php爬虫实战（抓取美拍视频）

抓取页面

地址：http://www.meipai.com/medias/hot

1234	`public function getContentByFilegetcontents($url) { $content = file_get_contents($url); return $content; }`

然后我们会获取到整个页面的代码，接下来就是从代码中提取出视频的地址标题图片等关键信息

2.提取

我们发现视频的主要代码集中在以下代码中

<li class="pr no-select loading J_media_list_item" itemscope itemtype="http://schema.org/VideoObject"> <img src="http://mvimg1.meitudata.com/5733fe57ce7aa8996.jpg!thumb320" width="300" height="300" class="db pa pai" alt="手撕包菜。包菜撕片装洗净备用。热锅入油五花肉下锅煸炒出油，多余的油盛出。放酱油肉上色，盛出。之前的油倒锅内，放蒜辣椒炒香，下包菜继续翻炒，倒适量酱油老抽五香粉。再下之前炒好的五花肉翻炒，放适量盐，出锅前放鸡精淋入适量香醋即可非常香啊，超级下饭。喜欢的点赞奥#美食##家常菜#" itemprop="thumbnail"> <div id="w517161790" class="content-l-video content-l-media-wrap pr cp" data-id="517161790" data-video="http://mvvideo1.meitudata.com/5734040ae2dec950.mp4"> <div class="layer-black pa">div> <a hidefocus href="/media/517161790" target="_blank" class="content-l-p pa" title="手撕包菜。包菜撕片装洗净备用。热锅入油五花肉下锅煸炒出油，多余的油盛出。放酱油肉上色，盛出。之前的油倒锅内，放蒜辣椒炒香，下包菜继续翻炒，倒适量酱油老抽五香粉。再下之前炒好的五花肉翻炒，放适量盐，出锅前放鸡精淋入适量香醋即可非常香啊，超级下饭。喜欢的点赞奥#美食##家常菜#"> <meta itemprop="url" content="/media/517161790"> <i class="icon icon-item-play">i> <strong class="js-convert-emoji" itemprop="description">哈喇嘎子流成河strong> a> div> <div class="pr" itemscope itemtype="http://schema.org/AggregateRating"> <a hidefocus href="/user/62299474" class="dbl h48"> <img src="http://mvavatar2.meitudata.com/5731f6b7bbee979.jpg!thumb60" width="28" height="28" class="avatar m10" title="小优Lucky" alt="小优Lucky"> a> <p class="content-name pa"> <a hidefocus href="/user/62299474" class="content-name-a js-convert-emoji" title="小优Lucky" itemprop="author">小优Luckya> p> <div class="content-like pa" data-id="517161790"> <i class="icon icon-like">i> <span itemprop="ratingCount">3060span> div> <a hidefocus href="/media/517161790" data-sc="1" target="_blank" class="conten-command pa" data-id="517161790"> <i class="icon icon-command">i> <span itemprop="reviewCount">100span> a> div>li>

通过正则匹配

public function extracturl($page) { $matches = array(); $voide=array(); $mainurl=""; $list=array(); $j=0; $pat = "/.*?/ism"; preg_match_all($pat, $page, $matches, PREG_PATTERN_ORDER); for ($i=0; $i <count($matches[0]) ; $i++) { $pat1 ="/data-video="https://www.mshxw.com/skin/sinaskin/image/nopic.gif"/ism"; preg_match_all($pat1, $matches[0][$i], $voide, PREG_PATTERN_ORDER); $myvoide=$voide[1][0]; $pat2 ="/src="https://www.mshxw.com/skin/sinaskin/image/nopic.gif"/ism"; preg_match_all($pat2, $matches[0][$i], $img, PREG_PATTERN_ORDER); $myimg=$img[1][0]; $pat3 ="/https://www.mshxw.com/skin/sinaskin/image/nopic.gif/ism"; preg_match_all($pat3, $matches[0][$i], $title, PREG_PATTERN_ORDER); $mytitle= $title[1][0]; $list[$j++]=array( 'voide'=>$myvoide, 'title'=>$mytitle, 'img'=>$myimg); } return $list; }}

全部代码

class Cutecrawler { public function getContentByFilegetcontents($url) { $content = file_get_contents($url); return $content; } public function extracturl($page) { $matches = array(); $voide=array(); $mainurl=""; $list=array(); $j=0; $pat = "/.*?/ism"; preg_match_all($pat, $page, $matches, PREG_PATTERN_ORDER); for ($i=0; $i <count($matches[0]) ; $i++) { $pat1 ="/data-video="https://www.mshxw.com/skin/sinaskin/image/nopic.gif"/ism"; preg_match_all($pat1, $matches[0][$i], $voide, PREG_PATTERN_ORDER); $myvoide=$voide[1][0]; $pat2 ="/src="https://www.mshxw.com/skin/sinaskin/image/nopic.gif"/ism"; preg_match_all($pat2, $matches[0][$i], $img, PREG_PATTERN_ORDER); $myimg=$img[1][0]; $pat3 ="/https://www.mshxw.com/skin/sinaskin/image/nopic.gif/ism"; preg_match_all($pat3, $matches[0][$i], $title, PREG_PATTERN_ORDER); $mytitle= $title[1][0]; $list[$j++]=array( 'voide'=>$myvoide, 'title'=>$mytitle, 'img'=>$myimg); } return $list; }} $url = "http://www.meipai.com/medias/hot"; $crawler = new Cutecrawler(); $content = $crawler->getContentByFilegetcontents($url); $c=$crawler->extracturl($content); var_dump($c);?>

最后结果：

array(24) { [0]=> array(3) { ["voide"]=> string(51) "http://mvvideo2.meitudata.com/5737fd5caeb838981.mp4" ["title"]=> string(27) "老师那些年常说的话" ["img"]=> string(58) "http://mvimg4.meitudata.com/57384337bd8b59410.jpg!thumb320" } [1]=> array(3) { ["voide"]=> string(50) "http://mvvideo2.meitudata.com/5737fceabf873602.mp4" ["title"]=> string(21) "女友突然冷落你" ["img"]=> string(58) "http://mvimg2.meitudata.com/5736d25d0aa5d8991.jpg!thumb320" } [2]=> array(3) { ["voide"]=> string(51) "http://mvvideo2.meitudata.com/5737f300131e18596.mp4" ["title"]=> string(27) "女明星之间的内心戏" ["img"]=> string(58) "http://mvimg1.meitudata.com/5737059ad66e16795.jpg!thumb320" } [3]=> array(3) { ["voide"]=> string(51) "http://mvvideo2.meitudata.com/5737eb9d0bfc92046.mp4" ["title"]=> string(24) "真替老师感到悲剧" ["img"]=> string(57) "http://mvimg3.meitudata.com/5737ebf503431343.jpg!thumb320" }

接下来。。。你可以存入数据库

php爬虫实战（抓取美拍视频）

PHP相关栏目本月热门文章