Question

我想抓一下Vancouver olympic games维基百科条目。不幸的是它不是一个很好的表格式。

我正在尝试创建一个包含2列的数据框：Nation和number of athletes。

此时我有

library(XML)
library(RCurl)

path<-"https://fr.wikipedia.org/wiki/Jeux_olympiques_d%27hiver_de_2010"
webpage <- getURL(path)
webpage <- readLines(tc <- textConnection(webpage)); close(tc)

pagetree <- htmlTreeParse(webpage, error=function(...){}, useInternalNodes = TRUE)

# Extract table header and contents
tablehead <- xpathSApply(pagetree, "//*/table/tr", xmlValue)
country<-tablehead[31]

国家/地区

> country
[1] "\n Afrique du Sud (2)\n Albanie (1)\n Algérie (1)\n Allemagne (153)\n Andorre (6)\n Argentine (7)\n Arménie (4)\n Australie (41)\n Autriche (82)\n Azerbaïdjan (2)\n Belgique (8)\n Bermudes (1)\n Biélorussie (50)\n Bosnie-Herzégovine (5)\n Brésil (5)\n Bulgarie (18)\n Canada (206)\n Chili (3)\n Chine (90)\n Chypre (2)\n Colombie (1)\n\n\n\n Corée du Nord (2)\n Corée du Sud (46)\n Croatie (18)\n Danemark (18)\n Espagne (18)\n Estonie (32)\n États-Unis (216)\n Éthiopie (1)\n Finlande (95)\n France (108)\n Géorgie (12)\n Ghana (1)\n Grande-Bretagne (52)\n Grèce (7)\n Hong Kong (1)\n Hongrie (16)\n Îles Caïmans (1)\n Inde (3)\n Iran (4)\n Irlande (6)\n Islande (4)\n\n\n\n Israël (3)\n Italie (109)\n Jamaïque (1)\n Japon (94)\n Kazakhstan (38)\n Kirghizistan (2)\n Lettonie (54)\n Liban (3)\n Liechtenstein (6)\n Lituanie (6)\n Macédoine (3)\n Moldavie (8)\n Maroc (1)\n Mexique (1)\n Monaco (3)\n Monténégro (1)\n Mongolie (2)\n Népal (1)\n Norvège (99)\n Nouvelle-Zélande (16)\n\n\n\n Ouzbékistan (3)\n Pakistan (1)\n Pays-Bas (34)\n Pérou (3)\n Pologne (50)\n Portugal (1)\n République tchèque (93)\n Roumanie (29)\n Russie (179)\n Saint-Marin (1)\n Sénégal (1)\n Serbie (10)\n Slovaquie (73)\n Slovénie (49)\n Suède (108)\n Suisse (146)\n Tadjikistan (1)\n Taipei chinois (1)\n Turquie (5)\n Ukraine (47)\n\n"

我试过了

str_detect(country,"\n")
country<-str_split(country,"\n")

但数据非常脏，而且效果不佳。有什么建议吗？

Answer 1

可能是使用正则表达式。我从来没有用R做过，但似乎建议使用库stringr： Extract a regular expression match in R version 2.10（http://cran.r-project.org/web/packages/stringr/stringr.pdf）

编辑：似乎对我有用的代码

library(XML)
library(RCurl)
options(RCurlOptions = list(cainfo = system.file("CurlSSL", "cacert.pem", package = "RCurl")))
library(stringr)

path<-"https://fr.wikipedia.org/wiki/Jeux_olympiques_d%27hiver_de_2010"
webpage <- getURL(path)
webpage <- readLines(tc <- textConnection(webpage)); close(tc)

pagetree <- htmlTreeParse(webpage, error=function(...){}, useInternalNodes = TRUE, encoding = "UTF-8")
# Extract table header and contents
tablehead <- xpathSApply(pagetree, "//*/table/tr", xmlValue)
country<-tablehead[31]

country<-strsplit(country,"\n")

# extract country
bar <- function(x) str_trim(str_extract(x, "[^(]*"), side = "both")
res1 <- sapply(country[[1]], bar)    
# extract nb of athletes
foo <- function(x) str_trim(str_match(x, "\\((.*?)\\)")[[2]], side = "both")
res2 <- sapply(country[[1]], foo)
# build df
res2 <- as.numeric(res2)
df <- data.frame(res1, res2)
df <- df[res1 != "",]
# inspect df
nrow(df)
summary(df)

Answer 2

尝试

library(plyr)
country <- str_split(country,"\n")[[1]]
df <- ldply(country[[1]], function(z) data.frame(str_extract(z, "[A-Za-z]+")[[1]], str_extract(z, "[0-9]+")))
head(na.omit(df))

                                  a                        b
2                           Afrique                        2
3                           Albanie                        1
4                               Alg                        1
5                         Allemagne                      153
6                           Andorre                        6
7                         Argentine                        7

使用R刮取维基百科以制作列表和数据框

2 个答案: