extraction.R

library("tidyverse", lib.loc="L:/RLIB")

##############################
# 1. Read in the data
##############################

Rladies<- readLines("https://raw.githubusercontent.com/jumpingrivers/meetingsR/master/03-Rladies.Rmd")
Asia <-readLines("https://raw.githubusercontent.com/jumpingrivers/meetingsR/master/02_useR_groups_asia.Rmd")
Europe <-readLines("https://raw.githubusercontent.com/jumpingrivers/meetingsR/master/02_useR_groups_europe.Rmd")
MiddleEast <-readLines("https://raw.githubusercontent.com/jumpingrivers/meetingsR/master/02_useR_groups_middle_east_africa.Rmd")
NAmerica <- readLines("https://raw.githubusercontent.com/jumpingrivers/meetingsR/master/02_useR_groups_north_america.Rmd")
Oceania <- readLines("https://raw.githubusercontent.com/jumpingrivers/meetingsR/master/02_useR_groups_oceania.Rmd")
SAmerica <-readLines("https://raw.githubusercontent.com/jumpingrivers/meetingsR/master/02_useR_groups_south_america.Rmd")

############################3
# 2. Function to extract data
#############################
make_table <- function(mydata, group_type){
  countries = vector()
  city1 = vector()
  city=vector()
  link = vector()
  type=vector()
  marker = 0
  country = vector()
  for (i in 1:length(mydata)){
    if (grepl('##', mydata[i])==TRUE){
      each_country <- gsub('##','',mydata[i])
      each_country <- gsub(' ', '', each_country)
      countries= c(countries, each_country)
      marker = marker + 1
    }
    if (grepl('[*]', mydata[i])==TRUE){
      each_city <- gsub('[*]','',mydata[i])
      just_city <- unlist(strsplit(each_city, ":"))[1]
      just_city <- gsub(' ', '', just_city)
      just_link <-unlist(strsplit(each_city, "[(]"))[2]
      just_link <- gsub ('[)]', '', just_link)
      just_link <- gsub(';.*', '', just_link)
      just_link <- gsub('[[].*', '', just_link)
      city1 <- c(city1, each_city )
      city <-c(city, just_city)
      link <- c(link, just_link)
      country <- c(country, countries[marker])
    }
  }
  
  RGroup_type <- rep(group_type, length(city)) 
  final <- data.frame(city, link, country, RGroup_type, stringsAsFactors = FALSE)
  final2 <- as.tibble(final)
  return (final2)
}


#############################
# 3. Run Function on all data
#############################
Rladies_table=make_table(Rladies, "RLadies")
Asia_table=make_table(Asia, "Rgroup")
Europe_table=make_table(Europe, "Rgroup")
MiddleEast_table=make_table(MiddleEast, "Rgroup")
NAmerica_table=make_table(NAmerica, "Rgroup")
Oceania_table=make_table(Oceania, "Rgroup")
SAmerica_table=make_table(SAmerica, "Rgroup")


###############################
# 4. Create Table of all Groups
###############################
RGroups <- full_join(Rladies_table, Asia_table) %>%
  full_join(Europe_table) %>%
  full_join(MiddleEast_table) %>%
  full_join(NAmerica_table) %>%
  full_join(Oceania_table) %>%
  full_join(SAmerica_table)  

###################
# 5. Save as a CSV
###################
write.csv(RGroups, "RGroups.csv")