刚刚在Hadley的杰出webinar上了解了NSURL *baseURL = [NSURL URLWithString:urlString];
AFOAuth2Manager *oAuthManager = [[AFOAuth2Manager alloc] initWithBaseURL:baseURL
clientID: keyClientID
secret:keyClientSecret];
[oAuthManager authenticateUsingOAuthWithURLString:@"/oauth/token"
username:myUserName
password:myPassword
scope:@"email"
success:^(AFOAuthCredential *credential) {
NSLog(@"Token: %@",credential.accessToken);
} failure:^(NSError *error) {
NSLog(@"Error: %@", error);
}];
//Authorizing requests
AFHTTPRequestOperationManager *manager = [[AFHTTPRequestOperationManager alloc] initWithBaseURL:baseURL];
[manager.requestSerializer setAuthorizationHeaderFieldWithUsername:keyClientID password:keyClientSecret];
[manager GET:@"/path/to/protected/resource"
parameters:nil
success:^(AFHTTPRequestOperation *operation, id responseObject) {
NSLog(@"Succes: %@", responseObject);
} failure:^(AFHTTPRequestOperation *operation, NSError *error) {
NSLog(@"Failure: %@", error);
}];
//storing credentials
AFOAuthCredential *credential = [[AFOAuthCredential alloc] init];
[AFOAuthCredential storeCredential: credential withIdentifier:serviceProviderIdentifier];
//retrieving credentials
AFOAuthCredential *storedCredential = [AFOAuthCredential retrieveCredentialWithIdentifier:serviceProviderIdentifier];
NSLog(@"%@", storedCredential);
,并且第一次尝试了它。
我想抓取(然后绘制)从Google搜索结果返回的棒球排名表。
我的问题是我无法进入我在浏览器插件中看到的表rvest
。
rvest
此搜索应返回一个页面,其中的表格位于多个图层下,但由library(rvest)
library(magrittr) # for %>% operator
( g_search <-html_session(url = "http://www.google.com/?q=mlb+standings",
add_headers("user-agent" = "Mozilla/5.0")) )
# <session> http://www.google.com/?q=mlb+standings
# Status: 200
# Type: text/html; charset=UTF-8
# Size: 52500
唯一标识。快速停在CSS Diner教我(我认为)&#34; div.tb_strip&#34;是一个有效的CSS选择器来捕获此表(可能还有其他垃圾)。事实上,使用Firebug的CSS选择器,我看到了完整的路径:
<div class="tb_strip">
但是,由于# Use Firebug "Copy CSS Path" and paste into table_path
table_path <- "html body#gsr.srp.tbo.vasq div#main div#cnt.big div.mw div#rcnt div.col div#center_col div#res.med div#search div div#ires ol#rso li.g.tpo.knavi.obcontainer div.kp-blk div#uid_0.r-iCGI_bFBahQE.xpdbox.xpdopen div div.lr_container.mod div#lr_tab_unit_uid_1.tb_u.r-igQv_rxlT08k div.tb_view div.tb_strip"
返回空列表,以下尝试访问此表失败。
html_nodes
内容似乎没有进入g_search,所以我还不知道CSS选择器是否有效。
( standings <- g_search %>%
html_nodes("div.tb_strip") %>%
html_table()
) #returns empty list
它去了哪里?
TYVM
答案 0 :(得分:2)
这是一个更容易的网站的例子......
library("rvest")
url <- "http://sports.yahoo.com/mlb/standings/"
html(url) %>% html_nodes(".yui3-tabview-content") %>% html_nodes("table") %>%html_table