-1

*编辑：感谢 Martin 和一点时间和精力，我能够在需要的地方获得代码。丑吗？是的，但它的工作方式现在对我有用。有关如何清理它并使其更有效的任何提示都会非常有帮助。

使用数据框trace_list，我试图将值附加Title到Yearfor 循环中每个列表的输出中。以下代码在第 10 页打开每个州的 PDF 链接，提取城市数据（范围为 1-12 个城市）。清理/整理数据，并在收集每个 PDF 的数据后将其存储在要绑定的列表中。现在它只提取城市名称和一个数值。

data.frame(Link = c('https://www.atf.gov/file/146951/download','https://www.atf.gov/file/146966/download','https://www.atf.gov/file/146976/download','https://www.atf.gov/file/137041/download','https://www.atf.gov/file/137231/download','https://www.atf.gov/file/137301/download','https://www.atf.gov/docs/undefined/flwebsite17183911pdf/download','https://www.atf.gov/docs/undefined/kywebsite17183876pdf/download','https://www.atf.gov/docs/undefined/prwebsite17183917pdf/download'), Title = c('Alabama','California','District of Columbia','Alaska','Pennsylvania','Wyoming','Florida','Kentucky','Puerto Rico'), Year = c('2019','2019','2019','2018','2018','2018','2017','2017','2017'))
library(pdftools)
library(dplyr)
library(tabulizer)
library(english)
library(gsubfn)
library(rebus)
library(htmlwidgets)

citytrace <- list()
trace_list <- as.data.frame(trace_list)
for (i in seq_len(nrow(trace_list[c(1:159),]))) {
  pdf_link <- trace_list[i, 1]
  pdf_link <- paste0('',pdf_link,'')
  
  gpi_table <- tabulizer::extract_tables(pdf_link,output = "data.frame",pages = c(10, 10), area = list(c(230,0,280,717), c(275,0,321,725)),guess = F)
  
  city <- list(gpi_table)[[1]][[1]]
  #city <- city[!Reduce(`|`, lapply(city[1], grepl, pattern = '^[0-9]+$""')),]
  city[city==""] <- NA
  city <- setNames(rbind(names(city), city), names(city))
  colnames(city) <- paste("V",seq(1,length(city),1),sep="")
  #city <- ifelse(city[1,]=='city',city[-1,],city)
  city <- if(length(city)>4){
    a <- data.frame(t(city))
    colnames(a) <- paste("X",seq(1,length(a),1),sep="")
    a[,1] <- factor(paste(a$X1,a$X2,a$X3,a$X4, sep = " "))
    a[,1] <- trimws(gsub("X|X\\.[[:digit:]]|\\.[[:digit:]]","",a$X1))
    a <- a[,-c(2:4)]
  } else {
    city %>%
      unite(city, 1:length(city), sep = " ", remove = FALSE) %>%
      mutate_all(na_if,"") %>%
      drop_na() %>%
      mutate(city = trimws(city), city = str_replace(city,"  "," ")) %>%
      select(city)
  }
  city <- ifelse(grepl(c("X|[[:digit:]]"),city),sapply(city, function(x) gsub(c('"*"|[[:digit:]]+|X|,|\\.|^c\\(|\\)$|'),"",x)),sapply(city, function(x) gsub("\\."," ",x)))
  city <- unique(data.frame(matrix(unlist(city), nrow=length(city), byrow=TRUE)))
  city[which(city=="" | city=="NA"),] <- NA
  city <- city[complete.cases(city), , drop=FALSE]
  colnames(city) <- "city"
  
  count <- list(gpi_table)[[1]][[2]]
  count <- setNames(rbind(names(count), count), names(count))
  colnames(count) <- paste("V",seq(1,length(count),1),sep="")
  count <- ifelse(grepl("^X[[:digit:]]+$|^X[[:digit:]]+\\.[[:digit:]]+$",count),sapply(count,function(x) gsub("X|\\.[[:digit:]]$","",x)),count)
  count <- cbind(city,count)
  
  library(english)
  library(gsubfn)
  result <- pdf_text(pdf_link)[10]  %>%
    str_split("\n") %>%
    first() %>%
    as_tibble() %>%
    mutate_all(list(~na_if(.,""))) %>%
    filter(grepl("NOTE:|determined",value))
  x3 <- ifelse(is.na(result[2,]),paste(result[1,], result[2,], sep=". "),paste(result[1,], result[2,], sep=" "))
  x3 <- dplyr::tibble(line = 1, text = x3)
  sv <- strsplit(x3$text, split = "\\. ")
  x3 <- data.frame(V1 = rep(x3$line, sapply(sv, length)), V2 = unlist(sv))
  x3[1,2] <- gsubfn("\\w+", setNames(as.list(1:10), as.english(1:10)), x3[1,2])
  x3[2,2] <- gsubfn("\\w+", setNames(as.list(1:10), as.english(1:10)), x3[2,2])
  x3$V2 <- gsub(",","",x3$V2)
  x3$V2 <- gsub("NA",0,x3$V2)
  x3$city <- ifelse(grepl("additional",x3$V2),"Other","None")
  
  library(rebus)
  library(htmlwidgets)
  trcount <- DGT %R% optional(DGT) %R% optional(DGT) %R% optional(DGT) %R% optional(DGT)
  str_view_all(x3$V2, 
               pattern = trcount)
  a0 <- str_match_all(x3$V2, pattern = trcount)
  a0[[1]] <- a0[[1]][-1,1]
  x3$count <- unlist(a0)
  x4 <- as.data.frame(x3[,-c(1:2)])
  x5 <- rbind(count,x4)
  
  x5 <- x5 %>% 
    mutate(state = trace_list[i, 2],
           year  = trace_list[i, 3]) 
  citytrace[[i]] <- x5
}
citytrace <- do.call(rbind,citytrace)
citytrace$city <- gsub(c(' NA|  '), '', citytrace$city)
citytrace$count <- gsub(c('\\.'), '', citytrace$count)
print(citytrace)

我遇到的麻烦是将'trace_list'中的'Title'和'Year'中的值分配给循环输出。预期结果如下：

城市 数数 状态 年
伯明翰 100 阿拉巴马州 2019
费尔班克斯 10 阿拉斯加州 2018

我不完全确定如何开始这样做，并且正在寻求帮助。非常感谢任何有关如何清理代码的建议。

4

1 回答 1

1

由于我无法在此处运行您的代码，因此对您的代码有一个小建议

library(dplyr)

for (i in seq_len(nrow(trace_list))) {
  pdf_link <- trace_list[i, 1]
  # Do stuff with the URL
  # probably you don't need the inner for-loop
  # create the data.frame x5
  
  x5 %>% 
    mutate(state = trace_list[i, 2],
           year  = trace_list[i, 3]) 
}

一些备注：

  • 我不明白你的for-loop 的定义：迭代list(trace_list[c(1:2),])对我来说没有任何意义。
  • 提取和存储urlinpdf_link最好由pdf_link <- trace_list[i, 1].
  • 迭代对unlist(pdf_link)我来说也没有意义。我认为您可以使用trace_list[i, 1],trace_list[i, 2]或trace_list[i, 3]代替。
于 2021-09-06T18:00:24.903 回答