準(zhǔn)備工作
1.導(dǎo)入TFHpple 2.引入靜態(tài)庫(kù)文件libxml2.2.dylib 3.PROJECT 中的 Search Path - header search paths添加 /usr/include/libxml2
解析步驟
1.初始化data 2.根據(jù)data創(chuàng)建TFHpple實(shí)例 3.查找節(jié)點(diǎn)存入數(shù)組 4.在該節(jié)點(diǎn)下 循環(huán)查找子節(jié)點(diǎn)
源HTML代碼:
<table cellpadding="0" cellspacing="0" border="0" width="100%">
<tr>
<td width="48" valign="top" align="center"><a href="/member/zhangyi2099"><img src="http://cdn.v2ex.co/avatar/d00c/ceb1/18330_normal.png?m=1345037943" class="avatar" border="0" align="default"></a></td>
<td width="10"></td>
<td width="auto" valign="middle"><span class="item_title"><a href="/t/228173#reply1">看了本「網(wǎng)球優(yōu)等生」</a></span>
<div class="sep5"></div>
<span class="small fade"><div class="votes"></div><a class="node" href="/go/acg">ACG</a> ? <strong><a href="/member/zhangyi2099">zhangyi2099</a></strong> ? 20 分鐘前 ? 最后回復(fù)來(lái)自 <strong><a href="/member/yishanxin">yishanxin</a></strong></span>
</td>
<td width="70" align="right" valign="middle">
<a href="/t/228173#reply1" class="count_livid">1</a>
</td>
</tr>
</table>
Object-C代碼:
NSData *htmlData = [[NSData alloc]initWithContentsOfURL:[NSURL URLWithString:@"http://www.xxx.com/xxxx?x=1"]];
TFHpple *xpathParser = [[TFHpple alloc]initWithHTMLData:htmlData];
pragma mark 每頁(yè)主題
NSArray *itemArray = [xpathParser searchWithXPathQuery:@"http://div[@class = 'cell item']"];
//通過(guò)for in 在itemArray數(shù)組中 循環(huán)查找子節(jié)點(diǎn) for (TFHppleElement *hppleElement in itemArray) {
/** 這段被正則表達(dá)代替 @"http://div[@class = 'cell item']"] if ([[hppleElement objectForKey:@"class" ] isEqualToString:@"cell item"]) { [self.allDataMutableArray addObject:hppleElement]; } /
pragma mark 子節(jié)點(diǎn)頭像
NSArray *IMGElementsArr = [hppleElement searchWithXPathQuery:@"http://img"];
for (TFHppleElement *tempAElement in IMGElementsArr) {
NSString *imgStr = [tempAElement objectForKey:@"src"];
NSString *subStr = [@"http:" stringByAppendingString:imgStr];
[self.avatarMutableArray addObject:subStr];
}
pragma mark 子節(jié)點(diǎn)標(biāo)題/鏈接
NSArray TitleElementArr = [hppleElement searchWithXPathQuery:@"http://span[@class='item_title']"]; for (TFHppleElement tempAElement in TitleElementArr) { //獲得標(biāo)題 NSString *titleStr = [tempAElement content];
//1.獲得子節(jié)點(diǎn)(正文連接節(jié)點(diǎn)) 2.獲得節(jié)點(diǎn)屬性值 3.加入到字典中
NSArray * arr = [tempAElement children];
TFHppleElement *href = arr.firstObject;
NSString * titleHrefStr = [href objectForKey:@"href"];
[self.allDataMutableDict setObject:titleStr forKey:@"title"];
self.allDataMutableDict[@"titleHref"] = titleHrefStr;
}
pragma mark 子節(jié)點(diǎn)fade
//簡(jiǎn)化寫(xiě)法 簡(jiǎn)化3步
NSArray *nodeElementArr = [hppleElement searchWithXPathQuery:@"http://a[@class='node']"];
self.allDataMutableDict[@"node"] = [nodeElementArr.firstObject content];
NSArray *fadeElementArr = [hppleElement searchWithXPathQuery:@"http://span[@class = 'small fade']"];
NSArray *subArray = [ [fadeElementArr.firstObject content] componentsSeparatedByString:@" ? "];
self.allDataMutableDict[@"louZhu"] = [subArray objectAtIndex:1];
self.allDataMutableDict[@"lastTime"] = [subArray objectAtIndex:2];
pragma mark 子節(jié)點(diǎn)回復(fù)數(shù)
NSArray * repeatElementArr = [hppleElement searchWithXPathQuery:@"http://a[@class = 'count_livid']"];
if ([repeatElementArr.firstObject content ]) {
self.allDataMutableDict[@"repeatCount"] = [repeatElementArr.firstObject content];
}else{
self.allDataMutableDict[@"repeatCount"] = [NSString stringWithFormat:@"%d",0];
}
pragma mark 轉(zhuǎn)化model 存進(jìn)數(shù)組
[model setValuesForKeysWithDictionary:self.allDataMutableDict];
[self.allDataMutableArray addObject:model];
}