====== NBER US patents ====== http://patft.uspto.gov/netahtml/PTO/srchnum.htm ===== Obtaining titles of selected patents =====


# PatNames - branje naslovov patentov z US Patent Office
# http://patft.uspto.gov/netahtml/PTO/srchnum.htm
#   Nataša Kejžar, 9. april 2004
#   'zlikal' V.B., 27. november 2004
# -------------------------------------------------------------
# na datoteki numbers.txt pripravimo seznam številk patentov,
# v obliki s priložene datoteke. Program PatNames bo na datoteko 
# titles.txt izpisal ustrezne naslove.
# !!! pred uporabo je potrebno naložiti paket  XML
# -------------------------------------------------------------

doloci.opis <- function(num){
  if(regexpr("island",num)>0){ opis <- paste('---',num)
  } else {
  # najprej sestavimo spletni naslov
    num.c <- as.character(num)
    url.s <- paste("http://patft.uspto.gov/netacgi/nph-Parser?",
      "Sect1=PTO1&Sect2=HITOFF&d=PALL&p=1&",
      "u=/netahtml/PTO/srchnum.htm&r=1&f=G&l=50&s1=",num.c,
      ".PN.&OS=PN/",num.c,"&RS=PN/",num.c,sep="")

  # poberemo tekočo stran s spleta in jo razčlenimo
  # preprečimo sporočila 'There were 50 or more warnings  ...'
    op <- options(); options(warn=-1)
    hp <- htmlTreeParse(url.s); options(op)
    html.s <- unlist(hp$children$html$children)

    if(any(regexpr('\"Images\"',html.s)>0)){
      opis <- paste(num.c,'*** Full text is not available,',
        'see image version')
    } else {
    # poiščemo točno določeno vrstico 4 elemente za 2. značko 
      i <- which(regexpr("hr",html.s)>0)[2]
      naslov <- html.s[i+4]
    # poiščemo še datum, predhodnik 2. značke 
      datum <- html.s[i-1]
      names(naslov) <- NULL; names(datum) <- NULL
      opis <- paste(num.c,datum,naslov)
    }
  }
  opis
}

  setwd("C:/Users/batagelj/Documents/manuscripts/Cite/R")
  library(XML)
# preberemo številke iz znakovne datoteke v num
  num <- readLines("./numbers.txt")

# določimo in izpišemo ustrezni seznam naslovov
  writeLines(unlist(sapply(num,doloci.opis)),"./titles.txt")


--- island 3
5010649 ** Cutterhead for a vegetation cutter apparatus
4926557 ** Semi-automatic string trimmer head
4426780 January 24, 1984 Line metering apparatus
4347666 September 7, 1982 Apparatus for cutting vegetation
4245454 January 20, 1981 Line metering apparatus
4254550 March 10, 1981 Lawn trimmer
4151646 May 1, 1979 Flexible line trimmer with line feeding apparatus
4095338 June 20, 1978 Lawn trimmer equipped with flexible line cutting edges
4134204 January 16, 1979 Rotary flail cutter system
4104796 August 8, 1978 Filament-type trimmer
4047299 September 13, 1977 Apparatus for trimming vegetation
4007525 February 15, 1977 Spool for a vegetation cutting apparatus having a flexible line cutting
     element
3892037 July 1, 1975 Grass cutting, trimming and edging device
3928911 ** Hollow-shaft feed filament trimmer
3664102 May 23, 1972 CUTTER MECHANISM FOR AGRICULTURAL MACHINES OR LAWN MOWERS
3693255 September 26, 1972 LAWN EDGE TRIMMER
3826068 ** ROTARY CUTTING ASSEMBLY
--- island 1
4604106 August 5, 1986 Composite polycrystalline diamond compact
4215999 August 5, 1980 Abrasive compact with a core of high rigidity material
4229186 October 21, 1980 Abrasive bodies
4252102 February 24, 1981 Cutting element for processing rocks, metal or the like
--- island 2
3512876 *** Full text is not available, see image version
3697150 October 10, 1972 ELECTRO-OPTIC SYSTEMS IN WHICH AN ELECTROPHORETIC-LIKE OR DIPOLAR
     MATERIAL IS DISPERSED THROUGHOUT A LIQUID CRYSTAL TO REDUCE THE
     TURN-OFF TIME
4514044 April 30, 1985 1-(Trans-4-alkylcyclohexyl)-2-(trans-4'-(p-substituted phenyl)
     cyclohexyl)ethane and liquid crystal mixture
5243451 ** DAP type liquid crystal device with cholesteric liquid crystal
     birefringent layer

===== Word clouds ===== To produce the word cloud go to the Jason Davies' [[http://www.jasondavies.com/wordcloud/#|Word Cloud Generator]] and copy the text into the entry field area. The obtained word cloud save in SVG format (an option provided by the generator). Use InkScape to transform it into PDF format. Here is the word cloud for the main islands (Liquid crystal display) for US patents -1999. {{notes:pics:lcd.svg}} ===== Titles / version 2017 ===== PatNames.R


# PatNames - branje naslovov patentov z US Patent Office
# http://patft.uspto.gov/netahtml/PTO/srchnum.htm
#   Nataša Kejžar, 9. april 2004
#   'zlikal' V.B., 27. november 2004
#   'posodobil' V.B., 21. marec 2017
# -------------------------------------------------------------
# na datoteki numbers.txt pripravimo seznam številk patentov,
# v obliki s priložene datoteke stevilke.txt. Program PatNames
# bo na datoteko titles.txt izpisal ustrezne naslove.
# !!! pred uporabo je potrebno naložiti paket  XML
# -------------------------------------------------------------

doloci.opis <- function(num){
# najprej sestavimo naslov
  if(regexpr("island",num)>0){
    opis <- paste('---',num)
    cat("Island ",num,"\n"); flush.console()
  } else {
    a1 <- "http://patft.uspto.gov/netacgi/nph-Parser?"
    b1 <- "Sect1=PTO1&Sect2=HITOFF&d=PALL&p=1&u=%2Fnetahtml"
    c1 <- "%2FPTO%2Fsrchnum.htm&r=1&f=G&l=50&s1="
    a2 <- ".PN.&OS=PN/"
    a3 <- "&RS=PN/"
    num.c <- as.character(num)
    cat(num,"\n"); flush.console()
    url.s <- paste(a1,b1,c1,num.c,a2,num.c,a3,num.c,sep="")

  # poberi tekočo stran s spleta in jo razčleni
  # prepreči sporočila 'There were 50 or more warnings  ...'
    op <- options(); options(warn=-1)
    hp <- htmlTreeParse(url.s); options(op)
    html.s <- unlist(hp$children$html$children)

    if(any(regexpr('\"Images\"',html.s)>0)){
      opis <- c(num,'*** Full text is not available,',
        '    see image version')
    } else {
    # poiščemo točno določeno vrstico
    # 4 elemente za 2. značko 
      i <- which(regexpr("hr",html.s)>0)[2]
      naslov <- html.s[i+4]
    # poiscemo še datum, predhodnik 2. značke 
      datum <- html.s[i-1]
      names(naslov) <- NULL; names(datum) <- NULL
      opis <- c(num,naslov,datum)
    }
  }
  opis
}

#  library(XML)
#  setwd("C:/Users/batagelj/work/R/patents")
#
## preberemo številke iz znakovne datoteke v num
#  num <- readLines("./numbers.txt")
#
## določi in izpiši ustrezni seznam naslovov
#  writeLines(unlist(sapply(num,doloci.opis)),"./titles.txt")

numbers.txt