php获取百度下拉词
时间:2023年10月05日
/来源:网络
/编辑:佚名
有些时候在做SEO的时候想要使用程序来自动修改标题,这时候可以用到百度下拉词库来自动匹配修改,以下是一段获取百度词库的PHP代码
//获取百度下拉信息
$title = urlencode($data['title']);
$api = "https://www.baidu.com/sugrec?pre=1&p=1&ie=utf-8&prod=pc&csor=2&wd=".$title."";
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $api);
curl_setopt($ch, CURLOPT_TIMEOUT, 5);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
$r = curl_exec($ch);
curl_close($ch);
$r = json_decode($r,true);
if(empty($r['g'])){
$new_title = $data['title'].'(图文)';
}
//数据一定存在,取出数据,然后随机获取一个
$baidu_title = $r['g'][mt_rand(0,count($r['g'])-1)]['q'];//数据的随机获取
$baidu_title2 = $r['g'][mt_rand(0,count($r['g'])-1)]['q'];//数据的随机获取
$baidu_title = $baidu_title==$data['title']?$r['g'][mt_rand(0,count($r['g'])-1)]['q']:$baidu_title;//数据随机,防止与原标题一样
$baidu_title2 = $baidu_title==$baidu_title2?$r['g'][mt_rand(0,count($r['g'])-1)]['q']:$baidu_title2;//数据随机,防止与第一个百度标题一样
优化后的代码:
<?php
// 获取百度下拉信息
$title = urlencode($data['title']);
$api = "https://www.baidu.com/sugrec?pre=1&p=1&ie=utf-8&prod=pc&csor=2&wd=".$title."";
$ch = curl_init();
curl_setopt_array($ch, [
CURLOPT_URL => $api,
CURLOPT_TIMEOUT => 5,
CURLOPT_RETURNTRANSFER => true,
]);
$r = curl_exec($ch);
curl_close($ch);
$r = json_decode($r, true);
// 检查是否为空,如果为空,则添加后缀到标题中
if (empty($r['g'])) {
$new_title = $data['title'] . ' (图文)';
}
// 从建议中获取随机标题
$titles = array_column($r['g'], 'q');
$random_title = $titles[array_rand($titles)];
// 避免与原始标题和先前的建议重复
if ($random_title == $data['title'] || $random_title == $baidu_title) {
$random_title = $titles[array_rand($titles)];
}
$baidu_title = $random_title;
$baidu_title2 = $titles[array_rand($titles)];
if ($baidu_title2 == $baidu_title) {
$baidu_title2 = $titles[array_rand($titles)];
}
代码的改进包括:
使用数组来存储随机标题选项,以避免重复
使用 array_column 提取响应中的标题
使用 array_rand 从选项数组中获取随机标题
简化了避免与原始标题和先前建议重复的代码
使用数组参数设置 curl 选项,以提高可读性和可维护性
根据上面上面的代码封装成函数,传入中文标题后,如果成功获取下拉则返回下拉数组,获取为空则返回false
function getBaiduSuggestion($title) {
$title = urlencode($title);
$api = "https://www.baidu.com/sugrec?pre=1&p=1&ie=utf-8&prod=pc&csor=2&wd=".$title."";
$ch = curl_init();
curl_setopt_array($ch, [
CURLOPT_URL => $api,
CURLOPT_TIMEOUT => 5,
CURLOPT_RETURNTRANSFER => true,
]);
$r = curl_exec($ch);
curl_close($ch);
$r = json_decode($r, true);
if (!empty($r['g'])) {
$titles = array_column($r['g'], 'q');
$baidu_title = $titles[array_rand($titles)];
if ($baidu_title == $title) {
$baidu_title = $titles[array_rand($titles)];
}
$baidu_title2 = $titles[array_rand($titles)];
if ($baidu_title2 == $baidu_title) {
$baidu_title2 = $titles[array_rand($titles)];
}
return [$baidu_title, $baidu_title2];
} else {
return false;
}
}
根据自己的需求将代码改了改:
function getBaiduSuggestion($title) {
$title = urlencode($title);
$api = "https://www.baidu.com/sugrec?pre=1&p=1&ie=utf-8&prod=pc&csor=2&wd=".$title."";
$ch = curl_init();
curl_setopt_array($ch, [
CURLOPT_URL => $api,
CURLOPT_TIMEOUT => 5,
CURLOPT_RETURNTRANSFER => true,
]);
$r = curl_exec($ch);
curl_close($ch);
$r = json_decode($r, true);
if (!empty($r['g'])) {
return array_column($r['g'], 'q');
} else {
return false;
}
}
//获取百度下拉信息
$title = urlencode($data['title']);
$api = "https://www.baidu.com/sugrec?pre=1&p=1&ie=utf-8&prod=pc&csor=2&wd=".$title."";
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $api);
curl_setopt($ch, CURLOPT_TIMEOUT, 5);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
$r = curl_exec($ch);
curl_close($ch);
$r = json_decode($r,true);
if(empty($r['g'])){
$new_title = $data['title'].'(图文)';
}
//数据一定存在,取出数据,然后随机获取一个
$baidu_title = $r['g'][mt_rand(0,count($r['g'])-1)]['q'];//数据的随机获取
$baidu_title2 = $r['g'][mt_rand(0,count($r['g'])-1)]['q'];//数据的随机获取
$baidu_title = $baidu_title==$data['title']?$r['g'][mt_rand(0,count($r['g'])-1)]['q']:$baidu_title;//数据随机,防止与原标题一样
$baidu_title2 = $baidu_title==$baidu_title2?$r['g'][mt_rand(0,count($r['g'])-1)]['q']:$baidu_title2;//数据随机,防止与第一个百度标题一样
优化后的代码:
<?php
// 获取百度下拉信息
$title = urlencode($data['title']);
$api = "https://www.baidu.com/sugrec?pre=1&p=1&ie=utf-8&prod=pc&csor=2&wd=".$title."";
$ch = curl_init();
curl_setopt_array($ch, [
CURLOPT_URL => $api,
CURLOPT_TIMEOUT => 5,
CURLOPT_RETURNTRANSFER => true,
]);
$r = curl_exec($ch);
curl_close($ch);
$r = json_decode($r, true);
// 检查是否为空,如果为空,则添加后缀到标题中
if (empty($r['g'])) {
$new_title = $data['title'] . ' (图文)';
}
// 从建议中获取随机标题
$titles = array_column($r['g'], 'q');
$random_title = $titles[array_rand($titles)];
// 避免与原始标题和先前的建议重复
if ($random_title == $data['title'] || $random_title == $baidu_title) {
$random_title = $titles[array_rand($titles)];
}
$baidu_title = $random_title;
$baidu_title2 = $titles[array_rand($titles)];
if ($baidu_title2 == $baidu_title) {
$baidu_title2 = $titles[array_rand($titles)];
}
代码的改进包括:
使用数组来存储随机标题选项,以避免重复
使用 array_column 提取响应中的标题
使用 array_rand 从选项数组中获取随机标题
简化了避免与原始标题和先前建议重复的代码
使用数组参数设置 curl 选项,以提高可读性和可维护性
根据上面上面的代码封装成函数,传入中文标题后,如果成功获取下拉则返回下拉数组,获取为空则返回false
function getBaiduSuggestion($title) {
$title = urlencode($title);
$api = "https://www.baidu.com/sugrec?pre=1&p=1&ie=utf-8&prod=pc&csor=2&wd=".$title."";
$ch = curl_init();
curl_setopt_array($ch, [
CURLOPT_URL => $api,
CURLOPT_TIMEOUT => 5,
CURLOPT_RETURNTRANSFER => true,
]);
$r = curl_exec($ch);
curl_close($ch);
$r = json_decode($r, true);
if (!empty($r['g'])) {
$titles = array_column($r['g'], 'q');
$baidu_title = $titles[array_rand($titles)];
if ($baidu_title == $title) {
$baidu_title = $titles[array_rand($titles)];
}
$baidu_title2 = $titles[array_rand($titles)];
if ($baidu_title2 == $baidu_title) {
$baidu_title2 = $titles[array_rand($titles)];
}
return [$baidu_title, $baidu_title2];
} else {
return false;
}
}
根据自己的需求将代码改了改:
function getBaiduSuggestion($title) {
$title = urlencode($title);
$api = "https://www.baidu.com/sugrec?pre=1&p=1&ie=utf-8&prod=pc&csor=2&wd=".$title."";
$ch = curl_init();
curl_setopt_array($ch, [
CURLOPT_URL => $api,
CURLOPT_TIMEOUT => 5,
CURLOPT_RETURNTRANSFER => true,
]);
$r = curl_exec($ch);
curl_close($ch);
$r = json_decode($r, true);
if (!empty($r['g'])) {
return array_column($r['g'], 'q');
} else {
return false;
}
}
新闻资讯 更多
- 【建站知识】查询nginx日志状态码大于400的请求并打印整行04-03
- 【建站知识】Python中的logger和handler到底是个什么?04-03
- 【建站知识】python3拉勾网爬虫之(您操作太频繁,请稍后访问)04-03
- 【建站知识】xpath 获取meta里的keywords及description的方法04-03
- 【建站知识】python向上取整以50为界04-03
- 【建站知识】scrapy xpath遇见乱码解决04-03
- 【建站知识】scrapy爬取后中文乱码,解决word转为html 时cp1252编码问题04-03
- 【建站知识】scrapy采集—爬取中文乱码,gb2312转为utf-804-03