iOS开发——WKWebView的学习、爬取

1. 前言

当时不知道怎么想的&＃xff0c;想实现把一个网页数据拿下来然后自己组装到app的tableview里面&＃xff0c;后来想法废弃了&＃xff0c;但是这个东西学了部分&＃xff0c;做个记录吧&＃xff0c;所以有了这个文章&＃xff0c;同时&＃xff0c;后续还会补充一下WKWebView的学习。
截止发文&＃xff1a;目标网址的结构没有变化&＃xff0c;我会把我现在爬取的网页结构一起放在demo里面&＃xff0c;供分析用。要不然结构变了&＃xff0c;demo就没用了。

2. 全部代码

demo:点击下载

3. WKWebView

3.1 引库

#import
&＃64;property (nonatomic, strong) WKWebView *webView;


3.2 网页简单加载

就拿微博说事吧

self.webView&＃61; [[WKWebView alloc] initWithFrame:self.view.frame];
self.webView.navigationDelegate &＃61; self;
[self.view addSubview:self.webView];
[self.webView loadRequest:[NSURLRequest requestWithURL:[NSURL URLWithString:&＃64;"https://weibo.com/"]]];


4. WKNavigationDelegate

4.1 方法

&＃64;protocol WKNavigationDelegate <NSObject>//请求之前&＃xff0c;决定是否要跳转:用户点击网页上的链接&＃xff0c;需要打开新页面时&＃xff0c;将先调用这个方法。
- (void)webView:(WKWebView *)webView decidePolicyForNavigationAction:(WKNavigationAction *)navigationAction decisionHandler:(void (^)(WKNavigationActionPolicy))decisionHandler;//接收到相应数据后&＃xff0c;决定是否跳转
- (void)webView:(WKWebView *)webView decidePolicyForNavigationResponse:(WKNavigationResponse *)navigationResponse decisionHandler:(void (^)(WKNavigationResponsePolicy))decisionHandler;//页面开始加载时调用
- (void)webView:(WKWebView *)webView didStartProvisionalNavigation:(null_unspecified WKNavigation *)navigation;// 主机地址被重定向时调用
- (void)webView:(WKWebView *)webView didReceiveServerRedirectForProvisionalNavigation:(null_unspecified WKNavigation *)navigation;// 页面加载失败时调用
- (void)webView:(WKWebView *)webView didFailProvisionalNavigation:(null_unspecified WKNavigation *)navigation withError:(NSError *)error;// 当内容开始返回时调用
- (void)webView:(WKWebView *)webView didCommitNavigation:(null_unspecified WKNavigation *)navigation;// 页面加载完毕时调用
- (void)webView:(WKWebView *)webView didFinishNavigation:(null_unspecified WKNavigation *)navigation;//跳转失败时调用
- (void)webView:(WKWebView *)webView didFailNavigation:(null_unspecified WKNavigation *)navigation withError:(NSError *)error;// 如果需要证书验证&＃xff0c;与使用AFN进行HTTPS证书验证是一样的
- (void)webView:(WKWebView *)webView didReceiveAuthenticationChallenge:(NSURLAuthenticationChallenge *)challenge completionHandler:(void (^)(NSURLSessionAuthChallengeDisposition disposition, NSURLCredential * _Nullable credential))completionHandler;//9.0才能使用&＃xff0c;web内容处理中断时会触发
- (void)webViewWebContentProcessDidTerminate:(WKWebView *)webView API_AVAILABLE(macosx(10.11), ios(9.0));
&＃64;end


4.2 本文主要用的

- (void)webView:(WKWebView *)webView didFinishNavigation:(null_unspecified WKNavigation *)navigation {[self.webView evaluateJavascript:&＃64;"document.body.innerHTML" completionHandler:^(id _Nullable result, NSError * _Nullable error) {NSLog(&＃64;"网页抓取结果:%&＃64;", result);[self writeToFileWithTxt:result];}];NSString *titleSrcString &＃61; [NSString stringWithFormat:&＃64;"document.getElementsByClassName(&＃39;weibo-text&＃39;)[0].getElementsByTagName(&＃39;a&＃39;)[0].href"];[self.webView evaluateJavascript:titleSrcString completionHandler:^(id _Nullable result, NSError * _Nullable error) {// 超话链接NSLog(&＃64;"标题链接抓取结果:%&＃64;", result);}];NSString *titleString &＃61; [NSString stringWithFormat:&＃64;"document.getElementsByClassName(&＃39;weibo-text&＃39;)[0].textContent"];[self.webView evaluateJavascript:titleString completionHandler:^(id _Nullable result, NSError * _Nullable error) {// 标题NSLog(&＃64;"标题抓取结果:%&＃64;", result);}];NSString *imageSrcString &＃61; [NSString stringWithFormat:&＃64;"document.getElementsByClassName(&＃39;m-img-box&＃39;)[0].getElementsByTagName(&＃39;img&＃39;)[0].src"];[self.webView evaluateJavascript:imageSrcString completionHandler:^(id _Nullable result, NSError * _Nullable error) {// 取一个头像地址NSLog(&＃64;"头像抓取结果:%&＃64;", result);}];NSString *authorString &＃61; [NSString stringWithFormat:&＃64;"document.getElementsByClassName(&＃39;m-text-cut&＃39;)[0].textContent"];[self.webView evaluateJavascript:authorString completionHandler:^(id _Nullable result, NSError * _Nullable error) {// 自媒体名称NSLog(&＃64;"自媒体名称抓取结果:%&＃64;", result);}];}


4.2.1 分析

脚本中要根据当前字段的class与tpye等相关内容去获取&＃xff0c;可以结合demo里面的网页结构来分析。