Scraping data from Twitter’s REST API
Pablo Barbera
October 18, 2018
We’ll now turn to a different type of Twitter data – static data, either recent tweets or user-level information. This type of data can be retrieved with Twitter’s REST API. We will use the tweetscores package here – this is a package that I created to facilitate the collection and analysis of Twitter data.
Searching recent tweets
It is possible to download recent tweets, but only up those less than 7 days old, and in some cases not all of them.
load("~/my_oauth")
library(tweetscores)## Loading required package: R2WinBUGS## Loading required package: coda## Loading required package: boot## ##
## ## tweetscores: tools for the analysis of Twitter data## ## Pablo Barbera (LSE)## ## www.tweetscores.com
## ##library(streamR)## Loading required package: RCurl## Loading required package: bitops## Loading required package: rjson## Warning: package 'rjson' was built under R version 3.4.4## Loading required package: ndjson## Warning: package 'ndjson' was built under R version 3.4.4searchTweets(q=c("brexit", "survey"),
filename="~/data/recent-brexit-tweets.json",
n=1000, until="2018-10-15",
oauth=my_oauth)## 100 tweets. Max id: 1051623681049456640## 178 hits left## 200 tweets. Max id: 1051623202785505280## 177 hits left## 300 tweets. Max id: 1051622789134864384## 176 hits left## 400 tweets. Max id: 1051622361819205632## 175 hits left## 500 tweets. Max id: 1051622077126586368## 174 hits left## 600 tweets. Max id: 1051621732220592128## 173 hits left## 700 tweets. Max id: 1051621281735544832## 172 hits left## 800 tweets. Max id: 1051620924603150336## 171 hits left## 900 tweets. Max id: 1051620596918960128## 170 hits left## 1000 tweets. Max id: 1051620164813361152tweets <- parseTweets("~/data/recent-brexit-tweets.json")## 1000 tweets have been parsed.What are the most popular hashtags?
library(stringr)
ht <- str_extract_all(tweets$text, '#[A-Za-z0-9_]+')
ht <- unlist(ht)
head(sort(table(ht), decreasing = TRUE))## ht
## #Brexit #EU #brexit #PeoplesVote #DFLA
## 102 14 12 9 6
## #StopBrexit
## 6You can check the documentation about the options for string search here.
Extracting users’ profile information
This is how you would extract information from user profiles:
wh <- c("realDonaldTrump", "POTUS", "VP", "FLOTUS")
users <- getUsersBatch(screen_names=wh,
oauth=my_oauth)## 1--4 users leftstr(users)## 'data.frame': 4 obs. of 9 variables:
## $ id_str : chr "822215679726100480" "818910970567344128" "25073877" "818876014390603776"
## $ screen_name : chr "POTUS" "VP" "realDonaldTrump" "FLOTUS"
## $ name : chr "President Trump" "Vice President Mike Pence" "Donald J. Trump" "Melania Trump"
## $ description : chr "45th President of the United States of America, @realDonaldTrump. Tweets archived: https://t.co/eVVzoBb3Zr" "Vice President Mike Pence. Husband, father, & honored to serve as the 48th Vice President of the United States."| __truncated__ "45th President of the United States of America\U0001f1fa\U0001f1f8" "This account is run by the Office of First Lady Melania Trump. Tweets may be archived. More at https://t.co/eVVzoBb3Zr"
## $ followers_count: int 24261707 6672535 55196162 11046469
## $ statuses_count : int 4236 5236 39313 402
## $ friends_count : int 39 11 47 6
## $ created_at : chr "Thu Jan 19 22:54:28 +0000 2017" "Tue Jan 10 20:02:44 +0000 2017" "Wed Mar 18 13:46:38 +0000 2009" "Tue Jan 10 17:43:50 +0000 2017"
## $ location : chr "Washington, D.C." "Washington, D.C." "Washington, DC" "Washington, D.C."Which of these has the most followers?
users[which.max(users$followers_count),]## id_str screen_name name
## 3 25073877 realDonaldTrump Donald J. Trump
## description
## 3 45th President of the United States of America\U0001f1fa\U0001f1f8
## followers_count statuses_count friends_count
## 3 55196162 39313 47
## created_at location
## 3 Wed Mar 18 13:46:38 +0000 2009 Washington, DCusers$screen_name[which.max(users$followers_count)]## [1] "realDonaldTrump"Download up to 3,200 recent tweets from a Twitter account:
getTimeline(filename="~/data/realDonaldTrump.json", screen_name="realDonaldTrump", n=1000, oauth=my_oauth)## 199 tweets. Max id: 1046201064469549056## 898 hits left## 397 tweets. Max id: 1040294453586665472## 897 hits left## 593 tweets. Max id: 1034810550025433090## 896 hits left## 793 tweets. Max id: 1029105967068323840## 895 hits left## 993 tweets. Max id: 1022812910702215169## 894 hits left## 1193 tweets. Max id: 1016487491065565184What are the most common hashtags?
tweets <- parseTweets("~/data/realDonaldTrump.json")## 1193 tweets have been parsed.ht <- str_extract_all(tweets$text, '#[A-Za-z0-9_]+')
ht <- unlist(ht)
head(sort(table(ht), decreasing = TRUE))## ht
## #MAGA #Florence #HurricaneFlorence
## 22 17 11
## #HurricaneMichael #UNGA #Michael
## 10 7 6Building friend and follower networks
Download friends and followers:
followers <- getFollowers("MethodologyLSE",
oauth=my_oauth)## 15 API calls left## 1554 followers. Next cursor: 0## 14 API calls leftfriends <- getFriends("MethodologyLSE",
oauth=my_oauth)## 15 API calls left## 126 friends. Next cursor: 0## 14 API calls leftWhat are the most common words that friends of the MethodologyLSE account use to describe themselves on Twitter?
# extract profile descriptions
users <- getUsersBatch(ids=friends, oauth=my_oauth)## 1--126 users left## 2--26 users left# create table with frequency of word use
library(quanteda)## Warning: package 'quanteda' was built under R version 3.4.4## Package version: 1.3.0## Parallel computing: 2 of 4 threads used.## See https://quanteda.io for tutorials and examples.##
## Attaching package: 'quanteda'## The following object is masked from 'package:utils':
##
## Viewtw <- corpus(users$description[users$description!=""])
dfm <- dfm(tw, remove=c(stopwords("english"), stopwords("spanish"),
"t.co", "https", "rt", "rts", "http"),
remove_punct=TRUE)
topfeatures(dfm, n = 30)## lse research science london political school
## 52 41 31 27 26 26
## economics social department policy news centre
## 26 23 14 13 11 10
## public uk events teaching university politics
## 10 10 10 9 9 9
## lse's us twitter account professor society
## 9 8 8 8 8 8
## official data programme academic methods institute
## 8 7 7 7 7 6# create wordcloud
par(mar=c(0,0,0,0))
textplot_wordcloud(dfm, rotation=0, min_size=1, max_size=5, max_words=100)
Estimating ideology based on Twitter networks
The tweetscores package also includes functions to replicate the method developed in the Political Analysis paper Birds of a Feather Tweet Together. Bayesian Ideal Point Estimation Using Twitter Data. For an application of this method, see also this Monkey Cage blog post.
# download list of friends for an account
user <- "DonaldJTrumpJr"
friends <- getFriends(user, oauth=my_oauth)## 14 API calls left## 1274 friends. Next cursor: 0## 13 API calls left# estimating ideology with correspondence analysis method
(theta <- estimateIdeology2(user, friends, verbose=FALSE))## DonaldJTrumpJr follows 141 elites: ABC, AEI, ajam, AlbertBrooks, AllenWest, AmbJohnBolton, andersoncooper, AndreaTantaros, AnnCoulter, AP, AriFleischer, azizansari, BBCBreaking, BBCWorld, benshapiro, BillyHallowell, BreakingNews, BreitbartNews, BretBaier, brithume, BuzzFeed, ByronYork, CharlieDaniels, chrisrock, chucktodd, chuckwoolery, CNBC, CNN, cnnbrk, DailyCaller, DanaPerino, daveweigel, davidgregory, DennisDMZ, DineshDSouza, DRUDGE, DRUDGE_REPORT, ericbolling, FareedZakaria, FinancialTimes, ForAmerica, Forbes, foxandfriends, FoxNews, foxnewspolitics, funnyordie, gatewaypundit, Gawker, ggreenwald, GOP, gopleader, GovChristie, GovernorPerry, GovMikeHuckabee, greggutfeld, GStephanopoulos, hardball_chris, Heritage, HeyTammyBruce, HouseGOP, howardfineman, HuffingtonPost, iamjohnoliver, IngrahamAngle, iowahawkblog, JamesOKeefeIII, JamesRosenFNC, jasoninthehouse, jim_jordan, JimDeMint, jimmyfallon, Judgenap, JudicialWatch, kanyewest, KatiePavlich, kilmeade, kimguilfoyle, krauthammer, KurtSchlichter, larryelder, LindaSuhler, loudobbsnews, LukeRussert, marcorubio, marklevinshow, MarkSteynOnline, marthamaccallum, michellemalkin, mitchellreports, MittRomney, MonicaCrowley, NASA, neiltyson, newsbusters, newtgingrich, NolteNC, NRA, NRO, nytimes, oreillyfactor, politico, ppppolls, RealBenCarson, realDonaldTrump, RealJamesWoods, Reince, repdianeblack, reploubarletta, replouiegohmert, reppaulryan, Reuters, SarahPalinUSA, scrowder, seanhannity, secupp, Senate_GOPs, senmikelee, sentedcruz, ShannonBream, SharylAttkisson, stevekingia, SteveMartinToGo, tamronhall, TeamCavuto, tedcruz, TedNugent, TEDTalks, tgowdysc, TheAtlantic, TheEconomist, TheOnion, ThomasSowell, TODAYshow, townhallcom, TuckerCarlson, TwitchyTeam, VanityFair, washingtonpost, wikileaks, WSJ, YoungCons## [1] 1.480885# download list of friends for an account
user <- "realDonaldTrump"
friends <- getFriends(user, oauth=my_oauth)## 11 API calls left## 47 friends. Next cursor: 0## 10 API calls left# estimating ideology with correspondence analysis method
(theta <- estimateIdeology2(user, friends, verbose=FALSE))## realDonaldTrump follows 10 elites: AnnCoulter, DRUDGE_REPORT, ericbolling, foxandfriends, IngrahamAngle, oreillyfactor, piersmorgan, Reince, seanhannity, TuckerCarlson## [1] 1.760218Other types of data
The REST API offers also a long list of other endpoints that could be of use at some point, depending on your research interests.
- You can search users related to specific keywords:
users <- searchUsers(q="MethodologyLSE", count=100, oauth=my_oauth)
users$screen_name[1:10]## [1] "p_barbera" "MethodologyLSE" "ellie_knott"
## [4] "SEDS_LSE" "gokhan_ciflikli" "NoamTitelman"
## [7] "Cris_Monteneg" "joannaaa" "ROliveiraT"
## [10] "kateesummers"- If you know the ID of the tweets, you can download it directly from the API. This is useful because tweets cannot be redistributed as part of the replication materials of a published paper, but the list of tweet IDs can be shared:
# Downloading tweets when you know the ID
getStatuses(ids=c("474134260149157888", "266038556504494082"),
filename="~/data/old-tweets.json",
oauth=my_oauth)## 900 API calls left## 2 tweets left.## 0 tweets left.## 899 API calls leftparseTweets("~/data/old-tweets.json")## 2 tweets have been parsed.## text
## 1 Are you allowed to impeach a president for gross incompetence?
## 2 The electoral college is a disaster for a democracy.
## retweet_count favorite_count favorited truncated id_str
## 1 NA NA FALSE FALSE 474134260149157888
## 2 NA NA FALSE FALSE 266038556504494082
## in_reply_to_screen_name
## 1 NA
## 2 NA
## source
## 1 <a href="http://twitter.com/download/android" rel="nofollow">Twitter for Android</a>
## 2 <a href="http://twitter.com" rel="nofollow">Twitter Web Client</a>
## retweeted created_at in_reply_to_status_id_str
## 1 FALSE Wed Jun 04 10:23:11 +0000 2014 NA
## 2 FALSE Wed Nov 07 04:45:09 +0000 2012 NA
## in_reply_to_user_id_str lang listed_count verified location
## 1 NA en 94781 TRUE Washington, DC
## 2 NA en 94781 TRUE Washington, DC
## user_id_str
## 1 25073877
## 2 25073877
## description
## 1 45th President of the United States of America\U0001f1fa\U0001f1f8
## 2 45th President of the United States of America\U0001f1fa\U0001f1f8
## geo_enabled user_created_at statuses_count
## 1 TRUE Wed Mar 18 13:46:38 +0000 2009 39313
## 2 TRUE Wed Mar 18 13:46:38 +0000 2009 39313
## followers_count favourites_count protected user_url
## 1 55196165 26 FALSE https://t.co/OMxB0x7xC5
## 2 55196165 26 FALSE https://t.co/OMxB0x7xC5
## name time_zone user_lang utc_offset friends_count
## 1 Donald J. Trump NA en NA 47
## 2 Donald J. Trump NA en NA 47
## screen_name country_code country place_type full_name place_name
## 1 realDonaldTrump NA NA NA NA NA
## 2 realDonaldTrump NA NA NA NA NA
## place_id place_lat place_lon lat lon expanded_url url
## 1 NA NaN NaN NA NA NA NA
## 2 NA NaN NaN NA NA NA NA- Lists of Twitter users, compiled by other users, are also accessible through the API.
# download user information from a list
MCs <- getList(list_name="new-members-of-congress",
screen_name="cspan", oauth=my_oauth)## 900 API calls left## 20 users in list. Next cursor: 5427698142933319684## 899 API calls left## 40 users in list. Next cursor: 4611686021745187729## 898 API calls left## 60 users in list. Next cursor: 0## 897 API calls lefthead(MCs)## id id_str name screen_name
## 1 8.272798e+17 827279765287559171 Rep. Mike Johnson RepMikeJohnson
## 2 8.235530e+17 823552974253342721 Anthony G. Brown RepAnthonyBrown
## 3 8.171385e+17 817138492614524928 Ted Budd RepTedBudd
## 4 8.170763e+17 817076257770835968 Adriano Espaillat RepEspaillat
## 5 8.170502e+17 817050219007328258 Rep. Blunt Rochester RepLBR
## 6 8.168339e+17 816833925456789505 Nanette D. Barragán RepBarragan
## location
## 1 Washington, DC
## 2 Washington, DC
## 3 Davie County, North Carolina
## 4 https://www.facebook.com/Congr
## 5 Delaware, USA - Washington, DC
## 6 San Pedro, CA
## description
## 1 Proudly serving Louisiana's 4th Congressional District. Member on @HouseJudiciary & @NatResources.
## 2 Congressman proudly representing Maryland's Fourth District. Member of @HASCDemocrats & @NRDems. Father, husband & retired @USArmyReserve Colonel
## 3 Proudly serving the 13th district of North Carolina. #NC13
## 4 U.S. Representative proudly serving New York’s 13th Congressional District. Follow my work in Washington and #NY13
## 5 Official Twitter page for U.S. Representative Lisa Blunt Rochester (D-DE). Tweets from Rep. Blunt Rochester signed -LBR.
## 6 Official account. Honored to represent California's 44th Congressional District. #CA44 Member of the @HispanicCaucus @USProgressives @Dodgers fan.
## url followers_count friends_count
## 1 https://t.co/qLAyhrFbRl 3736 402
## 2 https://t.co/2u5X332ICM 10491 922
## 3 https://t.co/VTsvWe0pia 5997 195
## 4 https://t.co/lcRqmQFAbz 11209 1291
## 5 https://t.co/Fe3XCG51wO 7604 321
## 6 https://t.co/Mt3nPi7hSH 8612 798
## created_at time_zone lang
## 1 Thu Feb 02 22:17:20 +0000 2017 NA en
## 2 Mon Jan 23 15:28:24 +0000 2017 NA en
## 3 Thu Jan 05 22:39:33 +0000 2017 NA en
## 4 Thu Jan 05 18:32:15 +0000 2017 NA en
## 5 Thu Jan 05 16:48:47 +0000 2017 NA en
## 6 Thu Jan 05 02:29:18 +0000 2017 NA enThis is also useful if e.g. you’re interested in compiling lists of journalists, because media outlets offer these lists in their profiles.
- List of users who retweeted a particular tweet – unfortunately, it’s limited to only 100 most recent retweets.
# Download list of users who retweeted a tweet (unfortunately, only up to 100)
rts <- getRetweets(id='942123433873281024', oauth=my_oauth)## 75 API calls left## 73 retweeters. Next cursor: 0## 74 API calls left# https://twitter.com/realDonaldTrump/status/942123433873281024
users <- getUsersBatch(ids=rts, oauth=my_oauth)## 1--73 users left# create table with frequency of word use
library(quanteda)
tw <- corpus(users$description[users$description!=""])
dfm <- dfm(tw, remove=c(stopwords("english"), stopwords("spanish"),
"t.co", "https", "rt", "rts", "http"),
remove_punct = TRUE)
# create wordcloud
par(mar=c(0,0,0,0))
textplot_wordcloud(dfm, rot.per=0, scale=c(3, .50), max.words=100)## Warning: scalemax.wordsrot.per is deprecated; use min_size and
## max_sizemax_wordsrotation instead
- And one final function to convert dates in their internal Twitter format to another format we could work with in R:
# format Twitter dates to facilitate analysis
tweets <- parseTweets("~/data/realDonaldTrump.json")## 1193 tweets have been parsed.tweets$date <- formatTwDate(tweets$created_at, format="date")
hist(tweets$date, breaks="month")
Checking for bots
# adapted from the botcheck package by @marsha5814
botometer = function(user, my_oauth, mashape_key, verbose=TRUE) {
require(httr)
# creating OAuth token
myapp = oauth_app("twitter", key=my_oauth$consumer_key,
secret=my_oauth$consumer_secret)
sig = sign_oauth1.0(myapp, token=my_oauth$access_token,
token_secret=my_oauth$access_token_secret)
users_url = "https://api.twitter.com/1.1/users/show.json?screen_name="
statuses_url = "https://api.twitter.com/1.1/statuses/user_timeline.json?screen_name="
search_url = "https://api.twitter.com/1.1/search/tweets.json?q=%40"
opts = "&count=200"
# API call to get user
if (verbose) message("Downloading user profile...")
userdata = GET(paste0(users_url,user,opts), sig)
# API call to get tweets
if (verbose) message("Downloading user tweets...")
tweets = GET(paste0(statuses_url,user,opts), sig)
# API call to get mentions
if (verbose) message("Downloading user mentions...")
mentions = GET(paste0(search_url,user,opts), sig)
# Put everything in a list
body = list(
timeline = content(tweets, type="application/json"),
mentions = content(mentions, type="application/json"),
user = content(userdata, type="application/json")
)
# Convert to JSON
body_json = RJSONIO::toJSON(body, auto_unbox = T, pretty = T)
# Make the API request
if (verbose) message("Checking Botometer scores...")
result = POST("https://osome-botometer.p.mashape.com/2/check_account",
encode="json",
add_headers(`X-Mashape-Key`=mashape_key),
body=body_json)
# Parse result
result = content(result, as = "parsed")
# Return "English" score
return(result)
}
results <- botometer("MethodologyLSE", my_oauth,
mashape_key = 'Ujq7AAd3igmshqCBvI1LWbz0J8Hlp1hvVOYjsnMOx8z6bg4U68')## Loading required package: httr## Downloading user profile...## Downloading user tweets...## Downloading user mentions...## Checking Botometer scores...results$scores## $english
## [1] 0.1684732
##
## $universal
## [1] 0.2837825results$categories## $content
## [1] 0.3181609
##
## $friend
## [1] 0.2837789
##
## $network
## [1] 0.1848488
##
## $sentiment
## [1] 0.4279485
##
## $temporal
## [1] 0.09392178
##
## $user
## [1] 0.1183601results <- botometer("realDonaldTrump", my_oauth,
mashape_key = 'Ujq7AAd3igmshqCBvI1LWbz0J8Hlp1hvVOYjsnMOx8z6bg4U68')## Downloading user profile...## Downloading user tweets...## Downloading user mentions...## Checking Botometer scores...results$scores## $english
## [1] 0.0254716
##
## $universal
## [1] 0.04447883results$categories## $content
## [1] 0.05090108
##
## $friend
## [1] 0.1423174
##
## $network
## [1] 0.1041661
##
## $sentiment
## [1] 0.0562195
##
## $temporal
## [1] 0.1172523
##
## $user
## [1] 0.02392906results <- botometer("everyword", my_oauth,
mashape_key = 'Ujq7AAd3igmshqCBvI1LWbz0J8Hlp1hvVOYjsnMOx8z6bg4U68')## Downloading user profile...## Downloading user tweets...## Downloading user mentions...## Checking Botometer scores...results$scores## $english
## [1] 0.1937495
##
## $universal
## [1] 0.08899516results$categories## $content
## [1] 0.1584955
##
## $friend
## [1] 0.2095719
##
## $network
## [1] 0.3196932
##
## $sentiment
## [1] 0.3957022
##
## $temporal
## [1] 0.3848495
##
## $user
## [1] 0.06275738results <- botometer("Horse_3books", my_oauth,
mashape_key = 'Ujq7AAd3igmshqCBvI1LWbz0J8Hlp1hvVOYjsnMOx8z6bg4U68')## Downloading user profile...## Downloading user tweets...## Downloading user mentions...## Checking Botometer scores...results$scores## $english
## [1] 0.5274968
##
## $universal
## [1] 0.05624491results$categories## $content
## [1] 0.8429447
##
## $friend
## [1] 0.8960434
##
## $network
## [1] 0.8997174
##
## $sentiment
## [1] 0.6087972
##
## $temporal
## [1] 0.8287204
##
## $user
## [1] 0.04684971Now time for another challenge!