In mariafcadena/FinalProject_CADENA: Web scraping real state information from Seloger.com

Get Pages This functions reads the web page given and returns the amount of pages of all the anounces in the link

library(ScrapingSelonger)
library(rvest)
link<-"http://www.seloger.com/list.htm?idtt=2&naturebien=1,2,4&idtypebien=1,2&ci=750056&tri=initial&surfacemin=5&surfacemax=20"
Web_page<-read_html(link)
No_Pages<-GetPages(Web_page)
print(No_Pages)

Creates DataFrame Takes the input link and downloads all the announces into a DataFrame

library(ScrapingSelonger)
link<-"http://www.seloger.com/list.htm?idtt=2&naturebien=1,2,4&idtypebien=1,2&ci=750056&tri=initial&surfacemin=5&surfacemax=20"
Data<-CreatesDataframe(link)

Fix Parameters Adjusts the scrapped data. Posibles inputs of Type (Cartier, Property, Area, Piece, Chambre)

library(ScrapingSelonger)
link<-"http://www.seloger.com/list.htm?idtt=2&naturebien=1,2,4&idtypebien=1,2&ci=750056&tri=initial&surfacemin=5&surfacemax=20"
WEB_PAGE <- read_html(link)
PRE_CARTIER  <- WEB_PAGE %>% html_nodes(".c-pa-city") %>% html_text()
CARTIER <-FixParameters(PRE_CARTIER[1],"Cartier")
print(CARTIER)

Clean Vector Adjusts the complete arry with FixParameters. Posibles inputs of Type (Cartier, Property, Area, Piece, Chambre, Price)

library(ScrapingSelonger)
link<-"http://www.seloger.com/list.htm?idtt=2&naturebien=1,2,4&idtypebien=1,2&ci=750056&tri=initial&surfacemin=5&surfacemax=20"
WEB_PAGE <- read_html(link)
PRE_CARTIER  <- WEB_PAGE %>% html_nodes(".c-pa-city") %>% html_text()
CARTIER <-CleanVector(PRE_CARTIER,"Cartier")
print(CARTIER)

Groups Area Set the areas in discrete groups

library(ScrapingSelonger)
link<-"http://www.seloger.com/list.htm?idtt=2&naturebien=1,2,4&idtypebien=1,2&ci=750056&tri=initial&surfacemin=5&surfacemax=20"
WEB_PAGE <- read_html(link)
PRE_CARACT   <- WEB_PAGE %>% html_nodes(".c-pa-criterion") %>% html_text()
AREA      <- CleanVector(PRE_PRICE, "Area")
AREA_GROUP<- lapply(PRICE,GroupsArea)
print(AREA_GROUP)

Groups Prices Set the prices in discrete groups

library(ScrapingSelonger)
link<-"http://www.seloger.com/list.htm?idtt=2&naturebien=1,2,4&idtypebien=1,2&ci=750056&tri=initial&surfacemin=5&surfacemax=20"
WEB_PAGE <- read_html(link)
PRE_CARACT   <- WEB_PAGE %>% html_nodes(".c-pa-criterion") %>% html_text()
PRICE      <- CleanVector(PRE_PRICE, "Price")
PRICE_GROUP<- lapply(PRICE,GroupsPrice)
print(PRICE_GROUP)

Download All Info of Paris Using the functions on the package is posible to download all the information of one city in Selonger.com

library(ScrapingSelonger)
m = matrix(c(5,10,20,30,40,50,60,70,80,100,150,200,9,19,29,39,49,59,69,79,99,149,199,400), nrow=12, ncol=2)
links =NULL
for (i in 1:12)
{
  p1 <-"http://www.seloger.com/list.htm?idtt=2&naturebien=1,2,4&idtypebien=1,2&ci=750056&tri=initial&"
  p2 <- paste("surfacemin=",as.character(m[i,1]), sep="")
  p3 <- paste("&surfacemax=",as.character(m[i,2]), sep="")
  link=paste(paste(p1,p2, sep=""),p3, sep="")
  links=append(links, link)
}

#Loop through Areas
for (i in range(links))
{
  ScrapedData <-CreatesDataframe(links[i])
  if (i==1){
    ParisData<-ScrapedData
  } else {ParisData<-rbind(ParisData, ScrapedData)}
}

sometimes selonger.com identifies the web scrapin and blocks the user. That has been a problem when finishing the loop defined in the previous chunk.

mariafcadena/FinalProject_CADENA documentation built on May 29, 2019, 3:44 a.m.