- iphone/
- Iphone NSXMLParser不';不要忽略CDATA
Iphone NSXMLParser不';不要忽略CDATA
Iphone NSXMLParser不';不要忽略CDATA,iphone,ios,xcode,xcode4.5,nsxmlparser,Iphone,Ios,Xcode,Xcode4.5,Nsxmlparser,我是ios开发的新手,我尝试解析RSS文件(xml)
这是xml:(很抱歉使用这种语言)
一般
在一次拖拉机事故中丧生,风帆冲浪者受重伤
< ! [CDATA[
] ] >
50多岁的拖拉机司机在Kfar Yuval附近翻车并被困在下面。在内塔尼亚,一名风帆冲浪者因强风投掷石块而受重伤,在内塔尼亚,一名风帆冲浪者受轻伤
http://www.ynet.co.il/articles/0 ,7340,L-4360016,00.html
2013年3月22日星期五17:10:15+0200
h
我是ios开发的新手,我尝试解析RSS文件(xml)
这是xml:(很抱歉使用这种语言)
一般
在一次拖拉机事故中丧生,风帆冲浪者受重伤
< ! [CDATA[
] ] >
50多岁的拖拉机司机在Kfar Yuval附近翻车并被困在下面。在内塔尼亚,一名风帆冲浪者因强风投掷石块而受重伤,在内塔尼亚,一名风帆冲浪者受轻伤
http://www.ynet.co.il/articles/0 ,7340,L-4360016,00.html
2013年3月22日星期五17:10:15+0200
http://www.ynet.co.il/articles/0 ,7340,L-4360016,00.html
杀人、车祸、冲浪
这是我的xmlparser代码:
- (void)parserDidStartDocument:(NSXMLParser *)parser
{
self.titles = [[NSMutableArray alloc]init];
self.descriptions = [[NSMutableArray alloc]init];
self.links = [[NSMutableArray alloc]init];
}
- (void)parser:(NSXMLParser *)parser didStartElement:(NSString *)elementName namespaceURI:(NSString *)namespaceURI qualifiedName:(NSString *)qName attributes:(NSDictionary *)attributeDict
{
if ([elementName isEqualToString:@"item"]) {
isItem = YES;
}
if ([elementName isEqualToString:@"title"]) {
isTitle=YES;
self.titlesString = [[NSMutableString alloc]init];
}
if ([elementName isEqualToString:@"description"]) {
isDesription = YES;
self.descriptionString = [NSMutableString string];
self.data = [NSMutableData data];
}
}
- (void)parser:(NSXMLParser *)parser foundCharacters:(NSString *)string{
if(isItem && isTitle){
[self.titlesString appendString:string];
}
if (isItem && isDesription) {
if (self.descriptionString)
[self.descriptionString appendString:string];
}
}
- (void)parser:(NSXMLParser *)parser foundCDATA:(NSData *)CDATABlock
{
if (self.data)
[self.data appendData:CDATABlock];
}
- (void)parser:(NSXMLParser *)parser didEndElement:(NSString *)elementName namespaceURI:(NSString *)namespaceURI qualifiedName:(NSString *)qName
{
if ([elementName isEqualToString:@"item"]) {
isItem = NO;
[self.titles addObject:self.titlesString];
[self.descriptions addObject:self.descriptionString];
}
if ([elementName isEqualToString:@"title"]) {
isTitle=NO;
}
if ([elementName isEqualToString:@"description"]) {
NSString *result = [self.descriptionString stringByTrimmingCharactersInSet:[NSCharacterSet whitespaceAndNewlineCharacterSet]];
NSLog(@"string=%@", result);
if ([self.data length] > 0)
{
NSString *htmlSnippet = [[NSString alloc] initWithData:self.data encoding:NSUTF8StringEncoding];
NSString *imageSrc = [self firstImgUrlString:htmlSnippet];
NSLog(@"img src=%@", imageSrc);
[self.links addObject:imageSrc];
}
self.descriptionString = nil;
self.data = nil;
}
}
- (NSString *)firstImgUrlString:(NSString *)string
{
NSError *error = NULL;
NSRegularExpression *regex = [NSRegularExpression regularExpressionWithPattern:@"(<img\\s[\\s\\S]*?src\\s*?=\\s*?['\"](.*?)['\"][\\s\\S]*?>)+?"
options:NSRegularExpressionCaseInsensitive
error:&error];
NSTextCheckingResult *result = [regex firstMatchInString:string
options:0
range:NSMakeRange(0, [string length])];
if (result)
return [string substringWithRange:[result rangeAtIndex:2]];
return nil;
}
@end
-(void)parserdistartdocument:(NSXMLParser*)解析器
{
self.titles=[[NSMutableArray alloc]init];
self.descriptions=[[NSMutableArray alloc]init];
self.links=[[NSMutableArray alloc]init];
}
-(void)parser:(NSXMLParser*)parser didStartElement:(NSString*)elementName namespaceURI:(NSString*)namespaceURI qualifiedName:(NSString*)qName属性:(NSDictionary*)attributeDict
{
if([elementName IsequalString:@“item”]){
isItem=是;
}
if([elementName IsequalString:@“title”]){
isTitle=是;
self.titleString=[[NSMutableString alloc]init];
}
if([elementName IsequalString:@“description”]){
isDesription=YES;
self.descriptionString=[NSMutableString];
self.data=[NSMutableData];
}
}
-(void)解析器:(NSXMLParser*)解析器查找字符:(NSString*)字符串{
如果(isItem&&isTitle){
[self.titleString appendString:string];
}
如果(isItem&&ISDeDescription){
if(自我描述字符串)
[self.descriptionString appendString:string];
}
}
-(void)解析器:(NSXMLParser*)解析器foundCDATA:(NSData*)CDATA块
{
if(自我数据)
[self.data appendData:CDATA块];
}
-(void)parser:(NSXMLParser*)parser didEndElement:(NSString*)elementName namespaceURI:(NSString*)namespaceURI qualifiedName:(NSString*)qName
{
if([elementName IsequalString:@“item”]){
isItem=否;
[self.titles addObject:self.titleString];
[self.descriptions添加对象:self.descriptionString];
}
if([elementName IsequalString:@“title”]){
isTitle=否;
}
if([elementName IsequalString:@“description”]){
NSString*result=[self.descriptionString-ByTrimmingCharactersInSet:[NSCharacterSet-whitespaceAndNewlineCharacterSet]];
NSLog(@“string=%@”,结果);
如果([self.data length]>0)
{
NSString*htmlSnippet=[[NSString alloc]initWithData:self.data encoding:NSUTF8StringEncoding];
NSString*imageSrc=[self-firstImgUrlString:htmlSnippet];
NSLog(@“img src=%@”,imageSrc);
[self.links addObject:imageSrc];
}
self.descriptionString=nil;
self.data=nil;
}
}
-(NSString*)第一个imgurlstring:(NSString*)字符串
{
n错误*错误=NULL;
NSRegularExpression*regex=[NSRegularExpression regular expression with pattern:@“()+?”
选项:nsregularexpressioncase不敏感
错误:&错误];
NSTextCheckingResult*结果=[regex firstMatchInString:字符串
选项:0
范围:NSMakeRange(0,[字符串长度]);
如果(结果)
返回[string substringWithRange:[结果范围索引:2]];
返回零;
}
@结束
就像我说的,我对iPhone开发还很陌生,我花了几个小时寻找解决方法,但什么也没找到。
我决定打开一个话题,然后问几个问题:
One.解析器不会忽略CDATA正在做的事情,而是解析所有内容。
为什么会这样?如您所见,描述本身不在cdata中,我只有第一步,但即使在不使用foundCDATA:(NSData*)cdata块的情况下,我也完成了其余步骤
两个。我想获取图像链接,怎么做?我在网上搜索了很多指南,其中解释了如何只使用foundCDATA:(NSData*)CDATA块函数
但是它是如何使用的呢?我在代码中使用的方式
请给我解释一下,以便我能理解,
谢谢回答您的两个问题:
如果您已经实现了foundCDATA
,解析器将在该方法中解析描述
CDATA,而不是在foundCharacters
中。另一方面,如果尚未实现foundCDATA
,则CDATA
将由foundCharacters
解析。因此,如果您不希望foundCharacters
解析CDATA
,那么您必须实现foundCDATA
如果你想提取img
URL,你必须解析你收到的HTML。您可以使用Hpple,但我可能倾向于使用正则表达式:
- (NSString *)firstImgUrlString:(NSString *)string
{
NSError *error = NULL;
NSRegularExpression *regex = [NSRegularExpression regularExpressionWithPattern:@"(<img\\s[\\s\\S]*?src\\s*?=\\s*?['\"](.*?)['\"][\\s\\S]*?>)+?"
options:NSRegularExpressionCaseInsensitive
error:&error];
NSTextCheckingResult *result = [regex firstMatchInString:string
options:0
range:NSMakeRange(0, [string length])];
if (result)
return [string substringWithRange:[result rangeAtIndex:2]];
return nil;
}
在回答你的两个问题时:
如果您已经实现了foundCDATA
,解析器将在该方法中解析描述
CDATA,而不是在foundCharacters
中。另一方面,如果尚未实现foundCDATA
,则CDATA
将由foundCharacters
解析。因此,如果您不希望foundCharacters
解析CDATA
,那么您必须实现foundCDATA
如果你想提取img
URL,你必须解析你收到的HTML。您可以使用Hpple,但我可能只是倾向于使用常规的
- (NSString *)firstImgUrlString:(NSString *)string
{
NSError *error = NULL;
NSRegularExpression *regex = [NSRegularExpression regularExpressionWithPattern:@"(<img\\s[\\s\\S]*?src\\s*?=\\s*?['\"](.*?)['\"][\\s\\S]*?>)+?"
options:NSRegularExpressionCaseInsensitive
error:&error];
NSTextCheckingResult *result = [regex firstMatchInString:string
options:0
range:NSMakeRange(0, [string length])];
if (result)
return [string substringWithRange:[result rangeAtIndex:2]];
return nil;
}
- (void)parser:(NSXMLParser *)parser didStartElement:(NSString *)elementName namespaceURI:(NSString *)namespaceURI qualifiedName:(NSString *)qName attributes:(NSDictionary *)attributeDict
{
if ([elementName isEqualToString:@"description"])
{
self.string = [NSMutableString string];
self.data = [NSMutableData data];
}
}
- (void)parser:(NSXMLParser *)parser parseErrorOccurred:(NSError *)parseError
{
NSLog(@"%s, parseError=%@", __FUNCTION__, parseError);
}
// In my standard NSXMLParser routine, I leave self.string `nil` when not parsing
// a particular element, and initialize it if I am parsing. I do it this way
// so only my `didStartElement` and `didEndElement` need to worry about the particulars
// and my `foundCharacters` and `foundCDATA` are simplified. But do it however you
// want.
- (void)parser:(NSXMLParser *)parser foundCharacters:(NSString *)string
{
if (self.string)
[self.string appendString:string];
}
- (void)parser:(NSXMLParser *)parser foundCDATA:(NSData *)CDATABlock
{
if (self.data)
[self.data appendData:CDATABlock];
}
- (void)parser:(NSXMLParser *)parser didEndElement:(NSString *)elementName namespaceURI:(NSString *)namespaceURI qualifiedName:(NSString *)qName
{
if ([elementName isEqualToString:@"description"])
{
// get the text (non-CDATA) portion
// you might want to get rid of the leading and trailing whitespace
NSString *result = [self.string stringByTrimmingCharactersInSet:[NSCharacterSet whitespaceAndNewlineCharacterSet]];
NSLog(@"string=%@", result);
// get the img out of the CDATA
if ([self.data length] > 0)
{
NSString *htmlSnippet = [[NSString alloc] initWithData:self.data encoding:NSUTF8StringEncoding];
NSString *imageSrc = [self firstImgUrlString:htmlSnippet];
NSLog(@"img src=%@", imageSrc);
}
// once I've saved the data where I want to save it, I `nil` out my
// `string` and `data` properties:
self.string = nil;
self.data = nil;
}
}
- (void)parser:(NSXMLParser *)parser didStartElement:(NSString *)elementName namespaceURI:(NSString *)namespaceURI qualifiedName:(NSString *)qName attributes:(NSDictionary *)attributeDict
{
if([currentElement isEqualToString:@"img"]) {
NSLog(@"%@",[attributeDict objectForKey:@"src"]);
}
}
- (void)parser:(NSXMLParser *)parser foundCDATA:(NSData *)CDATABlock
{
NSMutableString *cdstring = [[NSMutableString alloc] initWithData:CDATABlock encoding:NSUTF8StringEncoding];
}
<div>
<a href='http://www.ynet.co.il/articles/0,7340,L-4360016,00.html'>
<img src='http://www.ynet.co. il/PicServer3/2012/11/28/4302844/YOO_8879_a.jpg ' alt=' photo: Yaron Brener ' title=' Amona ' border='0' width='116 ' height='116'>
</ a>
</ div>
]]>
htmlContent = [NSString stringWithFormat:@"%@", cdstring];
[webView loadHTMLString:htmlContent baseURL:nil];