Last active
December 15, 2015 05:39
-
-
Save cloudsben/5210427 to your computer and use it in GitHub Desktop.
/*
获取指定URL的HTML,如果页面是非UTF-8编码,会自动转换为UTF-8编码
若指定网址的content-type不是text/html,则不会抓取网页内容
return: array url: 若有301/302,返回跳转后的url html: base_url: error: */
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<?php | |
if ( ! function_exists('http_get_utf8_html')) | |
{ | |
function http_get_utf8_html($url,$from_encoding='') | |
{ | |
$result = array(); | |
$result['url'] = $url; | |
$result['html'] = ''; | |
$header = get_headers_by_curl($url); | |
$url = $header['url']; | |
/* 很多页面在用HEAD方法只获取HTTP头是会返回404,因此注释此段 | |
if($header['http_code']!=200) | |
{ | |
$result['error'] = 'http_code:'.$header['http_code']; | |
return $result; | |
} | |
*/ | |
$content_type = trim($header['content_type']); | |
$encoding = null; | |
if($content_type) | |
{ | |
preg_match('/^\s*([^;]+)(?:;\s*charset=(.*))?/im', $content_type, $match); | |
$ctype = $match[1]; | |
if(count($match)>2) | |
{ | |
$encoding = strtolower(trim($match[2], '"\'')); | |
} | |
} | |
if(strpos($ctype,'text')===false and strpos($ctype,'xml')===false) | |
{ | |
$result['error'] = 'content-type:'.$ctype; | |
return $result; | |
} | |
$header = array( | |
'Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', | |
'Accept-Charset: ISO-8859-1,utf-8;q=0.7,*;q=0.3', | |
); | |
$ch = curl_init($url); | |
curl_setopt($ch, CURLOPT_SSL_VERIFYPEER,false); | |
curl_setopt($ch, CURLOPT_VERBOSE, false); | |
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); | |
curl_setopt($ch, CURLOPT_FOLLOWLOCATION,false); //是否抓取跳转后的页面 | |
curl_setopt($ch, CURLOPT_HEADER, false); | |
curl_setopt($ch, CURLOPT_USERAGENT, USER_AGENT); | |
curl_setopt($ch, CURLOPT_TIMEOUT, 15); | |
curl_setopt($ch, CURLOPT_HTTPHEADER, $header); | |
$body = curl_exec($ch); | |
$headers = curl_getinfo($ch); | |
curl_close($ch); | |
if($headers['http_code']!=200) | |
{ | |
$result['error'] = 'http_code:'.$headers['http_code']; | |
return $result; | |
} | |
if($body) | |
{ | |
if (!$encoding and !$from_encoding) { | |
if (preg_match('/^<\?xml\s+version=(?:"[^"]*"|\'[^\']*\')\s+encoding=("[^"]*"|\'[^\']*\')/s', $body, $match)) { | |
$encoding = strtolower(trim($match[1], '"\'')); | |
} | |
if (preg_match('/<meta.+?content="([^;]+)(?:;\s*charset=["]?([^"^\s]*))?"/i', $body, $match)) | |
{ | |
$encoding = strtolower(trim($match[2], '"\'')); | |
} | |
} | |
if($from_encoding) | |
{ | |
$encoding = $from_encoding; | |
} | |
if($encoding=='gb2312') $encoding = 'gbk'; | |
//转换页面编码 | |
if ($encoding != 'utf-8' and in_array($encoding,array('gbk','gb2312')) ) { | |
$body = mb_convert_encoding($body, 'utf-8', $encoding); | |
} | |
$result['url'] = $url; | |
$base_url = preg_replace('#/[^/]*$#', '', $url); | |
if(substr($base_url,-1,1)!="/") $base_url.='/'; | |
//转换页面链接来源为绝对地址 | |
$body = make_all_url_absolute($body,$base_url); | |
$result['html'] = $body; | |
$result['base_url']= $base_url; | |
} | |
return $result; | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment