행위

R 크롤링

DB CAFE

로그인 처리

전반적인 흐름은

  1. 로그인하고 웹 페이지로 이동하여 정보를 수집
  2. 데이터 프레임을 추가 한 다음 다음 페이지로 이동
library(rvest) 

#Address of the login webpage
login<-"https://stackoverflow.com/users/login?ssrc=head&returnurl=http%3a%2f%2fstackoverflow.com%2f"

#create a web session with the desired login address
pgsession<-html_session(login)
pgform<-html_form(pgsession)[[2]]  #in this case the submit is the 2nd form
filled_form<-set_values(pgform, email="*****", password="*****")
submit_form(pgsession, filled_form)

#pre allocate the final results dataframe.
results<-data.frame()  

#loop through all of the pages with the desired info
# 이 경우 루프는 5 페이지로 제한되며 응용 프로그램에 맞게 변경해야합니다. 
for (i in 1:5)
{
  #base address of the pages to extract information from
  url<-"http://stackoverflow.com/users/**********?tab=answers&sort=activity&page="
  url<-paste0(url, i)
  page<-jump_to(pgsession, url)

  #collect info on the question votes and question title
  summary<-html_nodes(page, "div .answer-summary")
  question<-matrix(html_text(html_nodes(summary, "div"), trim=TRUE), ncol=2, byrow = TRUE)

  #find date answered, hyperlink and whether it was accepted
  dateans<-html_node(summary, "span") %>% html_attr("title")
  hyperlink<-html_node(summary, "div a") %>% html_attr("href")
  accepted<-html_node(summary, "div") %>% html_attr("class")

  #create temp results then bind to final results 
  rtemp<-cbind(question, dateans, accepted, hyperlink)
  results<-rbind(results, rtemp)
}

#Dataframe Clean-up
names(results)<-c("Votes", "Answer", "Date", "Accepted", "HyperLink")
results$Votes<-as.integer(as.character(results$Votes))
results$Accepted<-ifelse(results$Accepted=="answer-votes default", 0, 1)