rvest

ryo

> library(rvest)
> library(pipeR)
> lnk <- 'http://www.sbobetonline.com/euro/football'
> lnk %>>% html_session %>% .$response %>% .$headers
> lnk %>>% html_session %>% .$response %>% .$cookies
> web <- lnk %>>% html_session
user <- lnk %>>% html_session %>>% html_node(xpath='//*[@id="username"]') %>>% set_values(., 'username'="xxxxxxx") #用户名 xxxxxxx
pass <- lnk %>>% html_session %>>% html_node(xpath='//*[@id="username"]') %>>% set_values(., 'password'="xxxxxxx") #密码 xxxxxxx
submit_form(web, user, pass)

#'@ domain=.sbobetonline.com
#'@ ASP.NET_SessionId=jx0jswds3w3jsoo0awxc4kyd
#'@ lnk2 %>>% getURL(., cookies='jx0jswds3w3jsoo0awxc4kyd; domain=.sbobetonline.com')
#'@ getURL(lnk2, cookie='jx0jswds3w3jsoo0awxc4kyd; domain=.sbobetonline.com')

怎么登入网站账户?
http://stackoverflow.com/questions/27631460/how-can-i-post-a-simple-html-form-in-r

ryo

> suppressMessages(library(rvest))
> suppressMessages(library(pipeR))
> 
> iSport <- 'http://ibet2.ascbet.com/IBET/Main.aspx'
> sbo <- 'http://www.longmirror.com/euro/football'
> sess <- html_session('http://myr.ibet.uk.com/General/NoneLogin/MainPage/')
> sess %>>% html_form
[[1]]
<form> '<unnamed>' (GET server-side-script.php)
  <select> 'country-options' [1/2]
  <input submit> '': Select

[[2]]
<form> 'loginform' (POST /General/NoneLogin/Login)
  <input text> 'UserName': 
  <input password> 'Password': 
  <input text> 'CaptchaValue': 
  <input hidden> 'MvcCaptchaHiddenInputId': Q1JJb1ZqdytNMWc2T3lSWk5XTXFHVndNQmpvaUtYOEtmMkE3R2dNaFBGb2lDeVV1T3djbE5VQW1CdzUrRVhSWkJ4b05KU3NnS0MwdUJCZ3FPbkkrU1dZSEFEUjZCUVIwY3hkVkdsb01aQjE1S2pjQk0yQnlSUT09

> CapVal <- sess %>>% html_form %>% .[[2]] %>% .$fields %>% .$MvcCaptchaHiddenInputId %>% .$value
> form <- sess %>>% html_form %>% .[[2]] %>>% set_values('UserName'='xxxxxxx', 'Password'='xxxxxxx', 'CaptchaValue'=CapVal)
> form
<form> 'loginform' (POST /General/NoneLogin/Login)
  <input text> 'UserName': xxxxxxx
  <input password> 'Password': ********
  <input text> 'CaptchaValue': Q1JJb1ZqdytNMWc2T3lSWk5XTXFHVndNQmpvaUtYOEtmMkE3R2dNaFBGb2lDeVV1T3djbE5VQW1CdzUrRVhSWkJ4b05KU3NnS0MwdUJCZ3FPbkkrU1dZSEFEUjZCUVIwY3hkVkdsb01aQjE1S2pjQk0yQnlSUT09
  <input hidden> 'MvcCaptchaHiddenInputId': Q1JJb1ZqdytNMWc2T3lSWk5XTXFHVndNQmpvaUtYOEtmMkE3R2dNaFBGb2lDeVV1T3djbE5VQW1CdzUrRVhSWkJ4b05KU3NnS0MwdUJCZ3FPbkkrU1dZSEFEUjZCUVIwY3hkVkdsb01aQjE1S2pjQk0yQnlSUT09
> iBET <- sess %>>% submit_form(form)
Error in names(submits)[[1]] : subscript out of bounds
> rm(CapVal)

Captcha方面遇到问题，请问如何解决呢？