Question

我有3个不同的文本文件，它们的名称为txt1 txt2 txt3：

txt1 <- read_html("https://tr.wikisource.org/wiki/Recep_Tayyip_Erdo%C4%9Fan%27%C4%B1n_1_Haziran_2010_tarihli_AK_Parti_grup_toplant%C4%B1s%C4%B1_konu%C5%9Fmas%C4%B1")  
txt2 <- read_html("https://tr.wikisource.org/wiki/Recep_Tayyip_Erdo%C4%9Fan%27%C4%B1n_1_Haziran_2011_tarihli_Diyarbak%C4%B1r_mitinginde_yapt%C4%B1%C4%9F%C4%B1_konu%C5%9Fma")  
txt3 <- read_html("https://tr.wikisource.org/wiki/Recep_Tayyip_Erdo%C4%9Fan%27%C4%B1n_1_%C5%9Eubat_2011_tarihli_AK_Parti_grup_toplant%C4%B1s%C4%B1_konu%C5%9Fmas%C4%B1 " )

现在，我正在尝试创建一个唯一的html文本文件来分析所有这些文件，因为它们都是一个文件。知道如何使用不同的html文本文件创建一个唯一的html文本文件吗？

Answer 1

您在正确的道路上，这怎么办？

library(rvest)
library(tidyverse)

txt1 <- read_html("https://tr.wikisource.org/wiki/Recep_Tayyip_Erdo%C4%9Fan%27%C4%B1n_1_Haziran_2010_tarihli_AK_Parti_grup_toplant%C4%B1s%C4%B1_konu%C5%9Fmas%C4%B1")  
txt2 <- read_html("https://tr.wikisource.org/wiki/Recep_Tayyip_Erdo%C4%9Fan%27%C4%B1n_1_Haziran_2011_tarihli_Diyarbak%C4%B1r_mitinginde_yapt%C4%B1%C4%9F%C4%B1_konu%C5%9Fma")  
txt3 <- read_html("https://tr.wikisource.org/wiki/Recep_Tayyip_Erdo%C4%9Fan%27%C4%B1n_1_%C5%9Eubat_2011_tarihli_AK_Parti_grup_toplant%C4%B1s%C4%B1_konu%C5%9Fmas%C4%B1 " )

# first link
 df1<- txt1 %>%
    html_nodes('#mw-content-text p') %>%  #choose the text
    html_text() %>%                       
    t() %>%                               # transpose
    data.frame() %>%                      # as data.frame
    unite()                               # melt all the cell in one text

第二个和第三个链接也是如此：

 df2<- txt2 %>%
   html_nodes('#mw-content-text p') %>%
   html_text() %>% t() %>% data.frame() %>%unite()

 df3<- txt3 %>%
   html_nodes('#mw-content-text p') %>%
   html_text() %>% t() %>% data.frame() %>%unite()

最后，例如，将所有内容放到一个单元格中：

 df_total <- cbind(df1,df2,df3) %>% unite()

编辑：

您可以创建一个循环，以解析链接矢量中的所有页面：

txt1 <- ("https://tr.wikisource.org/wiki/Recep_Tayyip_Erdo%C4%9Fan%27%C4%B1n_1_Haziran_2010_tarihli_AK_Parti_grup_toplant%C4%B1s%C4%B1_konu%C5%9Fmas%C4%B1")  
txt2 <- ("https://tr.wikisource.org/wiki/Recep_Tayyip_Erdo%C4%9Fan%27%C4%B1n_1_Haziran_2011_tarihli_Diyarbak%C4%B1r_mitinginde_yapt%C4%B1%C4%9F%C4%B1_konu%C5%9Fma")  
txt3 <- ("https://tr.wikisource.org/wiki/Recep_Tayyip_Erdo%C4%9Fan%27%C4%B1n_1_%C5%9Eubat_2011_tarihli_AK_Parti_grup_toplant%C4%B1s%C4%B1_konu%C5%9Fmas%C4%B1 " )

url <- c(txt1, txt2, txt3)        # all the urls

# the loop that scrapes and put in a list
dfList <- lapply(url, function(i) 
{
  swimwith <- read_html(i)
  swdf <- swimwith %>%
    html_nodes('#mw-content-text p') %>%
    html_text()%>%                       
    t() %>%                              
    data.frame() %>%                      
    unite()     
})

# from list to df
finaldf1 <- do.call(cbind, dfList) %>% unite()

合并html文件进行文本分析

1 个答案: