autoPipeSearch: autoPipeSearch function

In kkalininMI/CECscraper: The web scraping tool for the Russian electoral data

Description

This function automatically constructs pipe for a given election.

Usage

autoPipeSearch(
  x,
  ttime = FALSE,
  blocks = NULL,
  search.term = NULL,
  hits = 2,
  extracturls = FALSE,
  breakloop = 100,
  messages = FALSE
)

Arguments

x	url, list of urls.
ttime	checks if data covers reported turnout over election day (TRUE) or not (FALSE). ttime is valid when blocks=NULL
blocks	vector of blocks to be used to construct a pipe. blocks override ttime parameters. By default, c("listURLextractor()", "rowURLextractor('sayt izbiratel‘noy komissii sub'yekta’)", "rowURLextractor('Itogi golosovaniya|Rezul‘taty vyborov’)").
search.term	once the stop "term" is detected the algorithm stops building the pipe (by default, UIK|uik|uchastok).
hits	number of times the stop word is "hit" by the algorithm. Each time the stop word is "hit" extra block is added to the pipe (by default, hits=2).
extracturls	urls are extracted using the pipe or the list of pipes (by default, extracturls=FALSE).
breakloop	maximum number of iterations for optimal path search (by default, breakloop=100).
messages	display progress messages (messages = FALSE).

Value

Returns the list elections and pipe.table objects.

Examples

library(CECscraper)
library(dplyr)
library(rvest)
 webpage <- read_html(system.file("elections_primorye.html", package="CECscraper"))

 #Example 1
 wterrit <- webpage %>% fileURLextractor(hashid = FALSE)
 #uik_url1 <- wterrit[1,]%>%autoPipeSearch(extracturls=TRUE, ttime=FALSE)
 uik_url1 <- wterrit[1,]%>%autoPipeSearch(ttime=TRUE)
 uik_url2 <- uik_url1%>%execPipeList()
 #uik_url3 <- uik_url2%>%dataBuilder(ttime=FALSE)
  uik_url3 <- uik_url2%>%dataBuilder(ttime=TRUE)

 #Example 2
 uik_url1 <- wterrit[1,]%>%autoPipeSearch(blocks=c("listURLextractor()",
                                                  "rowURLextractor('sayt izbiratel`noy komissii sub`yekta')",
                                                  "rowURLextractor('Svodnaya tablitsa')"),  hits=3, search.term="Svodnaya tablitsa")
 uik_url2 <- uik_url1%>%
            execPipeList()%>%
            dataBuilder(typedata = "fast")

 #Example 3
 uik_url1 <- wterrit[1,]%>%autoPipeSearch(blocks=c("listURLextractor()",
                                                  "rowURLextractor('sayt izbiratel`noy komissii sub`yekta')",
                                                  "rowURLextractor('Dannyye ob otkrytii pomeshcheniy')"),  hits=3, search.term="Dannyye ob otkrytii pomeshcheniy")
 uik_url2 <- uik_url1%>%
            execPipeList()%>%
            dataBuilder(ttime = TRUE, typedata = "fast")

 #Example 4
 uik_url1 <- wterrit[1,]%>%autoPipeSearch(blocks=c("listURLextractor()",
                                               "rowURLextractor('sayt izbiratel`noy komissii sub`yekta')",
                                               "rowURLextractor('Svedeniya o kandidatakh')"),  hits=1, search.term="Svedeniya o kandidatakh")
 uik_url2 <- uik_url1%>%
             execPipeList()%>%
             scrapeCandidates(tabextract = NULL, savetodir = "")

kkalininMI/CECscraper documentation built on Oct. 28, 2020, 1:47 a.m.