使用r-我想从网站提取一些表格数据

Question

我在网站上刮擦数据时遇到了一些问题。我在网上剪贴式上没有很多经验。我的预期计划是使用以下网站的R刮擦一些数据： https：//www.fatf---fatf--- gafi.org/countries/

更确切地说，我想提取具有某种制裁的国家列表

library(XML)
  url <- paste0("https://www.fatf-gafi.org/countries/")
  source <- readLines(url, encoding = "UTF-8")
  parsed_doc <- htmlParse(source, encoding = "UTF-8")

，但这不会带来预期的信息，因为不在桌子旁，而是嵌套的Div。

Answer 1

只是为了测试JavaScript评估如何与V8，嵌入式JavaScript和WebAssembly Engine一起使用。

创建上下文引擎，评估请求的JavaScript并从V8中获取 nistry> nistry>变量的值（它已变成嵌套的dataframe，因此 nest（ nest）（ nest）（ ）），最后一行充满了 na s，因此是过滤器。

library(httr)
library(V8)
library(dplyr)
library(tidyr)
url <- paste0('https://www.fatf-gafi.org/media/fatf/fatfv20/',
              'js/country-data-multi-lang.js')
js_content <- content(GET(url), 'text')

ct <- v8()
ct$eval(js_content)
ct$get("countries") %>% 
  unnest(cols = c(groups)) %>%
  select(c(1:2,4:14,16)) %>%
  filter(!is.na(name))

#> # A tibble: 209 × 14
#>    name       code  FATF  APG   CFATF EAG   ESAAMLG GABAC GAFILAT GIABA MENAFATF
#>    <chr>      <chr> <chr> <chr> <chr> <chr> <chr>   <chr> <chr>   <chr> <chr>   
#>  1 Afghanist… AF    ""    "mbr" ""    "obs" ""      ""    ""      ""    ""      
#>  2 Albania    AL    ""    ""    ""    ""    ""      ""    ""      ""    ""      
#>  3 Algeria    DZ    ""    ""    ""    ""    ""      ""    ""      ""    "mbr"   
#>  4 Andorra    AD    ""    ""    ""    ""    ""      ""    ""      ""    ""      
#>  5 Angola     AO    ""    ""    ""    ""    "mbr"   ""    ""      ""    ""      
#>  6 Anguilla   AI    ""    ""    "mbr" ""    ""      ""    ""      ""    ""      
#>  7 Antigua a… AG    ""    ""    "mbr" ""    ""      ""    ""      ""    ""      
#>  8 Argentina  AR    "mbr" "non" "non" "non" "non"   ""    "mbr"   "non" "non"   
#>  9 Armenia    AM    ""    ""    ""    "obs" ""      ""    ""      ""    ""      
#> 10 Aruba Kin… AW    "els" ""    "mbr" ""    ""      ""    ""      ""    ""      
#> # … with 200 more rows, and 3 more variables: MONEYVAL <chr>,
#> #   jurisdiction <chr>, id <chr>

Answer 2

这是一项棘手的解析工作。您需要的信息不在您从 readlines 中获得的HTML中。而是使用XHR请求通过页面动态加载它。通常，像这样的XHR请求会返回JSON字符串，但是在您的情况下，它返回JavaScript，其中将信息存储为一个包含JSON片段的变量，每个国家 /地区一个。可以通过一些字符串操纵和JSON解析来访问这一点，以获得最终结果：

library(httr)
library(rvest)

url <- paste0('https://www.fatf-gafi.org/media/fatf/fatfv20/',
              'js/country-data-multi-lang.js')
js <- content(GET(url), 'text')

vars <- strsplit(js, 'var countries = ')[[1]][2]
vars <- paste0("{", sub("^\\[\\{", "", strsplit(vars, '\\},\\{')[[1]]), "}")
countries <- do.call(rbind, lapply(vars[1:209], 
                      function(x) as.data.frame(jsonlite::parse_json(x))))
countries <- countries[c(1, 4:13)]
names(countries) <- sub('^.*\\.', '', names(countries))

dplyr::tibble(countries)
#> # A tibble: 209 x 11
#>   name     FATF  APG   CFATF EAG   ESAAMLG GABAC GAFILAT GIABA MENAFATF MONEYVAL
#>   <chr>    <chr> <chr> <chr> <chr> <chr>   <chr> <chr>   <chr> <chr>    <chr>   
#> 1 Afghani~ ""    "mbr" ""    "obs" ""      ""    ""      ""    ""       ""      
#> 2 Albania  ""    ""    ""    ""    ""      ""    ""      ""    ""       "mbr"   
#> 3 Algeria  ""    ""    ""    ""    ""      ""    ""      ""    "mbr"    ""      
#> 4 Andorra  ""    ""    ""    ""    ""      ""    ""      ""    ""       "mbr"   
#> 5 Angola   ""    ""    ""    ""    "mbr"   ""    ""      ""    ""       ""      
#> 6 Anguilla ""    ""    "mbr" ""    ""      ""    ""      ""    ""       ""      
#> 7 Antigua~ ""    ""    "mbr" ""    ""      ""    ""      ""    ""       ""      
#> 8 Argenti~ "mbr" "non" "non" "non" "non"   ""    "mbr"   "non" "non"    "non"   
#> 9 Armenia  ""    ""    ""    "obs" ""      ""    ""      ""    ""       "mbr"   
#> 10 Aruba K~ "els" ""    "mbr" ""    ""      ""    ""      ""    ""       ""      
#> # ... with 199 more rows