我花了很长时间使用R来试图刮取NBA数据，到目前为止我通过反复试验做了一点，但最后我找到了documentation。前段时间我在抓取 shotchartdetail 时遇到了一些问题，当我找到this
时我发现了问题为此我就这样做了：
shotURLtotal <- paste0("http://stats.nba.com/stats/shotchartdetail?CFID=33&CFPARAMS=2016-17&ContextFilter=&ContextMeasure=FGA&DateFrom=&DateTo=&GameID=&GameSegment=&LastNGames=0&LeagueID=00&Location=&MeasureType=Base&Month=0&OpponentTeamID=0&Outcome=&PaceAdjust=N&PerMode=PerGame&Period=0&PlayerID=0&PlusMinus=N&Position=&Rank=N&RookieYear=&Season=2016-17&SeasonSegment=&SeasonType=Regular+Season&TeamID=0&VsConference=&VsDivision=&mode=Advanced&showDetails=0&showShots=1&showZones=0&PlayerPosition=")
Season <- rjson::fromJSON(file = shotURLtotal, method="C")
Names <- Season$resultSets[[1]][[2]]
Season <- data.frame(matrix(unlist(Season$resultSets[[1]][[3]]), ncol = length(Names), byrow = TRUE))
colnames(Season) <- Names
但是当我尝试对 shotchartlineupdetail 做同样的事情时，它不起作用，我怀疑它与 CFID 有关，我没有＆＃39不知道这意味着什么，这就是我的尝试。
shoturl <- "http://stats.nba.com/stats/shotchartlineupdetail/?leagueId=00&season=2016-17&seasonType=Regular+Season&teamId=0&outcome=&location=&month=0&seasonSegment=&dateFrom=&dateTo=&opponentTeamId=0&vsConference=&vsDivision=&gameSegment=&period=0&lastNGames=0&gameId=&group_id=0&contextFilter=&contextMeasure=FGA"
Season <- rjson::fromJSON(file = shoturl, method="C")
Names <- Season$resultSets[[1]][[2]]
Season <- data.frame(matrix(unlist(Season$resultSets[[1]][[3]]), ncol = length(Names), byrow = TRUE))
colnames(Season) <- Names
预期结果应该是包含以下列的数据框：
c("GRID_TYPE", "GAME_ID", "GAME_EVENT_ID", "GROUP_ID", "GROUP_NAME", "PLAYER_ID", "PLAYER_NAME", "TEAM_ID", "TEAM_NAME", "PERIOD", "MINUTES_REMAINING", "SECONDS_REMAINING", "EVENT_TYPE", "ACTION_TYPE", "SHOT_TYPE", "SHOT_ZONE_BASIC", "SHOT_ZONE_AREA", "SHOT_ZONE_RANGE", "SHOT_DISTANCE", "LOC_X", "LOC_Y", "SHOT_ATTEMPTED_FLAG", "SHOT_MADE_FLAG", "GAME_DATE", "HTM", "VTM")
你可以这样做：
shoturl <- "http://stats.nba.com/stats/shotchartlineupdetail/?leagueId=00&season=2016-17&seasonType=Regular+Season&teamId=0&outcome=&location=&month=0&seasonSegment=&dateFrom=&dateTo=&opponentTeamId=0&vsConference=&vsDivision=&gameSegment=&period=0&lastNGames=0&gameId=&group_id=0&contextFilter=&contextMeasure=FGA"
Season <- rjson::fromJSON(file = shoturl, method="C")
Names <- Season$resultSets[[1]][[2]]
所以Names将是数据帧的列，问题是不使用 CFID 你得到那些列的数据应该是空的列表，答案是@be_green给出联盟平均值，我需要球队特定数据
答案 0 :(得分：0)
因此，我认为这里的问题是您需要将PlayerID和TeamID传递给API。以下面的PlayerID = 2544和TeamID = 1610612739为例，看来可行：
library(tidyverse)
res <- jsonlite::read_json("https://stats.nba.com/stats/shotchartdetail?AheadBehind=&ClutchTime=&ContextFilter=&ContextMeasure=PTS&DateFrom=&DateTo=&EndPeriod=&EndRange=&GameID=&GameSegment=&LastNGames=0&LeagueID=00&Location=&Month=0&OpponentTeamID=0&Outcome=&Period=0&PlayerID=2544&PlayerPosition=&PointDiff=&Position=&RangeType=&RookieYear=&Season=&SeasonSegment=&SeasonType=Regular+Season&StartPeriod=&StartRange=&TeamID=1610612739&VsConference=&VsDivision=")
# res %>% str(max.level = 3)
header_names <- flatten_chr(res$resultSets[[1]]$headers)
header_names
#> [1] "GRID_TYPE" "GAME_ID" "GAME_EVENT_ID"
#> [4] "PLAYER_ID" "PLAYER_NAME" "TEAM_ID"
#> [7] "TEAM_NAME" "PERIOD" "MINUTES_REMAINING"
#> [10] "SECONDS_REMAINING" "EVENT_TYPE" "ACTION_TYPE"
#> [13] "SHOT_TYPE" "SHOT_ZONE_BASIC" "SHOT_ZONE_AREA"
#> [16] "SHOT_ZONE_RANGE" "SHOT_DISTANCE" "LOC_X"
#> [19] "LOC_Y" "SHOT_ATTEMPTED_FLAG" "SHOT_MADE_FLAG"
#> [22] "GAME_DATE" "HTM" "VTM"
res$resultSets[[1]]$rowSet %>%
map(`[`, 1:24) %>%
map(~ set_names(., header_names)) %>%
bind_rows()
#> # A tibble: 8,369 x 24
#> GRID_TYPE GAME_ID GAME_EVENT_ID PLAYER_ID PLAYER_NAME TEAM_ID TEAM_NAME
#> <chr> <chr> <int> <int> <chr> <int> <chr>
#> 1 Shot Cha~ 002030~ 20 2544 LeBron Jam~ 1.61e9 Clevelan~
#> 2 Shot Cha~ 002030~ 28 2544 LeBron Jam~ 1.61e9 Clevelan~
#> 3 Shot Cha~ 002030~ 35 2544 LeBron Jam~ 1.61e9 Clevelan~
#> 4 Shot Cha~ 002030~ 54 2544 LeBron Jam~ 1.61e9 Clevelan~
#> 5 Shot Cha~ 002030~ 67 2544 LeBron Jam~ 1.61e9 Clevelan~
#> 6 Shot Cha~ 002030~ 76 2544 LeBron Jam~ 1.61e9 Clevelan~
#> 7 Shot Cha~ 002030~ 224 2544 LeBron Jam~ 1.61e9 Clevelan~
#> 8 Shot Cha~ 002030~ 233 2544 LeBron Jam~ 1.61e9 Clevelan~
#> 9 Shot Cha~ 002030~ 235 2544 LeBron Jam~ 1.61e9 Clevelan~
#> 10 Shot Cha~ 002030~ 322 2544 LeBron Jam~ 1.61e9 Clevelan~
#> # ... with 8,359 more rows, and 17 more variables: PERIOD <int>,
#> # MINUTES_REMAINING <int>, SECONDS_REMAINING <int>, EVENT_TYPE <chr>,
#> # ACTION_TYPE <chr>, SHOT_TYPE <chr>, SHOT_ZONE_BASIC <chr>,
#> # SHOT_ZONE_AREA <chr>, SHOT_ZONE_RANGE <chr>, SHOT_DISTANCE <int>,
#> # LOC_X <int>, LOC_Y <int>, SHOT_ATTEMPTED_FLAG <int>,
#> # SHOT_MADE_FLAG <int>, GAME_DATE <chr>, HTM <chr>, VTM <chr>
由reprex package（v0.2.1）于2019-03-26创建