0

我需要一个函数来使用该库获取data.frame拥有超过 75000 个关注者（或朋友，超过 Twitter API 限制）的用户的所有关注者（或朋友）ID。rtwitter

我首先尝试了next_cursor文档帮助示例：

# Retrieve user ids of accounts following POTUS
f1 <- get_followers("potus", n = 75000)
page <- next_cursor(f1)

# max. number of ids returned by one token is 75,000 every 15
# minutes, so you'll need to wait a bit before collecting the
# next batch of ids
sys.Sleep(15*60) # Suspend execution of R expressions for 15 mins

# Use the page value returned from \code{next_cursor} to continue
# where you left off.
f2 <- get_followers("potus", n = 75000, page = page)

data.frame但是，考虑到不同用户的不同关注者或朋友数量，我如何才能获得所有关注者（或朋友）ID ？如何管理分页？

4

2 回答 2

1

默认情况下，Github 上 rtweet 开发版中get_followers的函数现在可以使用超过 75k。前几天晚上，我在测试中毫无问题地获得了 300 万特朗普的追随者。要获得超过 75k，请确保设置为 TRUE。retryonratelimit

于 2017-07-25T05:00:31.630 回答
1

经过一些测试，我编写了这个包含进度条并从用户那里获取所有关注者 ID 的递归函数：

# Load library
library('rtweet')

# Global variables:
ids <- 75000 # Max number of ids per token every 15 minutes
f <- list() # Vector where user_ids from followers will be appended

# Function to get all the followers from a user with pagination
GetFollowersRecursivePagination <- function(userId, followers, page) {

  if (ids == 0) {

    # API Twitter Limit reached - Wait
    message("Waiting 15 mins...")
    total <- 15*60 # Total time = 15 min ~ 900 sec
    pb <- txtProgressBar(min = 0, max = total, style = 3) # create progress bar

    for (i in 1:total) {
      Sys.sleep(time = 1) # 1 second interval
      setTxtProgressBar(pb, i) # update progress bar
    }
    close(pb)

    # Check rate limit followers/ids query
    if (!rate_limit(token = NULL)[38,]$reset > 14.9) {
      message("Waiting 15 seconds more...")
      Sys.sleep(time = 15) # wait 15 seconds more...
    }

    message("Go!")
    ids <<- 75000
  }

  if (followers <= ids) {

    message(paste("Followers < ids | Number of Followers: ",
                  followers, " | Number of resting ids: ",  ids, sep = ""))
    ftemp <- get_followers(user = userId, n = followers, page = page)

    if (page == '-1') {
      f <<- append(f, list(ftemp)) # append followers ids
    }

    if (page != '-1') {
      df <- data.frame('user_id' = ftemp)
      f <<- append(f, list(df)) # append followers ids
    }

    ids <<- ids - followers
    message("Finished!")
    rtemp <- f
    f <<- list()
    return(rtemp)

  } else if (followers > ids) {

    message(paste("Followers > ids | Number of Followers: ",
                  followers, " | Number of resting ids: ",  ids, sep = ""))
    ftemp <- get_followers(user = userId, n = ids, page = page)

    if (page == '-1') {
      f <<- append(f, list(ftemp)) # append followers ids
    }

    if (page != '-1') {
      df <- data.frame('user_id' = ftemp)
      f <<- append(f, list(df)) # append followers ids
    }

    n <- ids # n = count of followers ids already acquired

    pageTemp <- next_cursor(ftemp) # Pagination

    # API Twitter Limit reached - Wait
    message("Waiting 15 mins...")
    total <- 15*60 # Total time = 15 min ~ 900 sec
    pb <- txtProgressBar(min = 0, max = total, style = 3) # create progress bar

    for (i in 1:total) {
      Sys.sleep(time = 1) # 1 second interval
      setTxtProgressBar(pb, i) # update progress bar
    }
    close(pb)

    # Check rate limit followers/ids query
    if (!rate_limit(token = NULL)[38,]$reset > 14.9) {
      message("Waiting 15 seconds more...")
      Sys.sleep(time = 15) # wait 15 seconds more...
    }

    message("Go!")
    ids <<- 75000

    # Recursive function call
    GetFollowersRecursivePagination(userId = userId,
                                    followers = followers - n,
                                    page = pageTemp)
  }
}

# Test ( > 75000 followers )
# Get user
user1 <- lookup_users(users = "146620155")
FAOClimate <- GetFollowersRecursivePagination(userId = user1$user_id,
                                              followers = user1$followers_count,
                                              page = '-1')

# Output:
Followers > ids | Number of Followers: 87208 | Number of resting ids:  75000
Followers < ids | Number of Followers: 12208 | Number of resting ids: 62792
Finished!

str(FAOClimate)

List of 2
 $ :'data.frame':   75000 obs. of  1 variable:
  ..$ user_id: chr [1:75000] "87189802" "884863013928546304" "886995444512964608" "852940633652301824" ...
  ..- attr(*, "next_cursor")= num 1.45e+18
 $ :'data.frame':   12207 obs. of  1 variable:
  ..$ user_id: chr [1:12207] "2175314977" "2168898233" "1491745484" "2175065456" ...

注意：如果您想要朋友而不是关注者get_followers，请将功能更改为。get_friends

于 2017-07-17T19:36:46.110 回答