PHP XPath查询
我想从一个没有嵌套在斜体标记中的页面中查找所有锚定。 这就是我所拥有的，它是有效的，但链接的处理顺序不正确（根据页面来源） 关于如何在xpath查询中区分这两个集合的任何建议都将不胜感激 谢谢PHP XPath查询,php,dom,xpath,Php,Dom,Xpath,我想从一个没有嵌套在斜体标记中的页面中查找所有锚定。 这就是我所拥有的，它是有效的，但链接的处理顺序不正确（根据页面来源） 关于如何在xpath查询中区分这两个集合的任何建议都将不胜感激 谢谢 $phil = gettingToPhilosophy("http://en.wikipedia.org/Yarn"); for($i=0; $i<30; $i++) { $phil->hop(); $phil->processHTML(); } <?php class
$phil = gettingToPhilosophy("http://en.wikipedia.org/Yarn");
for($i=0; $i<30; $i++)
{
$phil->hop();
$phil->processHTML();
}
<?php
class gettingToPhilosophy
{
public $base_url; //base_url to start with
public $target_url; //url to hop to
public $previous_link; //keep track of last link
public $lookup; //cached array of visited links
public $curl; //curl object to execute
public $html; //html retrieved from curl request
public $conn; //database connection resource
public $hoplimit; //maximum number of hops (23 was the median as per the wikipedia article)
public $hop_num; //the number of hops taken to reach the philosophy page
public $id; //id of current link (Primary Key)
public $child_id; //id of next link
function __construct($base_url)
{
$this->base_url = filter_var($base_url, FILTER_VALIDATE_URL);
//determine if url is valid
if (!($this->base_url))
{
die("<font color='red'>Invalid URL</font>");
}
$this->target_url = parse_url($base_url, PHP_URL_PATH);
$this->previous_link = '';
$this->lookup = array();
$this->curl = curl_init();
// Create a user agent as to not get blocked by wikipedia
$userAgent = 'Googlebot/2.1 (http://www.google.bot.com/bot.html)';
// Initialize curl and following options
//curl_setopt($this->curl, CURLOPT_USERAGENT, $userAgent);
//curl_setopt($this->curl, CURLOPT_FAILONERROR, true);
//curl_setopt($this->curl, CURLOPT_FOLLOWLOCATION, true);
//curl_setopt($this->curl, CURLOPT_AUTOREFERER, true);
//curl_setopt($this->curl, CURLOPT_RETURNTRANSFER,true);
//curl_setopt($this->curl, CURLOPT_TIMEOUT, 10);
//$this->conn = pg_connect("dbname=Wesley user=Wesley host=localhost") or die("Can't connect to database".pg_last_error());
$this->hoplimit = 30;
$this->hop_num = 0;
$this->id = 1;
$this->child_id = 0;
}
function __destruct()
{
$this->base_url = null;
$this->target_url = null;
$this->previous_link = null;
$this->curl = null;
$this->lookup = null;
//pg_close($this-conn);
$this->conn = null;
$this->id = null;
$this->child_id = null;
}
function hop()
{
//Error handling for cached results of links
if (isset($this->lookup[$this->target_url]))
{
//printLinks();
die("<font color='red'>Never ending loop: $this->target_url has already been seen</font>");
}
$this->lookup[$this->target_url] = 1; //cache the link
$this->child_id++;
$sql = "insert into Philosophy (base_url, childid, link) values('$this->base_url', $this->child_id, '$this->target_url')";
//pg_execute($conn,$sql);
echo "$sql <br/>";
//append nodeValue to wikipedia url scheme
$this->target_url = "http://en.wikipedia.org".$this->target_url;
// Reset url
$userAgent = 'Googlebot/2.1 (http://www.google.bot.com/bot.html)';
// Initialize curl and following options
curl_setopt($this->curl, CURLOPT_USERAGENT, $userAgent);
curl_setopt($this->curl, CURLOPT_FAILONERROR, true);
curl_setopt($this->curl, CURLOPT_FOLLOWLOCATION, true);
curl_setopt($this->curl, CURLOPT_AUTOREFERER, true);
curl_setopt($this->curl, CURLOPT_RETURNTRANSFER,true);
curl_setopt($this->curl, CURLOPT_TIMEOUT, 10);
curl_setopt($this->curl, CURLOPT_URL,$this->target_url);
// Get html from the page
$this->html = curl_exec($this->curl);
// Error handling for invalid link
if(!$this->html)
{
//$this->printLinks();
//target_url was invalid or not reachable
die("<font color='red'>$this->target_url is invalid or unreachable - Hopped $this->hop_num times</font>");
}
$this->hop_num++;
}
function processHTML()
{
$dom = new DOMDocument();
@$dom->loadHTML($this->html);
$xpath = new DOMXpath($dom);
$anchorlinks = $xpath->query('//a[not(ancestor::i)]/@href');
//$anchorlinks = $dom->getElementsByTagName('a');
echo "<pre>"; print_r(iterator_to_array($anchorlinks)); echo "</pre>"; exit;
foreach($anchorlinks as $anchorlink)
{
if (!$this->isValid($anchorlink->nodeValue)){ continue; }
$this->previous_link = $this->target_url;
$this->target_url = "$anchorlink->nodeValue";
$flag = true;
break;
/*foreach($anchorlink->attributes as $attribute)
{
//skip erroneous links
if ($attribute->nodeName !== 'href') {continue;}
if (!$this->isValid($attribute->nodeValue)){ continue; }
$this->target_url = "$attribute->nodeValue";
$flag = true;
break;
}*/
}
}
function isValid($link)
{
if ($link === $this->previous_link){ return false; }
//links to ignore
if (strstr($link, '#') || stristr($link, 'Help:') || stristr($link, 'navigation') || stristr($link,'[note')
|| strstr($link, '(') || stristr($link, 'File:') || strstr($link, '.jpg') || strstr($link, '?') || stristr($link, 'http')
|| strstr($link, '//') || stristr($link, 'Portal:') || stristr($link, 'Special:') || stristr($link, 'Wikipedia:')
|| stristr($link, 'Talk:') || stristr($link, 'Category:') || stristr($link, 'Main_Page'))
{
return false;
}
return true;
}
function printLinks()
{
$sql = "select childid, link from philosophy where base_url='$this->base_url'";
if ($result = pg_execute($conn, $sql))
{
while ($row = pg_fetch_assoc($result))
{
echo "{$row['childid']}) {$row['link']} <br/>";
}
}
}
}
?>
$phil=gettingToPhilosophy（“http://en.wikipedia.org/Yarn");
对于（$i=0；$ihop（）；
$phil->processHTML（）；
}
我想从一个没有嵌套在斜体标记中的页面中查找所有锚定
那么你应该使用
href="#mw-head"
-----------------------
href="#p-search"
-----------------------
href="/wiki/File:Essay.svg"
-----------------------
href="/wiki/Wikipedia:Wikipedia_essays"
-----------------------
href="/wiki/Wikipedia:Policies_and_guidelines"
-----------------------
href="/wiki/Hyperlink"
-----------------------
href="/wiki/Wikipedia"
-----------------------
href="/wiki/Philosophy"
-----------------------
href="/wiki/Philosophy"
-----------------------
href="#cite_note-1"
-----------------------
href="/wiki/File:Crawl_on_Wikipedia_from_random_article_to_Philosophy..gif"
-----------------------
href="/wiki/File:Crawl_on_Wikipedia_from_random_article_to_Philosophy..gif"
-----------------------
href="/wiki/Document_classification"
-----------------------
href="/wiki/Wikipedia:MOSBEGIN"
-----------------------
href="/wiki/Mathematics"
-----------------------
href="/wiki/Science"
-----------------------
href="/wiki/Language"
-----------------------
href="/wiki/Philosophy"
-----------------------
href="#Method_summarized"
-----------------------
href="#Origins"
-----------------------
href="#Examples_of_exceptions_to_the_Getting_to_Philosophy_rule"
-----------------------
href="#See_also"
-----------------------
href="#References"
-----------------------
href="#External_links"
-----------------------
href="/w/index.php?title=Wikipedia:Getting_to_Philosophy&action=edit&section=1"
-----------------------
href="/w/index.php?title=Wikipedia:Getting_to_Philosophy&action=edit&section=2"
-----------------------
href="/wiki/Phenomenon"
-----------------------
href="/wiki/User:Mark_J"
-----------------------
href="#cite_note-2"
-----------------------
href="/wiki/Wikipedia:WikipediaWeekly/Episode50"
-----------------------
href="/wiki/Podcast"
-----------------------
href="#cite_note-3"
-----------------------
href="/w/index.php?title=Wikipedia:Getting_to_Philosophy&action=edit&section=3"
-----------------------
href="/wiki/Yarn"
-----------------------
href="/wiki/Fibres"
-----------------------
href="/wiki/Rope"
-----------------------
href="/w/index.php?title=Wikipedia:Getting_to_Philosophy&action=edit&section=4"
-----------------------
href="/wiki/Small-world_network"
-----------------------
href="/wiki/Attractor"
-----------------------
href="/wiki/Wikipedia:Wiki_Game"
-----------------------
href="/w/index.php?title=Wikipedia:Getting_to_Philosophy&action=edit&section=5"
-----------------------
href="#cite_ref-1"
-----------------------
href="/wiki/User:Ilmari_Karonen/First_link"
-----------------------
href="/wiki/Help:CS1_errors#cite_web_url"
-----------------------
href="#cite_ref-2"
-----------------------
href="http://en.wikipedia.org/w/index.php?title=Wikipedia:Getting_to_Philosophy&oldid=215744293"
-----------------------
href="#cite_ref-3"
-----------------------
href="http://huffduffer.com/psd/42471"
-----------------------
href="/w/index.php?title=Wikipedia:Getting_to_Philosophy&action=edit&section=6"
-----------------------
href="http://www.xefer.com/wikipedia"
-----------------------
href="http://www.youtube.com/watch?v=vehDe2lSptU"
-----------------------
href="/wiki/Philosophy"
-----------------------
href="http://matpalm.com/blog/2011/08/13/wikipedia-philosophy/"
-----------------------
href="http://xkcd.com/903/"
-----------------------
href="/wiki/Xkcd"
-----------------------
href="/wiki/Tooltip"
-----------------------
href="http://wikiloopr.com/"
-----------------------
href="http://www.guardian.co.uk/technology/2011/jul/10/only-way-essex-wikipedia-philosophy"
-----------------------
href="/wiki/The_Guardian"
-----------------------
href="http://www.huffingtonpost.com/2011/11/14/wikipedia-philosophy_n_1093460.html"
-----------------------
href="http://en.wikipedia.org/w/index.php?title=Wikipedia:Getting_to_Philosophy&oldid=645649870"
-----------------------
href="/wiki/Help:Category"
-----------------------
href="/wiki/Category:Wikipedia_essays"
-----------------------
href="/wiki/Category:Pages_using_web_citations_with_no_URL"
-----------------------
href="/w/index.php?title=Special:UserLogin&returnto=Wikipedia:Getting+to+Philosophy&type=signup"
-----------------------
href="/w/index.php?title=Special:UserLogin&returnto=Wikipedia:Getting+to+Philosophy"
-----------------------
href="/wiki/Wikipedia:Getting_to_Philosophy"
-----------------------
href="/wiki/Wikipedia_talk:Getting_to_Philosophy"
-----------------------
href="#"
-----------------------
href="/wiki/Wikipedia:Getting_to_Philosophy"
-----------------------
href="/w/index.php?title=Wikipedia:Getting_to_Philosophy&action=edit"
-----------------------
href="/w/index.php?title=Wikipedia:Getting_to_Philosophy&action=history"
-----------------------
href="#"
-----------------------
href="/wiki/Main_Page"
-----------------------
href="/wiki/Main_Page"
-----------------------
href="/wiki/Portal:Contents"
-----------------------
href="/wiki/Portal:Featured_content"
-----------------------
href="/wiki/Portal:Current_events"
-----------------------
href="/wiki/Special:Random"
-----------------------
href="https://donate.wikimedia.org/wiki/Special:FundraiserRedirector?utm_source=donate&utm_medium=sidebar&utm_campaign=C13_en.wikipedia.org&uselang=en"
-----------------------
href="//shop.wikimedia.org"
-----------------------
href="/wiki/Help:Contents"
-----------------------
href="/wiki/Wikipedia:About"
-----------------------
href="/wiki/Wikipedia:Community_portal"
-----------------------
href="/wiki/Special:RecentChanges"
-----------------------
href="//en.wikipedia.org/wiki/Wikipedia:Contact_us"
-----------------------
href="/wiki/Special:WhatLinksHere/Wikipedia:Getting_to_Philosophy"
-----------------------
href="/wiki/Special:RecentChangesLinked/Wikipedia:Getting_to_Philosophy"
-----------------------
href="/wiki/Wikipedia:File_Upload_Wizard"
-----------------------
href="/wiki/Special:SpecialPages"
-----------------------
href="/w/index.php?title=Wikipedia:Getting_to_Philosophy&oldid=645649870"
-----------------------
href="/w/index.php?title=Wikipedia:Getting_to_Philosophy&action=info"
-----------------------
href="//www.wikidata.org/wiki/Q14605740"
-----------------------
href="/w/index.php?title=Special:Book&bookcmd=book_creator&referer=Wikipedia:Getting+to+Philosophy"
-----------------------
href="/w/index.php?title=Special:Book&bookcmd=render_article&arttitle=Wikipedia:Getting+to+Philosophy&oldid=645649870&writer=rdf2latex"
-----------------------
href="/w/index.php?title=Wikipedia:Getting_to_Philosophy&printable=yes"
-----------------------
href="//fr.wikipedia.org/wiki/Wikipédia:Se_rendre_à_l'article_philosophie"
-----------------------
href="//uk.wikipedia.org/wiki/Вікіпедія:Всі_посилання_ведуть_до_філософії"
-----------------------
href="#"
-----------------------
href="//www.wikidata.org/wiki/Q14605740#sitelinks-wikipedia"
-----------------------
href="//en.wikipedia.org/wiki/Wikipedia:Text_of_Creative_Commons_Attribution-ShareAlike_3.0_Unported_License"
-----------------------
href="//creativecommons.org/licenses/by-sa/3.0/"
-----------------------
href="//wikimediafoundation.org/wiki/Terms_of_Use"
-----------------------
href="//wikimediafoundation.org/wiki/Privacy_policy"
-----------------------
href="//www.wikimediafoundation.org/"
-----------------------
href="//wikimediafoundation.org/wiki/Privacy_policy"
-----------------------
href="/wiki/Wikipedia:About"
-----------------------
href="/wiki/Wikipedia:General_disclaimer"
-----------------------
href="//en.wikipedia.org/wiki/Wikipedia:Contact_us"
-----------------------
href="https://www.mediawiki.org/wiki/Special:MyLanguage/How_to_contribute"
-----------------------
href="//en.m.wikipedia.org/w/index.php?title=Wikipedia:Getting_to_Philosophy&mobileaction=toggle_view_mobile"
-----------------------
href="//wikimediafoundation.org/"
-----------------------
href="//www.mediawiki.org/"
如果元素不是i
元素的后代，则查找href
元素的所有属性
结果集中节点的顺序可能因XPath 1.0的实现而异。使用兼容的XPath处理器将上述XPath表达式应用于中的结果（单个结果由----
分隔）：
谢谢！！我正试图解决这个问题，但不幸的是，您的xpath查询也没有以正确的顺序处理链接…还有其他建议吗？xpath是否以不同的顺序处理节点？@Wes欢迎您。很可能，您的xpath引擎只支持xpath 1.0。在版本1.0中，节点定义为集合（我还要指出），这意味着它们没有特定的顺序。但是，引擎通常会按文档顺序返回结果。您必须显示所有的PHP代码，并发布当前获得的结果，否则所有赌注都没有了。$this->html=curl\u exec（$this->curl）；//假设我正确设置了curl$dom=new DOMDocument（）；@$dom->loadHTML（$this->html）；$xpath=new DOMXpath（$dom）；$anchorlinks=$xpath->query（'//a[not（祖先：：I）]//@href'）；//echo”“；printr（迭代器到数组（$anchorlinks））；echo“”
如果目标url是，我得到的结果是“/wiki/fiber”、“/wiki/Natural\u fiber”、“/wiki/fiber”、“/wiki/Natural\u fiber”……它们应该是“/wiki/fibers”、“/wiki/Rope”@Wes我已将我的结果列表添加到我的答案中。你的结果与此相比如何？请不要在注释中添加代码或其他基本信息-始终编辑y我们的问题。
//a[not(ancestor::i)]/@href
href="#mw-head"
-----------------------
href="#p-search"
-----------------------
href="/wiki/File:Essay.svg"
-----------------------
href="/wiki/Wikipedia:Wikipedia_essays"
-----------------------
href="/wiki/Wikipedia:Policies_and_guidelines"
-----------------------
href="/wiki/Hyperlink"
-----------------------
href="/wiki/Wikipedia"
-----------------------
href="/wiki/Philosophy"
-----------------------
href="/wiki/Philosophy"
-----------------------
href="#cite_note-1"
-----------------------
href="/wiki/File:Crawl_on_Wikipedia_from_random_article_to_Philosophy..gif"
-----------------------
href="/wiki/File:Crawl_on_Wikipedia_from_random_article_to_Philosophy..gif"
-----------------------
href="/wiki/Document_classification"
-----------------------
href="/wiki/Wikipedia:MOSBEGIN"
-----------------------
href="/wiki/Mathematics"
-----------------------
href="/wiki/Science"
-----------------------
href="/wiki/Language"
-----------------------
href="/wiki/Philosophy"
-----------------------
href="#Method_summarized"
-----------------------
href="#Origins"
-----------------------
href="#Examples_of_exceptions_to_the_Getting_to_Philosophy_rule"
-----------------------
href="#See_also"
-----------------------
href="#References"
-----------------------
href="#External_links"
-----------------------
href="/w/index.php?title=Wikipedia:Getting_to_Philosophy&action=edit&section=1"
-----------------------
href="/w/index.php?title=Wikipedia:Getting_to_Philosophy&action=edit&section=2"
-----------------------
href="/wiki/Phenomenon"
-----------------------
href="/wiki/User:Mark_J"
-----------------------
href="#cite_note-2"
-----------------------
href="/wiki/Wikipedia:WikipediaWeekly/Episode50"
-----------------------
href="/wiki/Podcast"
-----------------------
href="#cite_note-3"
-----------------------
href="/w/index.php?title=Wikipedia:Getting_to_Philosophy&action=edit&section=3"
-----------------------
href="/wiki/Yarn"
-----------------------
href="/wiki/Fibres"
-----------------------
href="/wiki/Rope"
-----------------------
href="/w/index.php?title=Wikipedia:Getting_to_Philosophy&action=edit&section=4"
-----------------------
href="/wiki/Small-world_network"
-----------------------
href="/wiki/Attractor"
-----------------------
href="/wiki/Wikipedia:Wiki_Game"
-----------------------
href="/w/index.php?title=Wikipedia:Getting_to_Philosophy&action=edit&section=5"
-----------------------
href="#cite_ref-1"
-----------------------
href="/wiki/User:Ilmari_Karonen/First_link"
-----------------------
href="/wiki/Help:CS1_errors#cite_web_url"
-----------------------
href="#cite_ref-2"
-----------------------
href="http://en.wikipedia.org/w/index.php?title=Wikipedia:Getting_to_Philosophy&oldid=215744293"
-----------------------
href="#cite_ref-3"
-----------------------
href="http://huffduffer.com/psd/42471"
-----------------------
href="/w/index.php?title=Wikipedia:Getting_to_Philosophy&action=edit&section=6"
-----------------------
href="http://www.xefer.com/wikipedia"
-----------------------
href="http://www.youtube.com/watch?v=vehDe2lSptU"
-----------------------
href="/wiki/Philosophy"
-----------------------
href="http://matpalm.com/blog/2011/08/13/wikipedia-philosophy/"
-----------------------
href="http://xkcd.com/903/"
-----------------------
href="/wiki/Xkcd"
-----------------------
href="/wiki/Tooltip"
-----------------------
href="http://wikiloopr.com/"
-----------------------
href="http://www.guardian.co.uk/technology/2011/jul/10/only-way-essex-wikipedia-philosophy"
-----------------------
href="/wiki/The_Guardian"
-----------------------
href="http://www.huffingtonpost.com/2011/11/14/wikipedia-philosophy_n_1093460.html"
-----------------------
href="http://en.wikipedia.org/w/index.php?title=Wikipedia:Getting_to_Philosophy&oldid=645649870"
-----------------------
href="/wiki/Help:Category"
-----------------------
href="/wiki/Category:Wikipedia_essays"
-----------------------
href="/wiki/Category:Pages_using_web_citations_with_no_URL"
-----------------------
href="/w/index.php?title=Special:UserLogin&returnto=Wikipedia:Getting+to+Philosophy&type=signup"
-----------------------
href="/w/index.php?title=Special:UserLogin&returnto=Wikipedia:Getting+to+Philosophy"
-----------------------
href="/wiki/Wikipedia:Getting_to_Philosophy"
-----------------------
href="/wiki/Wikipedia_talk:Getting_to_Philosophy"
-----------------------
href="#"
-----------------------
href="/wiki/Wikipedia:Getting_to_Philosophy"
-----------------------
href="/w/index.php?title=Wikipedia:Getting_to_Philosophy&action=edit"
-----------------------
href="/w/index.php?title=Wikipedia:Getting_to_Philosophy&action=history"
-----------------------
href="#"
-----------------------
href="/wiki/Main_Page"
-----------------------
href="/wiki/Main_Page"
-----------------------
href="/wiki/Portal:Contents"
-----------------------
href="/wiki/Portal:Featured_content"
-----------------------
href="/wiki/Portal:Current_events"
-----------------------
href="/wiki/Special:Random"
-----------------------
href="https://donate.wikimedia.org/wiki/Special:FundraiserRedirector?utm_source=donate&utm_medium=sidebar&utm_campaign=C13_en.wikipedia.org&uselang=en"
-----------------------
href="//shop.wikimedia.org"
-----------------------
href="/wiki/Help:Contents"
-----------------------
href="/wiki/Wikipedia:About"
-----------------------
href="/wiki/Wikipedia:Community_portal"
-----------------------
href="/wiki/Special:RecentChanges"
-----------------------
href="//en.wikipedia.org/wiki/Wikipedia:Contact_us"
-----------------------
href="/wiki/Special:WhatLinksHere/Wikipedia:Getting_to_Philosophy"
-----------------------
href="/wiki/Special:RecentChangesLinked/Wikipedia:Getting_to_Philosophy"
-----------------------
href="/wiki/Wikipedia:File_Upload_Wizard"
-----------------------
href="/wiki/Special:SpecialPages"
-----------------------
href="/w/index.php?title=Wikipedia:Getting_to_Philosophy&oldid=645649870"
-----------------------
href="/w/index.php?title=Wikipedia:Getting_to_Philosophy&action=info"
-----------------------
href="//www.wikidata.org/wiki/Q14605740"
-----------------------
href="/w/index.php?title=Special:Book&bookcmd=book_creator&referer=Wikipedia:Getting+to+Philosophy"
-----------------------
href="/w/index.php?title=Special:Book&bookcmd=render_article&arttitle=Wikipedia:Getting+to+Philosophy&oldid=645649870&writer=rdf2latex"
-----------------------
href="/w/index.php?title=Wikipedia:Getting_to_Philosophy&printable=yes"
-----------------------
href="//fr.wikipedia.org/wiki/Wikipédia:Se_rendre_à_l'article_philosophie"
-----------------------
href="//uk.wikipedia.org/wiki/Вікіпедія:Всі_посилання_ведуть_до_філософії"
-----------------------
href="#"
-----------------------
href="//www.wikidata.org/wiki/Q14605740#sitelinks-wikipedia"
-----------------------
href="//en.wikipedia.org/wiki/Wikipedia:Text_of_Creative_Commons_Attribution-ShareAlike_3.0_Unported_License"
-----------------------
href="//creativecommons.org/licenses/by-sa/3.0/"
-----------------------
href="//wikimediafoundation.org/wiki/Terms_of_Use"
-----------------------
href="//wikimediafoundation.org/wiki/Privacy_policy"
-----------------------
href="//www.wikimediafoundation.org/"
-----------------------
href="//wikimediafoundation.org/wiki/Privacy_policy"
-----------------------
href="/wiki/Wikipedia:About"
-----------------------
href="/wiki/Wikipedia:General_disclaimer"
-----------------------
href="//en.wikipedia.org/wiki/Wikipedia:Contact_us"
-----------------------
href="https://www.mediawiki.org/wiki/Special:MyLanguage/How_to_contribute"
-----------------------
href="//en.m.wikipedia.org/w/index.php?title=Wikipedia:Getting_to_Philosophy&mobileaction=toggle_view_mobile"
-----------------------
href="//wikimediafoundation.org/"
-----------------------
href="//www.mediawiki.org/"