Web_Scraping/iteration.R at main · BehData/Web_Scraping · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70

nombres <- c("jorge","jacky","elias","daniel","nikol","oscar")

for(i in nombres){
  saludo <- paste0("Hola ", i, "!")
  print(saludo)
}


#-----------------------------------------------

df <- data.frame()

for(i in nombres){
  saludo <- paste0("Hola ", i, "!")
  df <- rbind(df, saludo)
}


#----------------------------------------------

for(año in seq(from = 2016, to = 2022, by = 2)){
  mensaje <- paste("El", año, "fue el mejor año")
  print(mensaje)
}

#----------------------------------------------

library(rvest)      # HTML Hacking & Web Scraping
library(tidyverse)  # Data Manipulation

# Guardar URL -------------------------------------------------------------
url <- "https://repositorioacademico.upc.edu.pe/handle/10757/621444/recent-submissions"

# Leer HTML ---------------------------------------------------------------
page <- read_html(url)
page

titulo <- page %>% html_nodes(".list-title-clamper") %>% html_text()
titulo


#Loop para 3 páginas
for (page_result in seq(from = 0, to = 40, by = 20)) {
  link <- paste0("https://repositorioacademico.upc.edu.pe/handle/10757/621444/recent-submissions?offset=",
                page_result)
  print(link)
}


#-------------------------------------------------------

df <- data.frame()

#Loop para 3 páginas
for (page_result in seq(from = 0, to = 40, by = 20)) {
  link <- paste0("https://repositorioacademico.upc.edu.pe/handle/10757/621444/recent-submissions?offset=",
                 page_result)

  page <- read_html(link)

  titulo <- page %>% html_nodes(".list-title-clamper") %>% html_text()

  df <- rbind(df,  data.frame(titulo))

  print(paste("Página:",(page_result/20)+1))

}