Web将tableauViz拖放到R数据帧中
我花了很多时间寻找这个问题的答案,但还没有找到任何答案。我试图完成的是将包含在tableauViz元素中的Tableau表信息刮取,并将其传播到R数据帧中。在我的第一次尝试中,使用RStudio,我使用了以下代码,并尝试将tableauViz作为HTML读取Web将tableauViz拖放到R数据帧中,r,xml,web-scraping,tableau-api,python,R,Xml,Web Scraping,Tableau Api,Python,我花了很多时间寻找这个问题的答案,但还没有找到任何答案。我试图完成的是将包含在tableauViz元素中的Tableau表信息刮取,并将其传播到R数据帧中。在我的第一次尝试中,使用RStudio,我使用了以下代码,并尝试将tableauViz作为HTML读取 # Load rvest functions library(rvest) # Specifying the url for desired website to be scrapped url <- “https://oir.uga
# Load rvest functions
library(rvest)
# Specifying the url for desired website to be scrapped
url <- “https://oir.uga.edu/factbook/studentinformation/S07StuP58/”
# Reading the HTML code from the website
webpage <- read_html(url)
# Using CSS selectors to scrap the rankings section
rank_data_html <- html_nodes(webpage,'.tableauViz')
我从该列表中找到的唯一有价值的属性是静态图像png链接
然而,我不相信我能将这些转换成数据帧
唯一提到这个问题的是这段优秀的YouTube视频“通过R笔记本和Shiny将Tableau与R集成”。我导航到作者的,看看是否能找到一些示例代码,但我找不到任何
如何解决此问题?为了获取数据,您需要tableau URL,在本例中为: 流程如下所示: 调用以下url:
GET https://public.tableau.com/views/S07StuP58/Dashboard1?:embed=y&:showVizHome=no
从id为tsConfigContainer的textarea中提取JSON内容
使用会话id生成url
POST https://public.tableau.com/{vizql_path}/bootstrapSession/sessions/{session_id}
从最初不是JSON的响应中提取JSON数据以分割数据
从大型JSON配置中提取数据,这并不简单,因为所有字符串数据都位于单个数组中。您需要从各个字段获取数据索引,以便能够将数据拆分为列,然后构建数据框架
以下代码将提示用户按索引选择工作表,解析数据并将其放入数据框中:
library(rvest)
library(rjson)
library(httr)
library(stringr)
#replace the hostname and the path if necessary
host_url <- "https://public.tableau.com"
path <- "/views/S07StuP58/Dashboard1"
body <- read_html(modify_url(host_url,
path = path,
query = list(":embed" = "y",":showVizHome" = "no")
))
data <- body %>%
html_nodes("textarea#tsConfigContainer") %>%
html_text()
json <- fromJSON(data)
url <- modify_url(host_url, path = paste(json$vizql_root, "/bootstrapSession/sessions/", json$sessionid, sep =""))
resp <- POST(url, body = list(sheet_id = json$sheetId), encode = "form")
data <- content(resp, "text")
extract <- str_match(data, "\\d+;(\\{.*\\})\\d+;(\\{.*\\})")
info <- fromJSON(extract[1,1])
data <- fromJSON(extract[1,3])
worksheets = names(data$secondaryInfo$presModelMap$vizData$presModelHolder$genPresModelMapPresModel$presModelMap)
for(i in 1:length(worksheets)){
print(paste("[",i,"] ",worksheets[i], sep=""))
}
selected <- readline(prompt="select worksheet by index: ");
worksheet <- worksheets[as.integer(selected)]
print(paste("you selected :", worksheet, sep=" "))
columnsData <- data$secondaryInfo$presModelMap$vizData$presModelHolder$genPresModelMapPresModel$presModelMap[[worksheet]]$presModelHolder$genVizDataPresModel$paneColumnsData
i <- 1
result <- list();
for(t in columnsData$vizDataColumns){
if (is.null(t[["fieldCaption"]]) == FALSE) {
paneIndex <- t$paneIndices
columnIndex <- t$columnIndices
if (length(t$paneIndices) > 1){
paneIndex <- t$paneIndices[1]
}
if (length(t$columnIndices) > 1){
columnIndex <- t$columnIndices[1]
}
result[[i]] <- list(
fieldCaption = t[["fieldCaption"]],
valueIndices = columnsData$paneColumnsList[[paneIndex + 1]]$vizPaneColumns[[columnIndex + 1]]$valueIndices,
aliasIndices = columnsData$paneColumnsList[[paneIndex + 1]]$vizPaneColumns[[columnIndex + 1]]$aliasIndices,
dataType = t[["dataType"]],
stringsAsFactors = FALSE
)
i <- i + 1
}
}
dataFull = data$secondaryInfo$presModelMap$dataDictionary$presModelHolder$genDataDictionaryPresModel$dataSegments[["0"]]$dataColumns
cstring <- list();
for(t in dataFull) {
if(t$dataType == "cstring"){
cstring <- t
break
}
}
data_index <- 1
name_index <- 1
frameData <- list()
frameNames <- c()
for(t in dataFull) {
for(index in result) {
if (t$dataType == index["dataType"]){
if (length(index$valueIndices) > 0) {
j <- 1
vector <- character(length(index$valueIndices))
for (it in index$valueIndices){
vector[j] <- t$dataValues[it+1]
j <- j + 1
}
frameData[[data_index]] <- vector
frameNames[[name_index]] <- paste(index$fieldCaption, "value", sep="-")
data_index <- data_index + 1
name_index <- name_index + 1
}
if (length(index$aliasIndices) > 0) {
j <- 1
vector <- character(length(index$aliasIndices))
for (it in index$aliasIndices){
if (it >= 0){
vector[j] <- t$dataValues[it+1]
} else {
vector[j] <- cstring$dataValues[abs(it)]
}
j <- j + 1
}
frameData[[data_index]] <- vector
frameNames[[name_index]] <- paste(index$fieldCaption, "alias", sep="-")
data_index <- data_index + 1
name_index <- name_index + 1
}
}
}
}
df <- NULL
lengthList <- c()
for(i in 1:length(frameNames)){
lengthList[i] <- length(frameData[[i]])
}
max <- max(lengthList)
for(i in 1:length(frameNames)){
if (length(frameData[[i]]) < max){
len <- length(frameData[[i]])
frameData[[i]][(len+1):max]<-""
}
df[frameNames[[i]]] <- frameData[i]
}
options(width = 1200)
df <- as.data.frame(df, stringsAsFactors = FALSE)
print(df)
上述代码的等效代码为:
导入请求
从bs4导入BeautifulSoup
导入json
进口稀土
作为pd进口熊猫
如有必要,请更换主机名和路径
主机url=https://public.tableau.com
路径=/views/s0758/Dashboard1
url=f{host\u url}{path}
r=requests.get
网址,
参数={
:嵌入:y,
:showVizHome:没有
}
soup=BeautifulSoupr.text,html.parser
tableauData=json.loadssup.findtextarea,{id:tsConfigContainer}.text
dataUrl=f'{host_url}{tableauData[vizql_root]}/bootstrapSession/sessions/{tableauData[sessionid]}'
r=请求。postdataUrl,数据={
工作表id:tableauData[工作表id],
}
dataReg=re.search'\d+;{.*}\d+;{.*}',r.text,re.MULTILINE
info=json.loadsdataReg.group1
data=json.loadsdataReg.group2
工作表=listdata[secondaryInfo][presModelMap][vizData][presModelHolder][GenPresModelMapPresModelMap][presModelMap]。键
对于idx,枚举工作表中的ws:
printf[{idx}]{ws}
选定=输入按索引选择工作表:
工作表=工作表[intselected]
您选择的打印:{工作表}
columnsData=data[secondaryInfo][presModelMap][vizData][presModelHolder][genPresModelMapPresModel][presModelMap][worksheet][presModelHolder][genVizDataPresModel][paneColumnsData]
结果=[
{
fieldCaption:t.getfieldCaption,
价值指数:columnsData[paneColumnsList][t[PaneIndicates][0]][vizPaneColumns][t[ColumnIndicates][0]][ValueIndicates],
别名索引:columnsData[paneColumnsList][t[PaneIndicates][0]][vizPaneColumns][t[ColumnIndicates][0]][AliasIndicates],
数据类型:t.getdataType,
窗格索引:t[窗格索引][0],
ColumnIndexes:t[ColumnIndexes][0]
}
对于t列数据[vizDataColumns]
如果t.getfieldCaption
]
dataFull=data[secondaryInfo][presModelMap][dataDictionary][presModelHolder][genDataDictionaryPresModel][dataSegments][0][dataColumns]
定义变量、值、字符串:
返回值[it],如果它>=0,则返回值[it],否则返回[dataValues][absit-1]
frameData={}
如果t[dataType]==cstring][0],则cstring=[t代表数据完整中的t]
对于数据完整中的t:
对于结果中的索引:
如果t[dataType]==索引[dataType]:
如果列宁指数[ValueIndexs]>0:
帧数据[f'{index[fieldCaption]}-value']=[t[dataValues][absit]用于索引[valueindex]]
如果列宁指数[AliasIndex]>0:
frameData[f'{index[fieldCaption]}-别名']=[OrianAsit,t[dataValues],在索引[AliasIndexes]中为其设置字符串]
df=pd.DataFrame.from_dictframeData,orient='index'.fillna0.T
使用pd.option\u上下文'display.max\u rows',None',display.max\u columns',None',display.width',1000:
printdf
对于python和R脚本来说,也许这不关我的事,但作者有意将该工作簿发布在Tableau Public上,限制仅允许PDF或PNG下载。您要求我们提供一种方法来规避作者对数据的预期用途。也就是说,您试图完成的工作非常困难,因为Tableau可视化不仅仅是html。AJAX、客户端渲染和SVG的使用非常复杂。您最好联系发布工作簿的人,询问他们是否愿意与您共享数据。
library(rvest)
library(rjson)
library(httr)
library(stringr)
#replace the hostname and the path if necessary
host_url <- "https://public.tableau.com"
path <- "/views/S07StuP58/Dashboard1"
body <- read_html(modify_url(host_url,
path = path,
query = list(":embed" = "y",":showVizHome" = "no")
))
data <- body %>%
html_nodes("textarea#tsConfigContainer") %>%
html_text()
json <- fromJSON(data)
url <- modify_url(host_url, path = paste(json$vizql_root, "/bootstrapSession/sessions/", json$sessionid, sep =""))
resp <- POST(url, body = list(sheet_id = json$sheetId), encode = "form")
data <- content(resp, "text")
extract <- str_match(data, "\\d+;(\\{.*\\})\\d+;(\\{.*\\})")
info <- fromJSON(extract[1,1])
data <- fromJSON(extract[1,3])
worksheets = names(data$secondaryInfo$presModelMap$vizData$presModelHolder$genPresModelMapPresModel$presModelMap)
for(i in 1:length(worksheets)){
print(paste("[",i,"] ",worksheets[i], sep=""))
}
selected <- readline(prompt="select worksheet by index: ");
worksheet <- worksheets[as.integer(selected)]
print(paste("you selected :", worksheet, sep=" "))
columnsData <- data$secondaryInfo$presModelMap$vizData$presModelHolder$genPresModelMapPresModel$presModelMap[[worksheet]]$presModelHolder$genVizDataPresModel$paneColumnsData
i <- 1
result <- list();
for(t in columnsData$vizDataColumns){
if (is.null(t[["fieldCaption"]]) == FALSE) {
paneIndex <- t$paneIndices
columnIndex <- t$columnIndices
if (length(t$paneIndices) > 1){
paneIndex <- t$paneIndices[1]
}
if (length(t$columnIndices) > 1){
columnIndex <- t$columnIndices[1]
}
result[[i]] <- list(
fieldCaption = t[["fieldCaption"]],
valueIndices = columnsData$paneColumnsList[[paneIndex + 1]]$vizPaneColumns[[columnIndex + 1]]$valueIndices,
aliasIndices = columnsData$paneColumnsList[[paneIndex + 1]]$vizPaneColumns[[columnIndex + 1]]$aliasIndices,
dataType = t[["dataType"]],
stringsAsFactors = FALSE
)
i <- i + 1
}
}
dataFull = data$secondaryInfo$presModelMap$dataDictionary$presModelHolder$genDataDictionaryPresModel$dataSegments[["0"]]$dataColumns
cstring <- list();
for(t in dataFull) {
if(t$dataType == "cstring"){
cstring <- t
break
}
}
data_index <- 1
name_index <- 1
frameData <- list()
frameNames <- c()
for(t in dataFull) {
for(index in result) {
if (t$dataType == index["dataType"]){
if (length(index$valueIndices) > 0) {
j <- 1
vector <- character(length(index$valueIndices))
for (it in index$valueIndices){
vector[j] <- t$dataValues[it+1]
j <- j + 1
}
frameData[[data_index]] <- vector
frameNames[[name_index]] <- paste(index$fieldCaption, "value", sep="-")
data_index <- data_index + 1
name_index <- name_index + 1
}
if (length(index$aliasIndices) > 0) {
j <- 1
vector <- character(length(index$aliasIndices))
for (it in index$aliasIndices){
if (it >= 0){
vector[j] <- t$dataValues[it+1]
} else {
vector[j] <- cstring$dataValues[abs(it)]
}
j <- j + 1
}
frameData[[data_index]] <- vector
frameNames[[name_index]] <- paste(index$fieldCaption, "alias", sep="-")
data_index <- data_index + 1
name_index <- name_index + 1
}
}
}
}
df <- NULL
lengthList <- c()
for(i in 1:length(frameNames)){
lengthList[i] <- length(frameData[[i]])
}
max <- max(lengthList)
for(i in 1:length(frameNames)){
if (length(frameData[[i]]) < max){
len <- length(frameData[[i]])
frameData[[i]][(len+1):max]<-""
}
df[frameNames[[i]]] <- frameData[i]
}
options(width = 1200)
df <- as.data.frame(df, stringsAsFactors = FALSE)
print(df)
X.Student.Aid.Program.Type..value X.Student.Aid.Program..value X..Measure.Names..alias X.Multiple.Values..alias
1 Grants/Scholarships Subtotal Graduate Amount Awarded $XXXXXXXX
2 Grants/Scholarships Other (External) Grants/Scholarships Graduate Amount Awarded $XXXXXX
3 Grants/Scholarships Miscellaneous Tuition/Fee Payments/Waivers Graduate Amount Awarded $XXXXXX
4 Grants/Scholarships Graduate Assistantship Tuition Waivers Graduate Amount Awarded $XXXXXX
5 Grants/Scholarships Athletic Scholarships Graduate Amount Awarded $XXXXXX
6 Grants/Scholarships Institutional Grants/Scholarships Graduate Amount Awarded $XXXXXX
7 Grants/Scholarships State (Other) Grants/Scholarships Graduate Amount Awarded $XXXXXX
8 Grants/Scholarships Zell Miller Scholarships Graduate Amount Awarded $XXXXXX
9 Grants/Scholarships HOPE Scholarships Graduate Amount Awarded $XXXXXX
10 Grants/Scholarships Federal (Other) Grants/Scholarships Graduate Amount Awarded
11 Grants/Scholarships Federal Supplemental Grants Graduate Amount Awarded
12 Grants/Scholarships Federal Pell Grants Graduate Amount Awarded
13 Grants/Scholarships Subtotal Graduate Number of Awards XXXXXX
14 Grants/Scholarships Other (External) Grants/Scholarships Graduate Number of Awards XXX