Created
October 27, 2016 07:47
-
-
Save seojcarlos/771b63c15b04a0cd9166ded1e8f775cb to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library("igraph") | |
# Intercambiar ruta a su Screaming Frog Todos_Outlink CSV. Para Windows, recuerde cambiar las barras invertidas de barras diagonales. | |
links <- read.csv("C:/Documents/screaming-frog-all-outlinks.csv", skip = 1) # CSV Path | |
# Esta línea de código es opcional. Se filtra el JavaScript, CSS e imágenes. Técnicamente debe mantenerlos allí. | |
links <- subset(links, Type=="HREF") # Optional line. Filter. | |
links <- subset(links, Follow=="true") | |
links <- subset(links, select=c(Source,Destination)) | |
g <- graph.data.frame(links) | |
pr <- page.rank(g, algo = "prpack", vids = V(g), directed = TRUE, damping = 0.85) | |
values <- data.frame(pr$vector) | |
values$names <- rownames(values) | |
row.names(values) <- NULL | |
values <- values[c(2,1)] | |
names(values)[1] <- "url" | |
names(values)[2] <- "pr" | |
# Intercambiar el nombre "dominio" por el tuyo y la extensión "com" por el tuyo dejar los signos ?. | |
values <- values[grepl("https?:\\/\\/(.*\\.)?domain\\.com.*", values$url),] # Domain filter. | |
# Reemplazar con el nombre del archivo deseado para el archivo de salida y su ubicación. | |
write.csv(values, file = "output-pagerank.csv") # Output file. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment