install.packages("XML")
library(XML)
#
# https://data.seoul.go.kr/
#
mykey <- "6c7a765a55627a6a33366e48767266"
#
#
url = "http://openapi.seoul.go.kr:8088"
auth_key = mykey
type = 'xml'
service = 'culturalEventInfo'
startindex = '1'
endindex = '50'
api_url = paste(url, auth_key, type, service, startindex, endindex, sep = '/')
api_url
parsedXml <-xmlParse(api_url)
rowXml <- getNodeSet(parsedXml, "//row")
api_data <-xmlToDataFrame(rowXml, stringsAsFactors = F)
#구조 확인
str(api_data)
#테이블 확인
View(api_data)
api_data
write.table(api_data,
file = "SeoulCulturalEventInfo.csv",
append = FALSE, quote = TRUE, sep = ",",
eol = "\n", na = "NA", col.names = T,
row.names = F)
----
{{:all_comb.xlsx}}
library(bitops)
library(RCurl)
library(rjson)
library(twitteR)
library(digest)
library(ROAuth)
library(KoNLP)
library(rJava)
library(tm)
library(wordcloud)
library(XLConnect)
setwd ("D:/Users/Hyo/Clouds/CS-DS/CS/MovieStudy")
rm(list=ls())
ani<- file.path("all_comb.xlsx")
anisheet <- readWorksheetFromFile(ani, sheet="imdb")
ani.text <- Corpus(VectorSource(anisheet$plotStory))
result.text <- ani.text
myCorpus <- Corpus(VectorSource(result.text))
myCorpus <- tm_map(myCorpus, removePunctuation)
myCorpus <- tm_map(myCorpus, removeNumbers)
myCorpus <- tm_map(myCorpus, tolower)
myStopwords <- c(stopwords('english'), "rt")
myCorpus <-tm_map(myCorpus, removeWords, myStopwords)
inspect(myCorpus[1:5])
myTdm <- TermDocumentMatrix(myCorpus, control=list(wordLengths=c(2,Inf)))
mat <- as.data.frame(as.matrix(myTdm))
write.table(mat, file="myTdm-ani.txt", col.names=FALSE, row.names=TRUE,sep="\t")
pal <- brewer.pal(12,"Paired")
# 폰트 세팅. 띄어쓰기나 대소문자에 민감하다는 점에 주의
# 맑은고딕 : windowsFonts(malgun=windowsFont("맑은 고딕"))
# 나눔고딕 : windowsFonts(malgun=windowsFont("나눔고딕"))
windowsFonts(malgun=windowsFont("서울남산체 B"))
m <- as.matrix(myTdm)
# calculate the frequency of words
v <- sort(rowSums(m), decreasing=TRUE)
myNames <- names(v)
k <- which(names(v)=="apple")
myNames[k] <- "apple"
d <- data.frame(word=myNames, freq=v)
#wordcloud(d$word, d$freq, scale=c(4,0.5), min.freq=3, random.order=F, rot.per=.1, family="malgun")
wordcloud(d$word, d$freq, scale=c(4,0.7), min.freq=2, random.order=F, rot.per=.1, colors=pal, family="malgun")
{{:ani_plot.png}}
{{:myTdm-ani.txt}}
";
$xml = simplexml_load_file($url);
echo "hello";
echo "";
echo $xml->asXML();
echo "
";
foreach ($xml->item as $oitemVal) {
$text = " \"".$oitemVal->title->content."\"\t";
$text .= " \"".$oitemVal->eng_title->content."\"\t";
$text .= $oitemVal->year->content."\t";
$text .= " \"".$oitemVal->director->content."\"\t";
foreach ($oitemVal->actor->content as $oContentVal) {
$text .= " \"$oContentVal\"";
} $oContentVal="";
$text .= "\t";
$text .= $oitemVal->more_actor->link."\t";
$text .= $oitemVal->nation->content."\t";
foreach ($oitemVal->genre->content as $oContentVal) {
$text .= " \"$oContentVal\"";
} $oContentVal="";
$text .= "\t";
$text .= $oitemVal->open_info[0]->content."\t";
$text .= "\n";
echo "$text";
fwrite($myfile, $text);
}
$text='';
}
fclose($myfile);
?>