Question

我正在使用Hpple解析HTML，它似乎无法识别它实际上是XML，它应该（XCode调试器显示此变量isXML = (BOOL) NO并且它不收集任何数据）。我该如何解决这个问题？

这是我的代码（它们也可能是其他错误）。首先使用[ListParser parse:@"http://www.fanfiction.net/book/Harry-Potter/" at:@"//div[@=\"class\"]"];：

调用解析方法/函数

@interface ListParser () //private
+ (NSArray*) getNodeListAt: (NSURL*) page inside: (NSString*) page;
+ (NSDictionary*) getNodeData: (TFHppleElement*) node;
+ (void) addMiniListData: (NSString*) list to: (NSMutableDictionary*) dict;
@end


@implementation ListParser

+ (NSArray*) getNodeListAt: (NSURL*) page inside: (NSString*) path { // "//div[@class"z-list"]"
    NSData *data = [NSData dataWithContentsOfURL: page];
    TFHpple *listparser = [TFHpple hppleWithHTMLData:data]; //WHERE CODE SEEMS TO STOP TO WORK
    NSArray *done = [listparser searchWithXPathQuery: path];
    return done;
}

+ (void) addMiniListData: (NSString*) list to: (NSMutableDictionary*) dict{
    NSArray *parts = [list componentsSeparatedByString:@" - "];

    for(NSString* p in parts){
        NSArray* two = [p componentsSeparatedByString:@": "];
        [dict setObject:[two objectAtIndex:1] forKey:[two objectAtIndex:0]];
    }
}

+ (NSDictionary*) getNodeData: (TFHppleElement*) node{
    NSMutableDictionary* data = [NSMutableDictionary dictionary];
    [data setObject:[[[node firstChild] firstChild] objectForKey:@"href"] forKey:@"Image"];
    [data setObject:[[node firstChild] text] forKey:@"Title"];
    [data setObject:[[[[node firstChild] children] objectAtIndex:2] text] forKey:@"By"];
    [data setObject:[[[[node firstChild] childrenWithClassName:@"z-indent"] objectAtIndex:0] text] forKey:@"Summery"];
    [self addMiniListData:[[[[[[node firstChild] childrenWithClassName:@"z-indent"] objectAtIndex:0] childrenWithClassName:@"z-padtop2"] objectAtIndex:0] text] to: data];

    return data;
}

+(NSArray*) parse: (NSString*) address at: (NSString*) path{
    NSURL *url = [[NSURL alloc] initWithString:address];
    NSArray* list = [self getNodeListAt:url inside:path];
    NSMutableArray *data = [[NSMutableArray alloc] init];
    for (TFHppleElement* e in list) {
        [data addObject:[self getNodeData:e]];
    }
    return [[NSArray alloc] initWithArray: data];
}

@end

以下是我关注的教程的链接：http://www.raywenderlich.com/14172/how-to-parse-html-on-ios

Answer 1

如果您需要使用TFHpple解析XML，您应该告诉它您正在这样做。你在呼叫+hppleWithHTMLData:。如果您阅读了此方法的实现，您会看到它将isXML设置为NO。相反，请使用hppleWithXMLData:方法。

Hpple无法解析HTML

1 个答案: