crawling_ex

---

library(stringr)

## Warning: package 'stringr' was built under R version 3.4.4

library(xml2)

## Warning: package 'xml2' was built under R version 3.4.4

library(purrr)

## Warning: package 'purrr' was built under R version 3.4.4

---

temp_list = vector("list", 42) #42개 list 설정 

t1 <- Sys.time()

#페이지 for문이 안 먹힘 (추후 확인)
for(pageNum in 0:1) { 
  url = paste0('https://onlinelibrary.wiley.com/action/doSearch?AllField=network&startPage=', pageNum)
  temp_html <- read_html(url)
  temp_title <- xml_find_all(temp_html, xpath = ".//span[@class='hlFld-Title']") %>% xml_text()
  temp_title <- temp_title %>% str_remove_all(., "\\\n") %>% str_trim() %>% str_squish()
  temp_list[[pageNum+1L]] <- temp_title
}
my_title <- flatten(temp_list) %>% unlist()
t2 <- Sys.time()
t2 - t1           # 걸리는 시간 

## Time difference of 6.910374 secs

length(my_title)

## [1] 40

head(my_title)

## [1] "My Networking Is Not Working! Conceptualizing the Latent and Dysfunctional Dimensions of the Network Paradigm"
## [2] "Remote network management for optical networks"                                                               
## [3] "Advanced optical networking<U+2014>Lucent's MONET network elements"                                           
## [4] "Civil Society Networks: Options for Network Design"                                                           
## [5] "Introduction to Network Routing"                                                                              
## [6] "Network"