In f0nzie/petro.One: Statistics and Text Mining for Oil and Gas Papers from OnePetro Metadata

We start by providing the keywords or words that are key for finding what we are searching.

library(petro.One)
url_any <- make_search_url(query = "Cantarell", how = "any")
get_papers_count(url_any)

Papers that differ in how "cantarell" is spelled:

url_any <- make_search_url(query = "Cantarel", how = "any")
get_papers_count(url_any)

Only one paper with Cantarell and Optimization

library(petro.One)
url_any <- make_search_url(query = "Cantarell optimization", how = "all")
get_papers_count(url_any)

UK english spelling of "optimization":

library(petro.One)
url_any <- make_search_url(query = "Cantarell optimisation", how = "all")
get_papers_count(url_any)

Any keywords "network"

library(petro.One)
url_any <- make_search_url(query = "Cantarell network", how = "all")
get_papers_count(url_any)

Provide keywords

In this example we provide a list of keywords as a text list - later converted to a dataframe-, that is used by petro.One to iterate through that list of keywords.

library(petro.One)

# provide the list of keywords
keywords <- "    
    Cantarell
    Cantarell optimization
    Cantarell optimisation
    Cantarell modeling
    Cantarell modelling
    Cantarell network
    Cantarell increase
    Cantarell production
    Cantarell IPM
    Cantarell integrated
    Cantarell gain
    Cantarell pipesim
"
# convert the text to a dataframe
#
# keywords
# read.table(text = keywords, header = FALSE, allowEscapes = FALSE)
# read text table and split rows at carriage return
kw_tbl <- read.table(text = keywords, header = FALSE, 
                              sep = "\n", stringsAsFactors = FALSE, 
                     strip.white = TRUE)
kw_tbl

major <- "cantarell"
mid <- c("optimization", "optimisation", "modeling", "modelling", "network",
         "increase", "production", "IPM", "integrated")

cantarell <- join_keywords(major, mid, 
                                   get_papers = TRUE, sleep = 3, verbose = TRUE)

library(rNodal.utils)
save_to_project(cantarell, name = "cantarell_L2")

cantarell$keywords

sum(cantarell$keywords$paper_count)

cantarell$papers

older code

rec <- vector("list")
i <- 1
for (k in kw_tbl$V1) {
    url_all <- make_search_url(query = k, how = "all")
    count <- get_papers_count(url_all)
    rec[[i]] <- list(keyword = k, count = count)
    cat(sprintf("%30s %5d \n", k, count))
    i <-  i + 1
    Sys.sleep(5)
}
data.table::rbindlist(rec)

library(petro.One)
url <- make_search_url(query = "Cantarell production", how = "all")
df1 <- onepetro_page_to_dataframe(url)
df1

library(petro.One)
url <- make_search_url(query = "Cantarell optimization", how = "all")
df2 <- onepetro_page_to_dataframe(url)
df2

Another way to do it: by getting the list of all papers

library(petro.One)
url <- make_search_url(query = "Cantarell", how = "all", rows = 1000)
df <- onepetro_page_to_dataframe(url)
df

f0nzie/petro.One documentation built on May 29, 2019, 12:05 a.m.