WebScraping

url_base <- "http://search.folha.uol.com.br/search?q=merenda&site=todos&results_count=3769&search_time=0.033&url=http%3A%2F%2Fsearch.folha.uol.com.br%2Fsearch%3Fq%3Dmerenda%26site%3Dtodos&sr="

i <- 1
url_pesquisa <- paste(url_base, i, sep = "")

for (i in 1:151){
  i <- (i - 1) * 25 + 1
  print(i)
}

## [1] 1
## [1] 26
## [1] 51
## [1] 76
## [1] 101
## [1] 126
## [1] 151
## [1] 176
## [1] 201
## [1] 226
## [1] 251
## [1] 276
## [1] 301
## [1] 326
## [1] 351
## [1] 376
## [1] 401
## [1] 426
## [1] 451
## [1] 476
## [1] 501
## [1] 526
## [1] 551
## [1] 576
## [1] 601
## [1] 626
## [1] 651
## [1] 676
## [1] 701
## [1] 726
## [1] 751
## [1] 776
## [1] 801
## [1] 826
## [1] 851
## [1] 876
## [1] 901
## [1] 926
## [1] 951
## [1] 976
## [1] 1001
## [1] 1026
## [1] 1051
## [1] 1076
## [1] 1101
## [1] 1126
## [1] 1151
## [1] 1176
## [1] 1201
## [1] 1226
## [1] 1251
## [1] 1276
## [1] 1301
## [1] 1326
## [1] 1351
## [1] 1376
## [1] 1401
## [1] 1426
## [1] 1451
## [1] 1476
## [1] 1501
## [1] 1526
## [1] 1551
## [1] 1576
## [1] 1601
## [1] 1626
## [1] 1651
## [1] 1676
## [1] 1701
## [1] 1726
## [1] 1751
## [1] 1776
## [1] 1801
## [1] 1826
## [1] 1851
## [1] 1876
## [1] 1901
## [1] 1926
## [1] 1951
## [1] 1976
## [1] 2001
## [1] 2026
## [1] 2051
## [1] 2076
## [1] 2101
## [1] 2126
## [1] 2151
## [1] 2176
## [1] 2201
## [1] 2226
## [1] 2251
## [1] 2276
## [1] 2301
## [1] 2326
## [1] 2351
## [1] 2376
## [1] 2401
## [1] 2426
## [1] 2451
## [1] 2476
## [1] 2501
## [1] 2526
## [1] 2551
## [1] 2576
## [1] 2601
## [1] 2626
## [1] 2651
## [1] 2676
## [1] 2701
## [1] 2726
## [1] 2751
## [1] 2776
## [1] 2801
## [1] 2826
## [1] 2851
## [1] 2876
## [1] 2901
## [1] 2926
## [1] 2951
## [1] 2976
## [1] 3001
## [1] 3026
## [1] 3051
## [1] 3076
## [1] 3101
## [1] 3126
## [1] 3151
## [1] 3176
## [1] 3201
## [1] 3226
## [1] 3251
## [1] 3276
## [1] 3301
## [1] 3326
## [1] 3351
## [1] 3376
## [1] 3401
## [1] 3426
## [1] 3451
## [1] 3476
## [1] 3501
## [1] 3526
## [1] 3551
## [1] 3576
## [1] 3601
## [1] 3626
## [1] 3651
## [1] 3676
## [1] 3701
## [1] 3726
## [1] 3751

library(xml2)
library(rvest)
library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

pagina <- read_html(url_pesquisa)

nodes_titulos <- html_nodes(pagina, xpath = "//ol/li/div/div/a")
titulos <- html_text(nodes_titulos)
links <- html_attr(nodes_titulos, name = "href")
tabela_titulos <- data.frame(titulos, links)

url_base <- "http://search.folha.uol.com.br/search?q=merenda&site=todos&results_count=3769&search_time=0.033&url=http%3A%2F%2Fsearch.folha.uol.com.br%2Fsearch%3Fq%3Dmerenda%26site%3Dtodos&sr="

dados_pesquisa <- data_frame()

for (i in 1:151){
  
  print(i)
  
  i <- (i - 1) * 25 + 1
  
  url_pesquisa <- paste(url_base, i, sep = "")
  
  pagina <- read_html(url_pesquisa)
  
  nodes_titulos <- html_nodes(pagina, xpath = "//ol/li/div/div/a")
  
  titulos <- html_text(nodes_titulos)
  links <- html_attr(nodes_titulos, name = "href")
  
  tabela_titulos <- data.frame(titulos, links)
  
  dados_pesquisa <- bind_rows(dados_pesquisa, tabela_titulos)
}