提取字符之间的字符串

Question

这是我的子字符串

> substring(reut2.000[4,], regexpr(">",reut2.000[3,]) + 1)
[1] "<D>el-salvador</D><D>usa</D><D>uruguay</D></PLACES>"

我想提取<D> 和</D> 之间的所有字符。
在这种情况下，输出将是

"el-salvador","use","uruguay"

到目前为止我已经尝试过

gsub(".*<D>\\s*|</D>.*", "", tmp)

其中tmp 是子字符串，它返回"uruguay"。

如何修改它以返回所有位置？

Answer 1

您有一个XML file（tmparallel 包中的示例文件，并且有many places in that package that have code that works with it。

使用 XML as XML。 不要对其进行正则表达式。

以下 sn-p 中的xdf$places 有您要查找的内容，但由于这可能是文本挖掘课程中使用的文件，您最终可能需要将所有其他位提取到数据帧中。

  library(xml2)
  library(tidyverse)

  download.file(
    "https://raw.githubusercontent.com/noahhl/tmparallel/master/pkg/inst/texts/reuters-21578.xml",
    "~/Data/reuters-21578.xml"
  )

  reut <- read_xml("~/Data/reuters-21578.xml")

  xml_find_all(reut, "//REUTERS") %>%
    map_df(~{

      xml_attrs(.x) %>%
        as.list() %>%
        as_data_frame() -> xdf

      xdf$date <- xml_find_first(.x, ".//DATE") %>% xml_text(trim=TRUE)

      #### NOTE THAT THIS FOLLOWING LINE IS THE DATA YOU ASKED FOR IN THE EXAMPLE

      xdf$places <- list(xml_find_all(.x, ".//PLACES/D") %>% xml_text(trim=TRUE))

      xdf$people <- list(xml_find_all(.x, ".//PEOPLE/D") %>% xml_text(trim=TRUE))

      xdf$orgs <- list(xml_find_all(.x, ".//ORGS/D") %>% xml_text(trim=TRUE))

      xdf$exchanges <- list(xml_find_all(.x, ".//EXCHANGES/D") %>% xml_text(trim=TRUE))

      xdf$companies <- list(xml_find_all(.x, ".//COMPANIES/D") %>% xml_text(trim=TRUE))

      xdf$uknown <- xml_find_first(.x, ".//UNKNOWN") %>% xml_text(trim=TRUE)

      xdf$text_title <- xml_find_first(.x, ".//TEXT/TITLE") %>% xml_text(trim=TRUE)

      xdf$text_dateline <- xml_find_first(.x, ".//TEXT/DATELINE") %>% xml_text(trim=TRUE)

      xdf$text_body <- xml_find_first(.x, ".//TEXT/BODY") %>% xml_text(trim=TRUE)

      xdf

    }) -> text_df

输出：

  text_df
  ## # A tibble: 10 x 15
  ##    TOPICS LEWISSPLIT CGISPLIT  OLDID NEWID date      places  people  orgs 
  ##    <chr>  <chr>      <chr>     <chr> <chr> <chr>     <list>  <list>  <lis>
  ##  1 YES    TRAIN      TRAINING… 5544  1     26-FEB-1… <chr [… <chr [… <chr…
  ##  2 NO     TRAIN      TRAINING… 5545  2     26-FEB-1… <chr [… <chr [… <chr…
  ##  3 NO     TRAIN      TRAINING… 5546  3     26-FEB-1… <chr [… <chr [… <chr…
  ##  4 NO     TRAIN      TRAINING… 5547  4     26-FEB-1… <chr [… <chr [… <chr…
  ##  5 YES    TRAIN      TRAINING… 5548  5     26-FEB-1… <chr [… <chr [… <chr…
  ##  6 YES    TRAIN      TRAINING… 5549  6     26-FEB-1… <chr [… <chr [… <chr…
  ##  7 NO     TRAIN      TRAINING… 5550  7     26-FEB-1… <chr [… <chr [… <chr…
  ##  8 YES    TRAIN      TRAINING… 5551  8     26-FEB-1… <chr [… <chr [… <chr…
  ##  9 YES    TRAIN      TRAINING… 5552  9     26-FEB-1… <chr [… <chr [… <chr…
  ## 10 YES    TRAIN      TRAINING… 5553  10    26-FEB-1… <chr [… <chr [… <chr…
  ## # ... with 6 more variables: exchanges <list>, companies <list>,
  ## #   uknown <chr>, text_title <chr>, text_dateline <chr>, text_body <chr>

  glimpse(text_df)
  ## Observations: 10
  ## Variables: 15
  ## $ TOPICS        <chr> "YES", "NO", "NO", "NO", "YES", "YES", "NO", "YE...
  ## $ LEWISSPLIT    <chr> "TRAIN", "TRAIN", "TRAIN", "TRAIN", "TRAIN", "TR...
  ## $ CGISPLIT      <chr> "TRAINING-SET", "TRAINING-SET", "TRAINING-SET", ...
  ## $ OLDID         <chr> "5544", "5545", "5546", "5547", "5548", "5549", ...
  ## $ NEWID         <chr> "1", "2", "3", "4", "5", "6", "7", "8", "9", "10"
  ## $ date          <chr> "26-FEB-1987 15:01:01.79", "26-FEB-1987 15:02:20...
  ## $ places        <list> [<"el-salvador", "usa", "uruguay">, "usa", "usa...
  ## $ people        <list> [<>, <>, <>, <>, <>, <>, <>, <>, <>, <>]
  ## $ orgs          <list> [<>, <>, <>, <>, <>, <>, <>, <>, <>, <>]
  ## $ exchanges     <list> [<>, <>, <>, <>, <>, <>, <>, <>, <>, <>]
  ## $ companies     <list> [<>, <>, <>, <>, <>, <>, <>, <>, <>, <>]
  ## $ uknown        <chr> "C T\nf0704reute\nu f BC-BAHIA-COCOA-REVIEW   02...
  ## $ text_title    <chr> "BAHIA COCOA REVIEW", "STANDARD OIL <SRD> TO FOR...
  ## $ text_dateline <chr> "SALVADOR, Feb 26 -", "CLEVELAND, Feb 26 -", "HO...
  ## $ text_body     <chr> "Showers continued throughout the week in\nthe B...

  str(head(text_df, 2))
  ## Classes 'tbl_df', 'tbl' and 'data.frame':    2 obs. of  15 variables:
  ##  $ TOPICS       : chr  "YES" "NO"
  ##  $ LEWISSPLIT   : chr  "TRAIN" "TRAIN"
  ##  $ CGISPLIT     : chr  "TRAINING-SET" "TRAINING-SET"
  ##  $ OLDID        : chr  "5544" "5545"
  ##  $ NEWID        : chr  "1" "2"
  ##  $ date         : chr  "26-FEB-1987 15:01:01.79" "26-FEB-1987 15:02:20.00"
  ##  $ places       :List of 2
  ##   ..$ : chr  "el-salvador" "usa" "uruguay"
  ##   ..$ : chr "usa"
  ##  $ people       :List of 2
  ##   ..$ : chr 
  ##   ..$ : chr 
  ##  $ orgs         :List of 2
  ##   ..$ : chr 
  ##   ..$ : chr 
  ##  $ exchanges    :List of 2
  ##   ..$ : chr 
  ##   ..$ : chr 
  ##  $ companies    :List of 2
  ##   ..$ : chr 
  ##   ..$ : chr 
  ##  $ uknown       : chr  "C T\nf0704reute\nu f BC-BAHIA-COCOA-REVIEW   02-26 0105" "F Y\nf0708reute\nd f BC-STANDARD-OIL-<SRD>-TO   02-26 0082"
  ##  $ text_title   : chr  "BAHIA COCOA REVIEW" "STANDARD OIL <SRD> TO FORM FINANCIAL UNIT"
  ##  $ text_dateline: chr  "SALVADOR, Feb 26 -" "CLEVELAND, Feb 26 -"
  ##  $ text_body    : chr  "Showers continued throughout the week in\nthe Bahia cocoa zone, alleviating the drought since early\nJanuary an"| __truncated__ "Standard Oil Co and BP North America\nInc said they plan to form a venture to manage the money market\nborrowin"| __truncated__

Answer 2

这是一种使用grepexpr 和regmatches 来捕获文本中所有匹配项的选项：

input <- c("<D>el-salvador</D><D>usa</D><D>uruguay</D></PLACES>")
m <- gregexpr("(?<=<D>).*?(?=</D>)", input, perl=TRUE)
regmatches(input, m)[[1]]

[1] "el-salvador" "usa"         "uruguay"

Demo

请注意，通常不建议使用正则表达式来解析 HTML/XML 或类似内容。原因之一是可能存在嵌套标签，导致简单的正则表达式中断。

Answer 3

使用 gsub 的另一个选项：

temp <- "<D>el-salvador</D><D>usa</D><D>uruguay</D></PLACES>"

temp <- unlist(strsplit(gsub("<D>|</D>|</PLACES>", " ", x = temp ), split = " "))
temp <- temp[temp != ""]