library(rvest)
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(stringr)
library(tidyr)journal_links <- c()
WebpageURL <- paste("https://www.sciencedirect.com/browse/journals-and-books?contentType=JL&subject=business-management-and-accounting&searchPhrase=accounting")
print(WebpageURL)#I added in the print statement just so you can see the URL created## [1] "https://www.sciencedirect.com/browse/journals-and-books?contentType=JL&subject=business-management-and-accounting&searchPhrase=accounting"folder <- read_html(WebpageURL)
#for journal name
journal_names <- html_nodes(folder,'#publication-list .anchor-text')%>% html_text() %>%
print()## [1] "Accounting Forum"
## [2] "Accounting, Management and Information Technologies"
## [3] "Accounting, Organizations and Society"
## [4] "Advances in Accounting"
## [5] "Advances in International Accounting"
## [6] "The British Accounting Review"
## [7] "China Journal of Accounting Research"
## [8] "Critical Perspectives on Accounting"
## [9] "The International Journal of Accounting"
## [10] "International Journal of Accounting Information Systems"
## [11] "Journal of Accounting and Economics"
## [12] "Journal of Accounting Education"
## [13] "Journal of Accounting Literature"
## [14] "Journal of Accounting and Public Policy"
## [15] "Journal of Contemporary Accounting & Economics"
## [16] "Journal of International Accounting, Auditing and Taxation"
## [17] "Management Accounting Research"
## [18] "Research in Accounting Regulation"extend_links <- html_nodes(folder,'.js-publication a')%>% html_attr("href") %>%
print()## [1] "/journal/accounting-forum"
## [2] "/journal/accounting-management-and-information-technologies"
## [3] "/journal/accounting-organizations-and-society"
## [4] "/journal/advances-in-accounting"
## [5] "/journal/advances-in-international-accounting"
## [6] "/journal/the-british-accounting-review"
## [7] "/journal/china-journal-of-accounting-research"
## [8] "/journal/critical-perspectives-on-accounting"
## [9] "/journal/the-international-journal-of-accounting"
## [10] "/journal/international-journal-of-accounting-information-systems"
## [11] "/journal/journal-of-accounting-and-economics"
## [12] "/journal/journal-of-accounting-education"
## [13] "/journal/journal-of-accounting-literature"
## [14] "/journal/journal-of-accounting-and-public-policy"
## [15] "/journal/journal-of-contemporary-accounting-and-economics"
## [16] "/journal/journal-of-international-accounting-auditing-and-taxation"
## [17] "/journal/management-accounting-research"
## [18] "/journal/research-in-accounting-regulation"for (i in extend_links) {
Fullurl<-paste("https://www.sciencedirect.com/journal",i,"", sep = "")
print(Fullurl)
journal_links <- c(journal_links,Fullurl)
}## [1] "https://www.sciencedirect.com/journal/journal/accounting-forum"
## [1] "https://www.sciencedirect.com/journal/journal/accounting-management-and-information-technologies"
## [1] "https://www.sciencedirect.com/journal/journal/accounting-organizations-and-society"
## [1] "https://www.sciencedirect.com/journal/journal/advances-in-accounting"
## [1] "https://www.sciencedirect.com/journal/journal/advances-in-international-accounting"
## [1] "https://www.sciencedirect.com/journal/journal/the-british-accounting-review"
## [1] "https://www.sciencedirect.com/journal/journal/china-journal-of-accounting-research"
## [1] "https://www.sciencedirect.com/journal/journal/critical-perspectives-on-accounting"
## [1] "https://www.sciencedirect.com/journal/journal/the-international-journal-of-accounting"
## [1] "https://www.sciencedirect.com/journal/journal/international-journal-of-accounting-information-systems"
## [1] "https://www.sciencedirect.com/journal/journal/journal-of-accounting-and-economics"
## [1] "https://www.sciencedirect.com/journal/journal/journal-of-accounting-education"
## [1] "https://www.sciencedirect.com/journal/journal/journal-of-accounting-literature"
## [1] "https://www.sciencedirect.com/journal/journal/journal-of-accounting-and-public-policy"
## [1] "https://www.sciencedirect.com/journal/journal/journal-of-contemporary-accounting-and-economics"
## [1] "https://www.sciencedirect.com/journal/journal/journal-of-international-accounting-auditing-and-taxation"
## [1] "https://www.sciencedirect.com/journal/journal/management-accounting-research"
## [1] "https://www.sciencedirect.com/journal/journal/research-in-accounting-regulation"Elsvierjournal <- cbind(journal_names,journal_links) %>%
as_tibble()
Elsvierjournal$publisher <- "Elsvier"##Taylor & Francis publisher
#Taylor & Francis
WebpageURL <- paste("https://www.tandfonline.com/action/doSearch?field1=Title&text1=account&ConceptID=4259&startPage=&target=titleSearch&content=title")
print(WebpageURL)#I added in the print statement just so you can see the URL created## [1] "https://www.tandfonline.com/action/doSearch?field1=Title&text1=account&ConceptID=4259&startPage=&target=titleSearch&content=title"folder <- read_html(WebpageURL)
#for journal name
journal_names <- html_nodes(folder,'.ref')%>% html_text() %>%
print()## [1] "Asia-Pacific Journal of Accounting & Economics"
## [2] "Accounting History Review"
## [3] "Accounting and Business Research"
## [4] "Accounting Education"
## [5] "Accounting in Europe"
## [6] "China Journal of Accounting Studies"
## [7] "European Accounting Review"
## [8] "Spanish Journal of Finance and Accounting / Revista Española de Financiación y Contabilidad"
## [9] "South African Journal of Accounting Research"#for journal link
journal_links <- c()
extend_links <- html_nodes(folder,'.ref')%>% html_attr("href") %>%
print()## [1] "/toc/raae20/current" "/toc/rabf21/current" "/toc/rabr20/current"
## [4] "/toc/raed20/current" "/toc/raie20/current" "/toc/rcja20/current"
## [7] "/toc/rear20/current" "/toc/refc20/current" "/toc/rsar20/current"for (i in extend_links) {
Fullurl<-paste("https://www.tandfonline.com",i,"", sep = "")
print(Fullurl)
journal_links <- c(journal_links,Fullurl)
}## [1] "https://www.tandfonline.com/toc/raae20/current"
## [1] "https://www.tandfonline.com/toc/rabf21/current"
## [1] "https://www.tandfonline.com/toc/rabr20/current"
## [1] "https://www.tandfonline.com/toc/raed20/current"
## [1] "https://www.tandfonline.com/toc/raie20/current"
## [1] "https://www.tandfonline.com/toc/rcja20/current"
## [1] "https://www.tandfonline.com/toc/rear20/current"
## [1] "https://www.tandfonline.com/toc/refc20/current"
## [1] "https://www.tandfonline.com/toc/rsar20/current"print(journal_links)## [1] "https://www.tandfonline.com/toc/raae20/current"
## [2] "https://www.tandfonline.com/toc/rabf21/current"
## [3] "https://www.tandfonline.com/toc/rabr20/current"
## [4] "https://www.tandfonline.com/toc/raed20/current"
## [5] "https://www.tandfonline.com/toc/raie20/current"
## [6] "https://www.tandfonline.com/toc/rcja20/current"
## [7] "https://www.tandfonline.com/toc/rear20/current"
## [8] "https://www.tandfonline.com/toc/refc20/current"
## [9] "https://www.tandfonline.com/toc/rsar20/current"T_Fjournal <- cbind(journal_names,journal_links) %>%
as_tibble()
T_Fjournal$publisher <- "Taylor & Francis"##Emerald publisher
extend_links <- c()
journal_names <- c()
journal_links <- c()
page <- as.character(seq(0,1,1))
for (i in page) {
Sys.sleep(0.1) #Allowing the system to pause for two seconds.
WebpageURL <- paste("https://www.emeraldgrouppublishing.com/products/journals/find-a-journal?searchfor=account&tid=All&starts_with=&sort_by=title&field_open_access_value_1=0&page=",i,"", sep = "")
print(WebpageURL)#I added in the print statement just so you can see the URL created
for (t in WebpageURL) {
Sys.sleep(0.1)
folder <- read_html(t)
linkfolder<-html_nodes(folder,'.journal-grid__link a')%>% html_attr("href")
namefolder <- html_nodes(folder,'.journal-grid__title p') %>% html_text()
extend_links <- c(extend_links, linkfolder)
journal_names <- c(journal_names, namefolder)
print(extend_links)
}
}## [1] "https://www.emeraldgrouppublishing.com/products/journals/find-a-journal?searchfor=account&tid=All&starts_with=&sort_by=title&field_open_access_value_1=0&page=0"
## [1] "/journal/arj" "/journal/aaaj" "/journal/ajar" "/journal/ara"
## [5] "/journal/ijaim" "/journal/jaoc" "/journal/jaee" "/journal/jaar"
## [9] "/journal/jfra" "/journal/jiabr" "/journal/jpbafm" "/journal/medar"
## [1] "https://www.emeraldgrouppublishing.com/products/journals/find-a-journal?searchfor=account&tid=All&starts_with=&sort_by=title&field_open_access_value_1=0&page=1"
## [1] "/journal/arj" "/journal/aaaj" "/journal/ajar" "/journal/ara"
## [5] "/journal/ijaim" "/journal/jaoc" "/journal/jaee" "/journal/jaar"
## [9] "/journal/jfra" "/journal/jiabr" "/journal/jpbafm" "/journal/medar"
## [13] "/journal/par" "/journal/qram" "/journal/raf" "/journal/sampj"print(journal_names)## [1] "Accounting Research Journal"
## [2] "Accounting, Auditing & Accountability Journal"
## [3] "Asian Journal of Accounting Research"
## [4] "Asian Review of Accounting "
## [5] "International Journal of Accounting & Information Management"
## [6] "Journal of Accounting & Organizational Change"
## [7] "Journal of Accounting in Emerging Economies"
## [8] "Journal of Applied Accounting Research"
## [9] "Journal of Financial Reporting and Accounting"
## [10] "Journal of Islamic Accounting and Business Research"
## [11] "Journal of Public Budgeting, Accounting & Financial Management"
## [12] "Meditari Accountancy Research"
## [13] "Pacific Accounting Review"
## [14] "Qualitative Research in Accounting & Management"
## [15] "Review of Accounting and Finance"
## [16] "Sustainability Accounting, Management and Policy Journal"for (x in extend_links) {
Fullurl<-paste("https://www.emeraldgrouppublishing.com",x,"", sep = "")
print(Fullurl)
journal_links <- c(journal_links,Fullurl)
}## [1] "https://www.emeraldgrouppublishing.com/journal/arj"
## [1] "https://www.emeraldgrouppublishing.com/journal/aaaj"
## [1] "https://www.emeraldgrouppublishing.com/journal/ajar"
## [1] "https://www.emeraldgrouppublishing.com/journal/ara"
## [1] "https://www.emeraldgrouppublishing.com/journal/ijaim"
## [1] "https://www.emeraldgrouppublishing.com/journal/jaoc"
## [1] "https://www.emeraldgrouppublishing.com/journal/jaee"
## [1] "https://www.emeraldgrouppublishing.com/journal/jaar"
## [1] "https://www.emeraldgrouppublishing.com/journal/jfra"
## [1] "https://www.emeraldgrouppublishing.com/journal/jiabr"
## [1] "https://www.emeraldgrouppublishing.com/journal/jpbafm"
## [1] "https://www.emeraldgrouppublishing.com/journal/medar"
## [1] "https://www.emeraldgrouppublishing.com/journal/par"
## [1] "https://www.emeraldgrouppublishing.com/journal/qram"
## [1] "https://www.emeraldgrouppublishing.com/journal/raf"
## [1] "https://www.emeraldgrouppublishing.com/journal/sampj"Emeraldjournal <- cbind(journal_names,journal_links) %>%
as_tibble()
Emeraldjournal$publisher <- "Emerald"##Wiley publisher
#Wiley publisher
journal_links <- c()
WebpageURL <- paste("https://onlinelibrary.wiley.com/action/doSearch?Ppub=&content=journalTitle&field1=Title&field2=AllField&field3=AllField&target=titleSearch&text1=account&text2=&text3=&startPage=&PubType=journal")
print(WebpageURL)#I added in the print statement just so you can see the URL created## [1] "https://onlinelibrary.wiley.com/action/doSearch?Ppub=&content=journalTitle&field1=Title&field2=AllField&field3=AllField&target=titleSearch&text1=account&text2=&text3=&startPage=&PubType=journal"folder <- read_html(WebpageURL)
#for journal name
journal_names <- html_nodes(folder,'.visitable')%>% html_text() %>%
print()## [1] "Accounting & Finance"
## [2] "Accounting Perspectives"
## [3] "Australian Accounting Review"
## [4] "Accounting Perspectives"
## [5] "Contemporary Accounting Research"
## [6] "Intelligent Systems in Accounting, Finance and Management"
## [7] "Intelligent Systems in Accounting, Finance and Management"
## [8] "Journal of Accounting Research"
## [9] "Journal of Business Finance & Accounting"
## [10] "Journal of Corporate Accounting & Finance"
## [11] "Journal of International Financial Management & Accounting"extend_links <- html_nodes(folder,'.visitable')%>% html_attr("href") %>%
print()## [1] "/journal/1467629x" "/journal/19113838" "/journal/18352561"
## [4] "/journal/19113838" "/journal/19113846" "/journal/21600074"
## [7] "/journal/21600074" "/journal/1475679x" "/journal/14685957"
## [10] "/journal/10970053" "/journal/1467646x"for (i in extend_links) {
Fullurl<-paste("https://onlinelibrary.wiley.com",i,"", sep = "")
print(Fullurl)
journal_links <- c(journal_links,Fullurl)
}## [1] "https://onlinelibrary.wiley.com/journal/1467629x"
## [1] "https://onlinelibrary.wiley.com/journal/19113838"
## [1] "https://onlinelibrary.wiley.com/journal/18352561"
## [1] "https://onlinelibrary.wiley.com/journal/19113838"
## [1] "https://onlinelibrary.wiley.com/journal/19113846"
## [1] "https://onlinelibrary.wiley.com/journal/21600074"
## [1] "https://onlinelibrary.wiley.com/journal/21600074"
## [1] "https://onlinelibrary.wiley.com/journal/1475679x"
## [1] "https://onlinelibrary.wiley.com/journal/14685957"
## [1] "https://onlinelibrary.wiley.com/journal/10970053"
## [1] "https://onlinelibrary.wiley.com/journal/1467646x"print(journal_links)## [1] "https://onlinelibrary.wiley.com/journal/1467629x"
## [2] "https://onlinelibrary.wiley.com/journal/19113838"
## [3] "https://onlinelibrary.wiley.com/journal/18352561"
## [4] "https://onlinelibrary.wiley.com/journal/19113838"
## [5] "https://onlinelibrary.wiley.com/journal/19113846"
## [6] "https://onlinelibrary.wiley.com/journal/21600074"
## [7] "https://onlinelibrary.wiley.com/journal/21600074"
## [8] "https://onlinelibrary.wiley.com/journal/1475679x"
## [9] "https://onlinelibrary.wiley.com/journal/14685957"
## [10] "https://onlinelibrary.wiley.com/journal/10970053"
## [11] "https://onlinelibrary.wiley.com/journal/1467646x"Wileyjournal <- cbind(journal_names,journal_links) %>%
as_tibble()
Wileyjournal$publisher <- "Wiley"journalinfo <- rbind(Elsvierjournal,T_Fjournal,Emeraldjournal,Wileyjournal) %>%
print()## # A tibble: 54 x 3
## journal_names journal_links publisher
## <chr> <chr> <chr>
## 1 Accounting Forum https://www.sciencedirect.com/journa… Elsvier
## 2 Accounting, Management and I… https://www.sciencedirect.com/journa… Elsvier
## 3 Accounting, Organizations an… https://www.sciencedirect.com/journa… Elsvier
## 4 Advances in Accounting https://www.sciencedirect.com/journa… Elsvier
## 5 Advances in International Ac… https://www.sciencedirect.com/journa… Elsvier
## 6 The British Accounting Review https://www.sciencedirect.com/journa… Elsvier
## 7 China Journal of Accounting … https://www.sciencedirect.com/journa… Elsvier
## 8 Critical Perspectives on Acc… https://www.sciencedirect.com/journa… Elsvier
## 9 The International Journal of… https://www.sciencedirect.com/journa… Elsvier
## 10 International Journal of Acc… https://www.sciencedirect.com/journa… Elsvier
## # … with 44 more rowsNote that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.