获取网页上数据(图片、文字、视频)-b
Demo地址:http://download.csdn.net/detail/u012881779/8831835
获取网页上所有图片、获取所有html、获取网页title、获取网页内容文字。。。
.h 文件 代码:
//网页
//NSString *strPath = [NSString stringWithFormat:@"http://www.baidu.com/s?wd=%@&cl=3",theWord];
//视频
//NSString *strPath = [NSString stringWithFormat:@"http://www.itinge.com/music/16241.mp4"];
//图片
NSString *strPath = [NSString stringWithFormat:@"http://image.baidu.com/search/index?tn=baiduimage&istype=2&ie=utf-8&word=%@",theWord];
strPath = [strPath stringByAddingPercentEscapesUsingEncoding:NSUTF8StringEncoding];
.m 文件 代码:
@interface ViewController ()<UISearchBarDelegate , UIWebViewDelegate,UIGestureRecognizerDelegate>
@property (weak, nonatomic) IBOutlet UISearchBar *searchBar;
@property (weak, nonatomic) IBOutlet UIWebView *webview;
@end
@implementation ViewController
- (void)viewDidLoad {
[super viewDidLoad];
_searchBar.delegate = self;
_webview.delegate = self;
[self addTapOnWebView];
}
-(void)addTapOnWebView{
UITapGestureRecognizer* singleTap = [[UITapGestureRecognizer alloc] initWithTarget:self action:@selector(handleSingleTap:)];
[_webview addGestureRecognizer:singleTap];
singleTap.delegate = self;
singleTap.cancelsTouchesInView = NO;
}
#pragma mark- TapGestureRecognizer
- (BOOL)gestureRecognizer:(UIGestureRecognizer *)gestureRecognizer shouldRecognizeSimultaneouslyWithGestureRecognizer:(UIGestureRecognizer *)otherGestureRecognizer{
return YES;
}
//被点击位置对应链接
-(void)handleSingleTap:(UITapGestureRecognizer *)sender{
CGPoint pt = [sender locationInView:_webview];
NSString *imgURL = [NSString stringWithFormat:@"document.elementFromPoint(%f, %f).src", pt.x, pt.y];
NSString *urlToSave = [_webview stringByEvaluatingJavaScriptFromString:imgURL];
NSLog(@"image url=%@", urlToSave);
NSString * JsToGetHTMLSource = @"top.location.href";
NSString * pageSource = [_webview stringByEvaluatingJavaScriptFromString:JsToGetHTMLSource];
NSLog(@"\n\n__url=%@", pageSource);
if (urlToSave.length > 4) {
NSString *substr = [urlToSave substringFromIndex:urlToSave.length-3];
if([substr isEqualToString:@"jpg"] || [substr isEqualToString:@"png"]){
[self showImageURL:urlToSave point:pt];
}
}
}
//呈现图片,HTML是否适配分辨率将影响点击资源与获取到得资源是否一致
-(void)showImageURL:(NSString *)url point:(CGPoint)point
{
UIImageView *showView = [[UIImageView alloc] initWithFrame:[[UIScreen mainScreen]bounds]];
showView.center = point;
CGPoint newPoint = self.view.center;
showView.center = newPoint;
showView.backgroundColor = [UIColor blackColor];
showView.alpha = 1;
showView.userInteractionEnabled = YES;
[self.view addSubview:showView];
[showView setContentMode:UIViewContentModeScaleAspectFit];
[showView showImageFromURL:url placeHolder:nil CompletionBlock:nil];
UITapGestureRecognizer* singleTap = [[UITapGestureRecognizer alloc] initWithTarget:self action:@selector(handleSingleViewTap:)];
[showView addGestureRecognizer:singleTap];
[self.navigationController setNavigationBarHidden:YES animated:YES];
}
//移除图片查看视图
-(void)handleSingleViewTap:(UITapGestureRecognizer *)sender
{
for (id obj in self.view.subviews) {
if ([obj isKindOfClass:[UIImageView class]]) {
[obj removeFromSuperview];
}
}
[self.navigationController setNavigationBarHidden:YES animated:YES];
}
- (void)didReceiveMemoryWarning {
[super didReceiveMemoryWarning];
// Dispose of any resources that can be recreated.
}
/*
*JavaScript获取网页信息总结
获取所有html:NSString *lJs = @"document.documentElement.innerHTML";
获取网页title:NSString *lJs2 = @"document.title";
UIWebView *lWebView = [self getCurrentWebView];
NSString *lHtml1 = [lWebView stringByEvaluatingJavaScriptFromString:lJs];
NSString *lHtml2 = [lWebView stringByEvaluatingJavaScriptFromString:lJs2];
JavaScript获取网页信息总结
JavaScript获取当前页面URL、title等
thisURL = document.URL;
thisHREF = document.location.href;
thisSLoc = self.location.href;
thisDLoc = document.location;
thisTLoc = top.location.href;
thisPLoc = parent.document.location;
thisTHost = top.location.hostname;
thisHost = location.hostname;
thisTitle = document.title;
thisProtocol = document.location.protocol;
thisPort = document.location.port;
thisHash = document.location.hash;
thisSearch = document.location.search;
thisPathname = document.location.pathname;
thisHtml = document.documentElement.innerHTML;
thisBodyText = document.documentElement.innerText;//获取网页内容文字
thisBodyText = document.body.innerText;//获取网页内容文字 怎么和上一个一样?有知道的请解释
*/
//获取
- (IBAction)receiveAction:(id)sender {
/*1视频*/
/*
//获取网页中所有视频
NSString *getVideoTitle = [_webview getVideoTitle];
NSLog(@"\n\n 视频名称 : %@",getVideoTitle);
double getVideoDuration = [_webview getVideoDuration];
NSLog(@"\n\n 视频总时间 : %f",getVideoDuration);
double getVideoCurrentTime = [_webview getVideoCurrentTime];
NSLog(@"\n\n 视频当前时间 : %f",getVideoCurrentTime);
*/
/*2网页*/
/*
//获取网页中所有图片
NSString *imageUrls = [_webview stringByEvaluatingJavaScriptFromString:@"var str=new Array();""$('img').each(function(){str.push($(this).attr('src'));});"
"str.join(',');"];
NSLog(@"\n\n 所有图片 : %@",imageUrls);
//获取所有html
NSString *lJs = @"document.documentElement.innerHTML";
NSString *lHtml1 = [_webview stringByEvaluatingJavaScriptFromString:lJs];
//NSLog(@"1.%@",lHtml1);
//获取网页title:
NSString *lJs2 = @"document.title";
NSString *lHtml2 = [_webview stringByEvaluatingJavaScriptFromString:lJs2];
NSLog(@"2.%@",lHtml2);
//thisURL = document.URL
NSString *lJs3 = @"document.URL";
NSString *lHtml3 = [_webview stringByEvaluatingJavaScriptFromString:lJs3];
NSLog(@"3.%@",lHtml3);
//获取网页内容文字
NSString *lJs4 = @"document.documentElement.innerText";
NSString *lHtml4 = [_webview stringByEvaluatingJavaScriptFromString:lJs4];
NSLog(@"4.%@",lHtml4);
//获取网页内容文字
NSString *lJs5 = @"document.body.innerText";
NSString *lHtml5 = [_webview stringByEvaluatingJavaScriptFromString:lJs5];
NSLog(@"5.%@",lHtml5);
*/
/*3图片*/
/**/
//获取所有html
NSString *innerHTML = @"document.documentElement.innerHTML";
NSString *innerHTMLString = [_webview stringByEvaluatingJavaScriptFromString:innerHTML];
//检索图片
if(![innerHTMLString isEqualToString:@"<head></head><body></body>"]){
[self searchPictureFromHTML:innerHTMLString];
}else{
UIAlertView *alert = [[UIAlertView alloc] initWithTitle:nil message:@"请先搜索关键字" delegate:nil cancelButtonTitle:@"确定" otherButtonTitles:nil, nil nil];
[alert show];
}
}
//检索图片
-(void)searchPictureFromHTML:(NSString *)theHTML{
//"http://img0.bdstatic.com/img/image/shouye/qwscmeb02.jpg”
NSMutableArray *picMutableArr = [[NSMutableArray alloc] init];
NSMutableArray *picHttpArr = [[theHTML componentsSeparatedByString:@"http://"] mutableCopy];
for (int i = 0; i < picHttpArr.count ; i ++) {
NSString *tempStr = [picHttpArr objectAtIndex:i];
NSArray *tempArr = [tempStr componentsSeparatedByString:@".jpg"];
NSString *firstStr = [tempArr firstObject];
//判断字符串是否为图片
if([self judgeStringIsPicture:firstStr]){
if([self judgeStringIsNull:firstStr]){
NSString *picUrl = [NSString stringWithFormat:@"http://%@.jpg",firstStr];
[picMutableArr addObject:picUrl];
}
}else{
}
}
//清除重复图片
picMutableArr = [self cleanRepeatPicture:picMutableArr];
//展示获取图片
PictureViewController *picVc = [[PictureViewController alloc] initWithNibName:@"PictureViewController" bundle:nil];
picVc.valueArr = picMutableArr;
[self.navigationController pushViewController:picVc animated:YES];
}
//判断字符串是否为图片链接
-(BOOL)judgeStringIsPicture:(NSString *)string{
BOOL result = YES;
NSMutableArray *mutable = [[NSMutableArray alloc] initWithObjects:@"<",@">",@"{",@"}",@"[",@"]",@"(",@")",@"|",@"||",@"$",@"?",@";", nil nil];
if(string != nil && string.length > 0){
for (int i = 0; i < string.length; i ++) {
NSString *subStr = [string substringWithRange:NSMakeRange(i, 1)];
for (int j = 0; j < mutable.count ; j ++) {
NSString *markStr = [mutable objectAtIndex:j];
if([subStr isEqualToString:markStr]){
result = NO;
}
}
}
}
return result;
}
//清除重复图片
-(NSMutableArray *)cleanRepeatPicture:(NSMutableArray *)picarr{
NSMutableArray *tempArr = [[NSMutableArray alloc] init];
for (int i = picarr.count-1 ; i >= 0 ; i --) {
NSString *tempStr = [picarr objectAtIndex:i];
NSArray *oneArr = [tempStr componentsSeparatedByString:@"&fm"];
if(tempArr.count == 0){
[tempArr insertObject:tempStr atIndex:0];
}else{
BOOL result = YES;
for (int j = 0 ; j < tempArr.count ; j ++) {
NSString *jstr = [tempArr objectAtIndex:j];
if([jstr isEqualToString:tempStr]){
result = NO;
}else{
if(oneArr.count > 1){
NSArray *twoArr = [jstr componentsSeparatedByString:@"&fm"];
if([[oneArr firstObject] isEqualToString:[twoArr firstObject]]){
result = NO;
}
}
}
}
if(result){
[tempArr insertObject:tempStr atIndex:0];
}
}
}
return tempArr;
}
//HTML
-(void)detailsWithUrl:(NSString *)urlStr{
NSURL *url =[NSURL URLWithString:urlStr];
NSURLRequest *request =[NSURLRequest requestWithURL:url];
[_webview loadRequest:request];
[_webview setScalesPageToFit:YES];
//隐藏滚动条
_webview.backgroundColor=[UIColor clearColor];
_webview.opaque = NO;
for (UIView *aView in [_webview subviews]){
[aView setBackgroundColor:[UIColor clearColor]];
if ([aView isKindOfClass:[UIScrollView class]]){
UIScrollView *tempSV = (UIScrollView *)aView;
tempSV.tag = 1321;
[tempSV setShowsHorizontalScrollIndicator:NO]; //右侧的滚动条 (水平的类似)
[tempSV setShowsVerticalScrollIndicator:NO];
[tempSV setBounces:NO];
[tempSV setContentSize:CGSizeMake(1,tempSV.contentSize.height )];
for (UIView *shadowView in tempSV.subviews){
if ([shadowView isKindOfClass:[UIImageView class]]){
shadowView.hidden = YES; //上下滚动出边界时的黑色的图片 也就是拖拽后的上下阴影
}
}
}
}
}
//判断字符串不全为空
-(BOOL)judgeStringIsNull:(NSString *)string{
BOOL result = NO;
if(string != nil && string.length > 0){
for (int i = 0; i < string.length; i ++) {
NSString *subStr = [string substringWithRange:NSMakeRange(i, 1)];
if(![subStr isEqualToString:@" "] && ![subStr isEqualToString:@""]){
result = YES;
}
}
}
return result;
}
#pragma mark UISearchBarDelegate
- (void)searchBarSearchButtonClicked:(UISearchBar *)searchBar{
if([self judgeStringIsNull:searchBar.text]){
//搜索接口
NSString *urlStr = [NetPortShared baiduSearchDelegate:self andTag:33333 andWord:_searchBar.text];
[self detailsWithUrl:urlStr];
}else{
UIAlertView *alert = [[UIAlertView alloc] initWithTitle:nil message:@"请输入关键字" delegate:nil cancelButtonTitle:@"确定" otherButtonTitles:nil, nil nil];
[alert show];
}
}
@end
示意图:
aaarticlea/png;base64,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" alt="" data-w="640" data-ratio="1.775" data-type="png" data-src="http://mmbiz.qpic.cn/mmbiz_png/g4uoJOMA38Lib8VMmfWNTzVHSJ9ibvJrEEiasibKYtG1EgbIr4s5J7QzTEk7VH1vf2f0aQAB6MY5hcHnTHcGFibWnvA/0?wx_fmt=png" />
文/作者:枫志应明
c博客地址:http://blog.csdn.net/wsyx768/article/details/46618125
获取网页上数据(图片、文字、视频)-b的更多相关文章
- Android获取网页上的图片的代码
public Bitmap getWebBitmap(String imgUrl) { Bitmap bitmap =null; try { InputStream inputStream = nul ...
- (java)Jsoup爬虫学习--获取网页所有的图片,链接和其他信息,并检查url和文本信息
Jsoup爬虫学习--获取网页所有的图片,链接和其他信息,并检查url和文本信息 此例将页面图片和url全部输出,重点不太明确,可根据自己的需要输出和截取: import org.jsoup.Jsou ...
- 如何获取网页上的LOGO
一般公司网页上的图片都会禁止右键另存为,用截图工具接下来的图会带背景色,PS成背景透明有点费时间. 用Google Chrome 或Firefox 打开目标网页,右键点击审查元素,将鼠标放在图片上,一 ...
- 网页上播放音频、视频Mp3,Mp4
昨天在处理网页上播放音频mp3,视频mp4上用了一天的时间来比较各种方案,最终还是选择了HTML5的 标签,谷歌浏览器.IE浏览器对标签的支持都很好,火狐上需要安装quicktime插件,效果比较差. ...
- c++ 实现https网页上的图片爬取
一.主要的原理 我们通过发送一个http请求,获得目标网页的html源代码,然后通过正则表达式获取到图片的URL,把该网页的所有的图片都保存到一个文件夹,这就是整个软件的流程. 二.具体的实践 现在很 ...
- 不需要爬虫也能轻松获取 unsplash 上的图片
我经常会使用 unsplash, 这里面的图片非常清爽,我的大多数文章的图片都是在这个网上找的,虽然也有同类型网站,但是用过一段时间以后基本都放弃了,图片质量参差不齐,筛选过程太费劲. 但是 unsp ...
- 用PHP获取网页上的信息相对于xpath效率低点
用php实现对网页的抓取,及信息的收集,其实就是爬数据,具体实现步骤如下,首先应引入两个文件curl_html_get.php和save_file.php文件,两个文件具体代码是这样的curl_htm ...
- Android获取ImageView上的图片,和一个有可能遇到的问题!
1.在获取图片前先调用setDrawingCacheEnabled(true)这个方法: 举例:mImageView.setDrawingCacheEnabled(true); 2.之后可以通过get ...
- [BUG]Dreamweaver6做网页的一个图片文字不清晰的问题
自己用Dreamweaver6做一个网页,使用PS做图片,为了节约下载流量,我把图片裁剪为GIF格式,通过系统自带的图片浏览器和美图看看,图片上的文字都是清晰的. 我把图片加载进入DW中后,在DW界面 ...
随机推荐
- 关于hadoop2.4.1伪分布式系统的搭建
1.准备Linux环境 1.0点击VMware快捷方式,右键打开文件所在位置 -> 双击vmnetcfg.exe -> VMnet1 host-only ->修改subnet ip ...
- linux两种增加交换分区(swap)的方法
在安装Oracle后,为使Oracle流畅运行,需要手动增加linux的交换分区(相当于Windows下的虚拟内存)的大小,本文介绍两种增加交换分区(swap)的方法. 第一种方法:新建分区 1.fd ...
- jquery的datepicker汉化
$("#date").datepicker({ dateFormat: "yy-mm-dd", monthNames:["1月", &quo ...
- Commons Codec - 常见的编码解码
Base64 Base64 编码 assertEquals("T3chIQ==", Base64.encodeBase64String("Ow!!".getBy ...
- centos6.5下逻辑卷操作
1.将两块独立磁盘分别分区 2.创建物理卷-pvcreate 3.创建卷组 4.创建逻辑卷 5.格式化逻辑卷 6.扩展逻辑卷 7.缩小逻辑卷
- 将svn添加到系统服务
C:\Users\Administrator>sc create svnServer binPath= "D:\Program Files\Subversion\bin\svnserv ...
- PC电脑运行Android模拟器总是弹出“视频源”窗体的原因和解决方案
原因: PC电脑运行Android模拟器时弹出“视频源”窗体,会让你"选择视频设备",如:HP TruevIsion HD,而这个视频设备就是你电脑中的内置摄像头,这个内置摄像头在 ...
- VScript 函数调用的两种分类:Sub过程和Function过程
来源:http://soft.zdnet.com.cn/software_zone/2007/0925/523318.shtml 在 VBScript 中,过程被分为两类:Sub 过程和 Functi ...
- Oracle 10g设置IP访问限制
出于数据安全考虑,对Oracle数据库的IP做一些限制,只有固定的IP才能访问. 修改 db_1/NETWORK/ADMIN/sqlnet.ora文件 增加以下内容(红色表示注释): #开启ip限制功 ...
- Xml 学习
XML概述 XML的历史背景 GML(1969):通用标记语言 IBM公司的一些专家们一起研究的一个课题: 软件必须有高度的可移植性,而且必须有一个统一的标准.为了实现软件的一处编写多处运行这个愿景所 ...