Last active
April 10, 2017 12:37
-
-
Save Nachtjagdgeschwader/b5a90a5c2acc35e3859ab230bdf021d2 to your computer and use it in GitHub Desktop.
Save data ("URL","Date","Original Text","SharedText") about Facebook posts found by keyword with RSelenium and PhantomJS
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| install.packages("devtools") | |
| library(devtools) | |
| install_github("ropensci/RSelenium") | |
| library(RSelenium) | |
| psPath <- "S:/Path to PhantomJS folder/phantomjs-2.1.1-windows/bin/phantomjs.exe" | |
| pJS <- phantom(pjs_cmd = psPath) | |
| remDr <- remoteDriver(browserName = "phantomjs") | |
| remDr$open() | |
| loginURL <- 'https://www.facebook.com/login.php' | |
| remDr$navigate(loginURL) | |
| remDr$findElement("id", "email")$sendKeysToElement(list("Your email")) | |
| remDr$findElement("id", "pass")$sendKeysToElement(list("Your password")) | |
| remDr$findElement("id", "loginbutton")$clickElement() | |
| searchURL <- 'https://www.facebook.com/search/top/?q=%D0%9A%D0%9C%D0%98%D0%A1&filters_rp_creation_time=%7B"start_month"%3A"2014-01"%2C"end_month"%3A"2014-04"%7D&filters_rp_author=public&filters_rp_chrono_sort=top' | |
| # search query URL whith all filters needed | |
| remDr$navigate(searchURL) | |
| for(i in 1:100){ | |
| remDr$executeScript(paste("scroll(0,",i*1000,");")) | |
| Sys.sleep(3) | |
| } | |
| # scroll down 100 times waiting 3 seconds each time for page to render | |
| URLRaw <- remDr$findElements(using = 'css', "div._6a._5u5j._6b span.fsm.fwn.fcg a._5pcq") | |
| Attr<-function(x) | |
| { | |
| x$getElementAttribute("href") | |
| } | |
| URL <- mapply(Attr,URLRaw) | |
| getText<-function(x) | |
| { | |
| x$getElementText() | |
| } | |
| Date <- mapply(getText,URLRaw) | |
| TextRaw <- remDr$findElements(using = 'css', "div.userContent p") | |
| OriginalText <- mapply(getText,TextRaw) | |
| Shared <- remDr$findElements(using = 'css', "div.mtm") | |
| SharedText <- mapply(getText,Shared) | |
| cbind.fill <- function(...){ | |
| nm <- list(...) | |
| nm <- lapply(nm, as.matrix) | |
| n <- max(sapply(nm, nrow)) | |
| do.call(cbind, lapply(nm, function (x) | |
| rbind(x, matrix(, n-nrow(x), ncol(x))))) | |
| } | |
| # function to deal with missing data (like no shared or original text) | |
| # vectors needs to be of the similar length to be combined into matrix | |
| # thus for each missing value the "NA" is inserted | |
| data <- data.frame(cbind.fill(URL,Date,OriginalText,SharedText)) | |
| colnames(data) <- c("URL","Date","Original Text","SharedText") | |
| write.table(data, "S:/Path for results to be saved/Data.csv", col.names = TRUE, sep=";") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment