)
}

Parse Google Citations Over Time

Description

Parses a google citations over time from the main Citation page

Usage

gcite_cite_over_time(doc, ...)

## S3 method for class 'xml_node'
gcite_cite_over_time(doc, ...)

## S3 method for class 'xml_document'
gcite_cite_over_time(doc, ...)

## S3 method for class 'character'
gcite_cite_over_time(doc, ...)

## Default S3 method:
gcite_cite_over_time(doc, ...)

Arguments

Value

A matrix of citations

Examples

library(httr)
library(rvest) 
url = "https://scholar.google.com/citations?user=T9eqZgMAAAAJ"
url = gcite_url(url = url, pagesize = 10, cstart = 0) 
if (!is_travis() & !is_cran()) {
#' ind = gcite_cite_over_time(url)
doc = content(httr::GET(url))
ind = gcite_cite_over_time(doc)
ind_nodes = rvest::html_nodes(doc, ".gsc_md_hist_b")
ind = gcite_cite_over_time(ind_nodes)
}

Parse Google Citation Graph

Description

Parses a google citation bar graph from html

Usage

gcite_graph(citations, ...)

## S3 method for class 'xml_node'
gcite_graph(citations, ...)

## S3 method for class 'xml_document'
gcite_graph(citations, ...)

## S3 method for class 'character'
gcite_graph(citations, ...)

## Default S3 method:
gcite_graph(citations, ...)

Arguments

Value

A matrix of citations and years

Parse Google Citation Graph

Description

Parses a google citation bar graph from html

Usage

gcite_main_graph(citations, ...)

## S3 method for class 'xml_document'
gcite_main_graph(citations, ...)

## S3 method for class 'character'
gcite_main_graph(citations, ...)

## Default S3 method:
gcite_main_graph(citations, ...)

Arguments

Value

A matrix of citations and years

Get Paper Data Frame from Title URLs

Description

Get Paper Data Frame from Title URLs

Usage

gcite_paper_df(urls, verbose = TRUE, force = FALSE, sleeptime = 0, ...)

Arguments

Value

A data.frame of authors, journal, and citations

Examples

if (!is_travis() & !is_cran()) {
L = gcite_user_info(user = "uERvKpYAAAAJ", 
read_citations = FALSE)
urls = L$all_papers$title_link
paper_df = gcite_paper_df(urls = urls, force = TRUE)
} 

Parse Google Citation Index

Description

Parses a google citation indices (h-index, etc.) from main page

Usage

gcite_papers(doc, ...)

## S3 method for class 'xml_nodeset'
gcite_papers(doc, ...)

## S3 method for class 'xml_document'
gcite_papers(doc, ...)

## S3 method for class 'character'
gcite_papers(doc, ...)

## Default S3 method:
gcite_papers(doc, ...)

Arguments

Value

A matrix of indices

Examples

library(httr)
library(rvest) 
url = "https://scholar.google.com/citations?user=T9eqZgMAAAAJ"
url = gcite_url(url = url, pagesize = 10, cstart = 0) 
if (!is_travis() & !is_cran()) {
ind = gcite_papers(url)
doc = content(httr::GET(url))
ind = gcite_papers(doc)
ind_nodes = rvest::html_nodes(doc, "#gsc_a_b")
ind = gcite_papers(ind_nodes)
}

Google Cite Stopwords

Description

Additional stopwords to remove from Google Cite results

Usage

gcite_stopwords()

Value

Character Vector

Examples

gcite_stopwords()

Google Citations URL

Description

Simple wrapper for adding in pagesize and start values for the page

Usage

gcite_url(url, cstart = 0, pagesize = 100)

gcite_base_url(secure = TRUE)

gcite_user_url(user, secure = TRUE)

Arguments

Value

A character string

Examples

url = "https://scholar.google.com/citations?user=T9eqZgMAAAAJ"
gcite_url(url = url, pagesize = 100, cstart = 5)

Getting User Information of papers

Description

Loops through pages for all information on Google Citations

Usage

gcite_user_info(
  user,
  pagesize = 100,
  verbose = TRUE,
  secure = TRUE,
  force = FALSE,
  read_citations = TRUE,
  sleeptime = 0,
  ...
)

Arguments

Value

A list of citations, citation indices, and a data.frame of authors, journal, and citations, and a data.frame of the links to all paper URLs and the character string of the user name.

Examples

## Not run: 
if (!is_travis() & !is_cran()) {
df = gcite_user_info(user = "uERvKpYAAAAJ")
}

## End(Not run)

Google Citation Username Searcher

Description

Search Google Citation for an author username

Usage

gcite_username(author, verbose = TRUE, ask = TRUE, secure = TRUE, ...)

Arguments

Value

A character vector of the username of the author

Examples

if (!is_travis() & !is_cran()) {
gcite_username("John Muschelli")
}

Wordcloud of Google Citations Information

Description

Simple wrapper for author_cloud and title_cloud

Usage

gcite_wordcloud(
  paper_df,
  author_args = list(),
  title_args = list(),
  warn = FALSE
)

Arguments

gcite Wordcloud default

Description

Simple wrapper for wordcloud with different defaults

Usage

gcite_wordcloud_spec(
  words,
  freq,
  min.freq = 1,
  max.words = Inf,
  random.order = FALSE,
  colors = c("#F768A1", "#DD3497", "#AE017E", "#7A0177", "#49006A"),
  vfont = c("sans serif", "plain"),
  ...
)

Arguments

Value

Nothing

Check if on Travis CI

Description

Simple check for Travis CI for examples

Usage

is_travis()

is_cran()

Value

Logical if user is named travis

Examples

is_travis()
is_cran()

Set Cookies from Text file

Description

Set Cookies from Text file

Usage

set_cookies_txt(file)

Arguments

Value

Either NULL if no domains contain the word "scholar", or an object of class request from set_cookies

Note

This function searches for domains that contain the word "scholar"

Make Wordcloud of Titles from Papers

Description

Takes a vector of titles and then creates a frequency table of those words and plots a wordcloud

Usage

title_cloud(titles, addstopwords = gcite_stopwords(), ...)

paper_cloud(...)

title_word_frequency(titles, addstopwords = NULL)

Arguments

Value

A data.frame of the words and the frequencies of the title words

Examples

## Not run: 
L = gcite_author_info("John Muschelli")
paper_df = L$paper_df
titles = paper_df$title
title_cloud(titles)

## End(Not run)