The rtweet package makes it easy to scrape twitter. You fird need a twitter account and your access tokens (see instructions in the following link).
Additional example code from the vignette for more example code.
library(rtweet)
library(tidyverse)consumer_key <- "YYYYYYYYYYY"
consumer_secret <- "XXXXXXXXXXXX"
appname <- 'stor390'
twitter_token <- create_token(app = appname,
consumer_key = consumer_key,
consumer_secret = consumer_secret)search_results <- search_tweets("data science")## Searching for tweets...## Finished collecting tweets!## # A tibble: 100 × 35
## screen_name user_id created_at status_id
## <chr> <chr> <dttm> <chr>
## 1 JasMRussell 414848069 2017-04-04 20:13:00 849354132586733569
## 2 predartbot 3369695584 2017-04-04 20:12:58 849354124068098050
## 3 jomcinerney 22478416 2017-04-04 20:12:41 849354055986139139
## 4 cpaynejr1 126676393 2017-04-04 20:12:41 849354055864520704
## 5 GmbakerNC 634571080 2017-04-04 20:12:19 849353961425567745
## 6 alevergara78 104520454 2017-04-04 20:12:11 849353928290562049
## 7 EGKBJames 3429712161 2017-04-04 20:11:43 849353810749345793
## 8 stephen_oman 84029229 2017-04-04 20:11:41 849353803648421890
## 9 astorino_steven 2176745083 2017-04-04 20:11:36 849353783809363969
## 10 IoTBlogs 1141258524 2017-04-04 20:11:23 849353725776994305
## # ... with 90 more rows, and 31 more variables: text <chr>,
## # retweet_count <int>, favorite_count <int>, is_quote_status <lgl>,
## # quote_status_id <chr>, is_retweet <lgl>, retweet_status_id <chr>,
## # in_reply_to_status_status_id <chr>, in_reply_to_status_user_id <chr>,
## # in_reply_to_status_screen_name <chr>, lang <chr>, source <chr>,
## # media_id <chr>, media_url <chr>, media_url_expanded <chr>, urls <chr>,
## # urls_display <chr>, urls_expanded <chr>, mentions_screen_name <chr>,
## # mentions_user_id <chr>, symbols <chr>, hashtags <chr>,
## # coordinates <chr>, place_id <chr>, place_type <chr>, place_name <chr>,
## # place_full_name <chr>, country_code <chr>, country <chr>,
## # bounding_box_coordinates <chr>, bounding_box_type <chr>search_results$text[1]## [1] "RT @monicatdata: Art Technologies: @ArthenaArt uses data science to find the best investments in art: https://t.co/JOZjloDrLL https://t.co/…"timelime <- get_timeline("UNC_Basketball")## # A tibble: 200 × 35
## screen_name user_id created_at status_id
## <chr> <chr> <dttm> <chr>
## 1 UNC_Basketball 45575375 2017-04-04 17:40:48 849315833503502337
## 2 UNC_Basketball 45575375 2017-04-04 16:36:24 849299625127313408
## 3 UNC_Basketball 45575375 2017-04-04 16:12:11 849293532804206592
## 4 UNC_Basketball 45575375 2017-04-04 15:01:01 849275621473607680
## 5 UNC_Basketball 45575375 2017-04-04 14:19:01 849265052116963328
## 6 UNC_Basketball 45575375 2017-04-04 13:47:01 849256996389871616
## 7 UNC_Basketball 45575375 2017-04-04 13:27:01 849251965267656704
## 8 UNC_Basketball 45575375 2017-04-04 13:05:12 849246473573236738
## 9 UNC_Basketball 45575375 2017-04-04 12:00:20 849230152496279553
## 10 UNC_Basketball 45575375 2017-04-04 08:20:59 849174948052516865
## # ... with 190 more rows, and 31 more variables: text <chr>,
## # retweet_count <int>, favorite_count <int>, is_quote_status <lgl>,
## # quote_status_id <chr>, is_retweet <lgl>, retweet_status_id <chr>,
## # in_reply_to_status_status_id <chr>, in_reply_to_status_user_id <chr>,
## # in_reply_to_status_screen_name <chr>, lang <chr>, source <chr>,
## # media_id <chr>, media_url <chr>, media_url_expanded <chr>, urls <chr>,
## # urls_display <chr>, urls_expanded <chr>, mentions_screen_name <chr>,
## # mentions_user_id <chr>, symbols <lgl>, hashtags <chr>,
## # coordinates <lgl>, place_id <lgl>, place_type <lgl>, place_name <lgl>,
## # place_full_name <lgl>, country_code <lgl>, country <lgl>,
## # bounding_box_coordinates <lgl>, bounding_box_type <lgl># last five tweets
timelime$text[1:5]## [1] "See you soon Chapel Hill!\n\n#GetIntoIt https://t.co/pqWkHBVPpF"
## [2] "That happened. \n#GetIntoIt https://t.co/dAmpPCULyn"
## [3] "RT @UNC_Basketball: THIS IS CAROLINA BASKETBALL!\n\nNATIONAL CHAMPIONS!\n\n#GetIntoIt\n#OneShiningMoment https://t.co/PUMfEdFYBM"
## [4] "Carolina captured its sixth NCAA championship last night in Phoenix. #GetIntoIt https://t.co/TM50LlZTdG"
## [5] "Lucas: Lucky Us https://t.co/bso8J9VZzy #GetIntoIt https://t.co/X6UWUHsh0G"user <- lookup_users('UNC_basketball')## # A tibble: 1 × 36
## user_id name screen_name location
## <chr> <chr> <chr> <chr>
## 1 45575375 Carolina Basketball UNC_Basketball Chapel Hill, N.C.
## # ... with 32 more variables: description <chr>, protected <lgl>,
## # followers_count <int>, friends_count <int>, listed_count <int>,
## # created_at <dttm>, favourites_count <int>, utc_offset <int>,
## # time_zone <chr>, geo_enabled <lgl>, verified <lgl>,
## # statuses_count <int>, lang <chr>, contributors_enabled <lgl>,
## # is_translator <lgl>, is_translation_enabled <lgl>,
## # profile_background_color <chr>, profile_background_image_url <chr>,
## # profile_background_image_url_https <chr>,
## # profile_background_tile <lgl>, profile_image_url <chr>,
## # profile_image_url_https <chr>, profile_image_url.1 <chr>,
## # profile_image_url_https.1 <chr>, profile_link_color <chr>,
## # profile_sidebar_border_color <chr>, profile_sidebar_fill_color <chr>,
## # profile_text_color <chr>, profile_use_background_image <lgl>,
## # default_profile <lgl>, default_profile_image <lgl>,
## # profile_banner_url <chr>trends <- get_trends()## # A tibble: 50 × 9
## trend
## * <chr>
## 1 #LeGrandDebat
## 2 #EqualPayDay
## 3 José Mayer
## 4 #لماذا_المراه_السعوديه_مستهدفه
## 5 #RomaLazio
## 6 #MUNEVE
## 7 Syria
## 8 Acre
## 9 Tony Romo
## 10 Ramón Espinar
## # ... with 40 more rows, and 8 more variables: url <chr>,
## # promoted_content <lgl>, query <chr>, tweet_volume <int>, as_of <dttm>,
## # created_at <dttm>, place <fctr>, woeid <int>