iOS解析html
首先是要对HTML文本进行去除标签。
+ (NSString *)filterHTML:(NSString *)html
{
if (!html) {
return nil;
}
NSScanner * scanner = [NSScanner scannerWithString:html];
NSString *text = nil;
while([scanner isAtEnd]==NO)
{
//找到标签的起始位置
[scanner scanUpToString:@"<" intoString:nil];
//找到标签的结束位置
[scanner scanUpToString:@">" intoString:&text];
NSRange range = [text rangeOfString:@"img"];
if (!range.length) {
NSRange range = [text rangeOfString:@"image"];
if (range.length) {
}else {
//
标签设置换行
if ([text hasSuffix:@"",text] withString:@"\n"];
}else{
html = [html stringByReplacingOccurrencesOfString:[NSString stringWithFormat:@"%@>",text] withString:@""];
}
}
}else {
html = [html stringByReplacingOccurrencesOfString:[NSString stringWithFormat:@"%@>",text] withString:[text getImageSrc]];
}
}
//防止设置标签导致的多次换行
NSString *n = @"\n\n";
html = [html stringByReplacingOccurrencesOfString:n withString:@"\n"];
NSString *regEx = @""";
html = [html stringByReplacingOccurrencesOfString:regEx withString:@"\""];
// NSString *nbsp= @" ";
// html = [html stringByReplacingOccurrencesOfString:nbsp withString:@"\n"];
NSString *nbsps= @" ";
html = [html stringByReplacingOccurrencesOfString:nbsps withString:@" "];
NSString *amp= @"&";
html = [html stringByReplacingOccurrencesOfString:amp withString:@"&"];
return [html stringByTrimmingCharactersInSet:[NSCharacterSet whitespaceAndNewlineCharacterSet]];//去除首尾空格和换行
}
然后是，用正则表达式解析字符串
/// 用正则表达式解析字符串 返回 DATKTextPart 数组
+ (NSArray *)parserString:(NSString *)text
{
// 换行的规则
NSString *wrapPattern = @"\n\t";
// 表情的规则
NSString *emotionPattern = @"\\[[0-9a-zA-Z\\u4e00-\\u9fa5]+\\]";
// @的规则
NSString *atPattern = @"@[0-9a-zA-Z\\u4e00-\\u9fa5]+";
// #话题#的规则
NSString *topicPattern = @"#[0-9a-zA-Z\\u4e00-\\u9fa5]+#";
// url链接的规则
// NSString *urlPattern = @"[a-zA-z]+://[^\\s]*";//@"\\b(([\\w-]+://?|www[.])[^\\s()<>]+(?:\\([\\w\\d]+\\)|([^[:punct:]\\s]|/)))";
NSString *urlPattern = @"((http|ftp|https)://)?(([a-zA-Z0-9\\._-]+\\.[a-zA-Z]{2,6})|([0-9]{1,3}\\.[0-9]{1,3}\\.[0-9]{1,3}\\.[0-9]{1,3}))(:[0-9]{1,4})*(/[a-zA-Z0-9\\&%_\\./-~-]*)?";
// 中文网址匹配规则
// NSString *cnUrlPattern = @"((http|ftp|https|file):[^'\"\\s]+)";
NSString *cnUrlPattern = @"((http|ftp|https|file):[^'\"]+)";
// 图片链接的规则
NSString *imgPattern = [NSString stringWithFormat:@"", cnUrlPattern];
// 填空的规则
NSString *gapPattern = @"_____+";
// 选择填空的规则
NSString *optionalGapPattern = @"______+";
// NSString *imgPattern = [NSString stringWithFormat:@"", @"([\\S]*)"];
// (\\s*) 表示若干个 空格符，包括tab键和换行符
// ([\\S]*) 匹配除去空格的任意字符
// ([\s\S]*) 或 ([\d\D]*) 或 ([\w\W]*) 匹配包括换行符在内的任意字
// ^s*|s*$ 匹配首尾空白字符的正则表达式 可以用来删除行首行尾的空白字符(包括空格、制表符、换页符等等)，非常有用的表达式
// 组合多个正则条件
// NSString *pattern = [NSString stringWithFormat:@"%@|%@|%@|%@|%@|%@|%@|%@", wrapPattern,emotionPattern, gapPattern,atPattern, topicPattern, urlPattern, imgPattern, optionalGapPattern];
NSString *pattern = [NSString stringWithFormat:@"%@|%@|%@|%@|%@", wrapPattern,emotionPattern, gapPattern, imgPattern, optionalGapPattern];
// 遍历所有的特殊字符串
NSMutableArray *parts = [NSMutableArray array];
[text enumerateStringsMatchedByRegex:pattern usingBlock:^(NSInteger captureCount, NSString *const __unsafe_unretained *capturedStrings, const NSRange *capturedRanges, volatile BOOL *const stop) {
if ((*capturedRanges).length == 0) return;
DATKTextPart *part = [[DATKTextPart alloc] init];
part.isSpecical = YES;
part.text = *capturedStrings;
part.isEmotion = [part.text isMatchedByRegex:[NSString stringWithFormat:@"^%@$",emotionPattern]];//[part.text hasPrefix:@"["] && [part.text hasSuffix:@"]"];
part.isWebsite = [part.text isMatchedByRegex:[NSString stringWithFormat:@"^%@$",urlPattern]];
part.isTopic = [part.text isMatchedByRegex:[NSString stringWithFormat:@"^%@$",topicPattern]];
part.isImage = [part.text isMatchedByRegex:[NSString stringWithFormat:@"^%@$",imgPattern]];
part.isAt = [part.text isMatchedByRegex:[NSString stringWithFormat:@"^%@$",atPattern]];
part.isGap = [part.text isMatchedByRegex:[NSString stringWithFormat:@"^%@$",gapPattern]];
part.isOptionalGap = [part.text isMatchedByRegex:[NSString stringWithFormat:@"^%@$",optionalGapPattern]];
part.isWrap = [part.text isMatchedByRegex:[NSString stringWithFormat:@"^%@$",wrapPattern]];
part.range = *capturedRanges;
// 二次匹配查找url
if (part.isImage) {
//判断是否是公式图片
part.imgUrl = [part.text stringByMatching:cnUrlPattern capture:0];
NSString *sizePattern = @"size='(\\d+?)-(\\d+)'";
part.imgWidht = [[part.text stringByMatching:sizePattern capture:1] floatValue];
part.imgHeight = [[part.text stringByMatching:sizePattern capture:2] floatValue];
part.isFormula = [part.text containsString:@"F=1"];
}
[parts addObject:part];
}];
// 遍历所有的非特殊字符
[text enumerateStringsSeparatedByRegex:pattern usingBlock:^(NSInteger captureCount, NSString *const __unsafe_unretained *capturedStrings, const NSRange *capturedRanges, volatile BOOL *const stop) {
if ((*capturedRanges).length == 0) return;
DATKTextPart *part = [[DATKTextPart alloc] init];
part.text = *capturedStrings;
part.range = *capturedRanges;
[parts addObject:part];
}];
// 排序
// 系统是按照从小 -> 大的顺序排列对象
[parts sortUsingComparator:^NSComparisonResult(DATKTextPart *part1, DATKTextPart *part2) {
// NSOrderedAscending = -1L, NSOrderedSame, NSOrderedDescending
// 返回NSOrderedSame:两个一样大
// NSOrderedAscending(升序):part2>part1
// NSOrderedDescending(降序):part1>part2
if (part1.range.location > part2.range.location) {
// part1>part2
// part1放后面, part2放前面
return NSOrderedDescending;
}
// part1 这里的DATKTextPart类，主要是对正则解析出的字符串类型进行封装。方便后面使用。
typedef NS_ENUM(NSUInteger, DTKTextPartSpecicalType) {
DTKTextPartSpecicalTypeNormal = 0, // 无格式字符串
DTKTextPartSpecicalTypeEmotion = 1, // 表情
DTKTextPartSpecicalTypeTopic = 2, // 话题
DTKTextPartSpecicalTypeAt = 3, // @某人
DTKTextPartSpecicalTypeWebsite = 4, // 网址
DTKTextPartSpecicalTypeImage = 5, // 其他图片
DTKTextPartSpecicalTypeGap = 6, // 填空
DTKTextPartSpecicalTypeOptionalGap = 7, // 填空选择
DTKTextPartSpecicalTypeWrap = 8, // 换行
};
@interface DATKTextPart : NSObject
/** 这段文字的内容 */
@property (nonatomic, copy) NSString *text;
/** 这段文字的范围 */
@property (nonatomic, assign) NSRange range;
@property (nonatomic, assign) DTKTextPartSpecicalType textType;
/** 是否为特殊文字 */
@property (nonatomic, assign) BOOL isSpecical;
/** 是否为表情 */
@property (nonatomic, assign) BOOL isEmotion;
/** 是否为图片 */
@property (nonatomic, assign) BOOL isImage;
/** 是否为话题 */
@property (nonatomic, assign) BOOL isTopic;
/** 是否为网址 */
@property (nonatomic, assign) BOOL isWebsite;
/** 是否为@某人 */
@property (nonatomic, assign) BOOL isAt;
/** 是否为选择填空题 */
@property (nonatomic, assign) BOOL isOptionalGap;
/** 是否为填空题 */
@property (nonatomic, assign) BOOL isGap;
/** 是否为换行 */
@property (nonatomic, assign) BOOL isWrap;
/** imgurl */
@property (nonatomic, strong) NSString *imgUrl;
/** imgWidth */
@property (nonatomic, assign) CGFloat imgWidht;
/** imgHeight */
@property (nonatomic, assign) CGFloat imgHeight;
/**
是否是公式
*/
@property (nonatomic , assign) BOOL isFormula;
在实际项目中，我们采用第三方图文混排的TYATTributeLabel进行内容的展示和布局。
大概代码如下：
- (void)setStemContent {
for (DATKTextPart *textPart in self.textArray) {
if (textPart.textType == DTKTextPartSpecicalTypeNormal) {
[self.stemLabel appendText:textPart.text];
}
if (textPart.textType == DTKTextPartSpecicalTypeImage) {
NSURL *imageUrl = [NSURL URLWithString:textPart.imgUrl];
// 追加 图片Url
TYImageStorage *imageUrlStorage = [[TYImageStorage alloc]init];
imageUrlStorage.isFormula = textPart.isFormula;
imageUrlStorage.imageURL = imageUrl;
if (imageUrlStorage.isFormula) {
imageUrlStorage.size = CGSizeMake(formulaImageRate*textPart.imgWidht, formulaImageRate*textPart.imgHeight);
} else {
imageUrlStorage.size = CGSizeMake(normalImageRate*textPart.imgWidht, normalImageRate*textPart.imgHeight);
}
[self.stemLabel appendTextStorage:imageUrlStorage];
[self.stemLabel appendText:@" "];
}
if (textPart.textType == DTKTextPartSpecicalTypeGap|| textPart.textType == DTKTextPartSpecicalTypeOptionalGap ) {
// 填空题
TYTextStorage *textStorage = [[TYTextStorage alloc] init];
textStorage.text = @" ";
textStorage.underLineStyle = kCTUnderlineStyleSingle;
textStorage.font = PF_SC_Medium(17);;
[self.stemLabel appendTextStorage:textStorage];
}
}
self.stemLabel.linesSpacing = tkLineSpace;
[self.stemLabel sizeToFit];
}