糖尿病康复,内容丰富有趣,生活中的好帮手!
糖尿病康复 > 百度 360 搜狗 神马的SEO搜索结果php爬取排名。

百度 360 搜狗 神马的SEO搜索结果php爬取排名。

时间:2020-10-17 09:24:50

相关推荐

百度 360 搜狗 神马的SEO搜索结果php爬取排名。

1.百度请求链接

/s?sa=tb&ts=3706509&t_kt=0&ie=utf-8&rsv_iqid=0097572279&rsv_t=773fQuIl7f3OmEVcEZlyJas2A2BF3%252FCbSUw09yYuylEa2exL1dKn&sa=ib&rsv_pq=0097572279&rsv_sug4=7799&inputT=4471&sugid=4422540089986279028&ss=100&tj=1&word=如何重装系统&oq=如何重装系统

2.360请求链接

/s?src=msearch_next_input&sug_pos=&sug=&nlpv=&ssid=&srcg=home_next&q=如何重装系统

3.搜狗请求链接

/s?from=smor&safe=1&snum=6&q=如何重装系统

4.神马请求链接

/web/searchList.jsp?keyword=如何重装系统

function getSearchData($url = '', $type = 'baidu')

{

$ch = curl_init();

curl_setopt($ch, CURLOPT_URL, $url);

curl_setopt($ch, CURLOPT_HEADER, false);

curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);

curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);

$timeout = 3;

curl_setopt($ch, CURLOPT_TIMEOUT, $timeout);

switch ($type) {

case 'baidu': //百度

// 百度只要设置这个,目前没遇到ip限制

curl_setopt($ch, CURLOPT_USERAGENT, 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.1 Safari/537.11'); //百度可以用

break;

case 'so': //360

curl_setopt($ch, CURLOPT_FOLLOWLOCATION ,1); //加入重定向处理

// 设置cookie 用验证过的cookie 预计每天更新一次

curl_setopt($ch, CURLOPT_COOKIE, 'QiHooGUID=B7D6552FB1C344B346FCC1174A67F71A.1598950767471; __guid=15484592.902187674292818400.1598950768236.8838; __md=0368dd03f34bf215989507690306c7f326d0577038ebdcf.12; so_md=0368dd03f34bf215989507690306c7f326d0577038ebdcf.12; so_huid=11EPEdKBqMJBeiNc0hIEWJWNH83QSaVJ%2F%2Byvfwapylv%2FM%3D; __huid=11EPEdKBqMJBeiNc0hIEWJWNH83QSaVJ%2F%2Byvfwapylv%2FM%3D; stc_ls_sa=M2ha6RiGO2jKQAk6o8B(lZ)A; env_webp=1; mso_ext=1903!1!1; __gid=72253007.916749197.1599098517639.1599098518573.12; opqopq=57081bf3f954084a438922b574664dfd.1599804933; _S=96qp8lf3qennc14ua3dacd4n6k; 490f8229fdb00c70e471587ce00c934e=1599804954');

curl_setopt($ch, CURLOPT_USERAGENT, getRandUseragent()); //360随机替换

curl_setopt($ch, CURLOPT_REFERER, ""); //构造来路

break;

case 'sm': //神马 目前就神马比较麻烦,需要研究看看怎么优化

curl_setopt($ch, CURLOPT_FOLLOWLOCATION ,1); //加入重定向处理

/****************可以短暂临时的使用 start***********/

// 对不同浏览器的频率限制是分开的,这浏览器的cookie不行了,换一个浏览器又会可以

// 设置cookie 神马用验证过的cookie 预计每半小时更新一次 cookie要跟user-agent相对应

$header = array(

"Cookie:sm_uuid=c91ccaace76e591c473669571de75017%7C%7C%7C1599105461; sm_diu=c91ccaace76e591c473669571de75017%7C%7C11eeeeee4e4178a4dd%7C1599105461; cna=cECyF5wt6zACAXFAYl7bEhDV; isg=BDs7ytJn4CCOx9ymdJ_Qj_u2yR-lkE-SuQJyZS34EDpRjFtutWPL4o7OoqzCt6eK; _uab_collina=159911462041806459614869; sm_sid=7d5e3711abf734eef1f9f9dfa4f1e262; phid=7d5e3711abf734eef1f9f9dfa4f1e262; tsid=7d5e3711abf734eef1f9f9dfa4f1e262; x5sec=7b2277616762726964676561643b32223a22313330663538376466333065346633326434393838613230613161653663346243492f756976734645506273372b3235794a50393777453d227d", //预计每半小时更新一次

//"User-Agent: Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Mobile Safari/537.36", //360

"User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:80.0) Gecko/0101 Firefox/80.0", //火狐

// "User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.83 Safari/537.36", //谷歌

// "User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko", //IE

);

curl_setopt($ch, CURLOPT_HTTPHEADER, $header);

/****************可以短暂临时的使用 end***********/

break;

case 'new_ips': //使用代理ip,可以绕过所有验证,不过各大代理ip的网速都很慢,效率太低了

curl_setopt($ch, CURLOPT_USERAGENT, getRandUseragent()); //360随机替换

break;

case 'sogou': //搜狗

curl_setopt($ch, CURLOPT_FOLLOWLOCATION ,1); //加入重定向处理

$header = array(

"Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",

"Accept-Encoding: deflate, br",

"Accept-Encoding: gunzip",

"Accept-Language zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2",

"Cache-Control: max-age=0",

"Connection: keep-alive",

"Cookie: IPLOC=CN4414; SUID=D26340715218910A000000005F4E0D59; SUV=1598950749102892; usid=CyVNYdjKPOlJ3dL1; ABTEST=0|1599115673|v1; SNUID=C209708B1316BC44C109FBCE13BA2E21; wuid=AAH9sFYJMQAAAAqHGF+0ZAEAkwA=; CXID=99B3508887B7DDDE15A5C0C5CE5963A3; ugid=89; FREQUENCY=1599115684815_114; front_screen_resolution=1920*1080; ld=zZllllllll2KUJpklllllVdkAIcllllltUxyykllllwlllllRZlll5@@@@@@@@@@; sgwtype=3; pgv_pvi=8502525952; JSESSIONID=aaavbZM66GjkI40r1UQqx; pgv_si=s3318787072; SESSION_CAPTCHA=ia647mvj4e1j03r4mfjh44q2855", //预计每小时更新一次

"Host: ",

"Upgrade-Insecure-Requests: 1",

"User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:80.0) Gecko/0101 Firefox/80.0",

);

curl_setopt($ch, CURLOPT_HTTPHEADER, $header);

break;

default:

curl_setopt($ch, CURLOPT_USERAGENT, 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.1 Safari/537.11'); //百度可以用

break;

}

$res = curl_exec($ch);

curl_close($ch);

return $res; //返回字符串 再用正则对数据进行处理

}

/**

* 获取随机的useragent

**/

function getRandUseragent() {

$useragent = array(

'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0)',

'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.2)',

'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)',

'Mozilla/5.0 (Windows; U; Windows NT 5.2) Gecko/070208 Firefox/3.0.1',

'Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/0309 Firefox/2.0.0.3',

'Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/0803 Firefox/1.5.0.12',

'Opera/9.27 (Windows NT 5.2; U; zh-cn)',

'Opera/8.0 (Macintosh; PPC Mac OS X; U; en)',

'Mozilla/5.0 (Macintosh; PPC Mac OS X; U; en) Opera 8.0',

'Mozilla/5.0 (Windows; U; Windows NT 5.2) AppleWebKit/525.13 (KHTML, like Gecko) Chrome/0.2.149.27 Safari/525.13',

'Mozilla/5.0 (Windows; U; Windows NT 5.2) AppleWebKit/525.13 (KHTML, like Gecko) Version/3.1 Safari/525.13',

'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.1 Safari/537.11',

'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.12) Gecko/0219 Firefox/2.0.0.12 Navigator/9.0.0.6',

'Mozilla/5.0 (iPhone; U; CPU like Mac OS X) AppleWebKit/420.1 (KHTML, like Gecko) Version/3.0 Mobile/4A93 Safari/419.3',

// 网上搜索的

"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36",

"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.133 Safari/537.36",

"Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",

"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",

"Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",

"Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",

"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",

"Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/0215 K-Ninja/2.1.1",

"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/0705 Firefox/3.0 Kapiko/3.0",

"Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",

"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",

"Mozilla/5.0 (Windows; U; Windows NT 5.2) Gecko/070208 Firefox/3.0.1",

"Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/0309 Firefox/2.0.0.3",

"Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/0803 Firefox/1.5.0.12",

"Opera/9.27 (Windows NT 5.2; U; zh-cn)",

"Mozilla/5.0 (Windows; U; Windows NT 5.2) AppleWebKit/525.13 (KHTML, like Gecko) Version/3.1 Safari/525.13",

"Mozilla/5.0 (Windows; U; Windows NT 5.2) AppleWebKit/525.13 (KHTML, like Gecko) Chrome/0.2.149.27 ",

"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_6; en-US) AppleWebKit/530.9 (KHTML, like Gecko) Chrome/ Safari/530.9 ",

"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",

"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)",

"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.11 (KHTML, like Gecko) Ubuntu/11.10 Chromium/27.0.1453.93 Chrome/27.0.1453.93 Safari/537.36",

"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.93 Safari/537.36",

"Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.94 Safari/537.36",

'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.186 Safari/537.36',

//PC端的UserAgent

"Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11",

"Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",

"Mozilla/5.0 (Windows NT 10.0; WOW64; rv:38.0) Gecko/0101 Firefox/38.0",

"Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.30729; .NET CLR 3.5.30729; InfoPath.3; rv:11.0) like Gecko",

"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0",

"Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)",

"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)",

"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)",

"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/0101 Firefox/4.0.1",

"Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/0101 Firefox/4.0.1",

"Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",

"Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",

"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",

"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)",

"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)",

"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",

"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)",

"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)",

"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)",

"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)",

"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",

//移动端口

"Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",

"Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",

"Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",

"Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",

"MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",

"Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10",

"Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13",

"Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; en) AppleWebKit/534.1+ (KHTML, like Gecko) Version/6.0.0.337 Mobile Safari/534.1+",

"Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.0; U; en-US) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/233.70 Safari/534.6 TouchPad/1.0",

"NOKIA5700/ UCWEB7.0.2.37/28/999",

"Openwave/ UCWEB7.0.2.37/28/999",

"Mozilla/4.0 (compatible; MSIE 6.0; ) Opera/UCWEB7.0.2.37/28/999",

"Mozilla/5.0 (Linux; Android 6.0; 1503-M02 Build/MRA58K) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/37.0.0.0 Mobile MQQBrowser/6.2 TBS/036558 Safari/537.36 MicroMessenger/6.3.25.861 NetType/WIFI Language/zh_CN",

);

return array_rand($useragent);

}

如果觉得《百度 360 搜狗 神马的SEO搜索结果php爬取排名。》对你有帮助,请点赞、收藏,并留下你的观点哦!

本内容不代表本网观点和政治立场,如有侵犯你的权益请联系我们处理。
网友评论
网友评论仅供其表达个人看法,并不表明网站立场。