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

library(petro.One)

my_url <- make_search_url(query = "IPR viscosity", how = "all")
page.01 <- xml2::read_html(my_url)

my_url <- make_search_url(query = "IPR neural", how = "all")
page.02 <- xml2::read_html(my_url)

# page.01
# page.02

page.li <- list(page.01 = page.01, page.02 = page.02)
page.li

test_save_loc  <- paste(PROJHOME, "inst/testdata", sep = "/")
test_save_file <- paste(test_save_loc, "pbt.rda", sep = "/")
save(page.li, file = test_save_file)

roundtrip <- function(obj) {
  tf <- tempfile()
  con <- file(tf, "wb")
  on.exit(unlink(tf))

  xml_serialize(obj, con)
  close(con)
  con <- file(tf, "rb")
  on.exit(close(con), add = TRUE)
  xml_unserialize(con)
}

page.1

roundtrip(page.1, )

library(petro.One)

my_url <- make_search_url(query = "mechanistic performance",
                          how = "all")

    #load(file = paste(test_loc, "pagexml.rda", sep = "/"))
    #print(page.1)
    page.1 <- xml2::read_html(my_url)
    expect_false(petro.One:::is_dctype_enabled(page.1))

xml2::write_html(page.1, file = "page_1.html")

webpage <- xml2::read_html("page_1.html")

expect_false(petro.One:::is_dctype_enabled(webpage))
expect_true(petro.One:::is_dctype_enabled(webpage))

Persisting HTML documents to disk

https://stackoverflow.com/a/36024318/5270873

library(xml2)
library(httr)

str_url <- "https://www.holidayhouses.co.nz/Browse/List.aspx?page=1"
str_url.1 <- make_search_url(query = "IPR viscosity", how = "all")
str_url.2 <- make_search_url(query = "IPR neural", how = "all")

# use `GET` to make the request, and pull out the html with `content`; returns text string
x.1 <- content(GET(str_url.1), as = 'text')
x.2 <- content(GET(str_url.2), as = 'text')

# make a list of html documents to save
list_xs <- list(x.1. = x.1, x.2 = x.2)

# save list with `saveRDS`
saveRDS(list_xs, 'test.rds')
save(list_xs, file = 'test.rda')

rm(list_xs, x.1, x.2)

# read in rds file we saved
saved_html <- readRDS('test.rds')
load(file = 'test.rda')

# parse the second element in it with `xml2::read_html`
saved_x_parsed.1 <- read_html(saved_html[[1]])
saved_x_parsed.2 <- read_html(saved_html[[2]])

identical(saved_x_parsed.1, saved_x_parsed.1) # must be true
identical(saved_x_parsed.2, saved_x_parsed.2) # must be true
identical(saved_x_parsed.1, saved_x_parsed.2) # must be false
all.equal(saved_x_parsed.1, saved_x_parsed.2) # must be false

cat("2nd comparison \n")
identical(saved_x_parsed.2, read_html(list_xs$x.2)) # must be true
identical(saved_x_parsed.1, read_html(list_xs$x.1)) # must be true
all.equal(saved_x_parsed.2, read_html(list_xs$x.2)) # must be true
all.equal(saved_x_parsed.1, read_html(list_xs$x.1)) # must be true
all.equal(saved_x_parsed.1, read_html(list_xs$x.2)) # must be false

# and let's see...
saved_x_parsed.2

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