获取微博排行榜是获取微博html页面的数据，而非直接调用微博后端接口获取
PHP实现
class WeiBoHotSearchService extends BaseService
{/*** 微博热搜缓存过期时间* @var int*/protected int $expireTime = 600;/*** 微博热搜URL* @var string*/protected string $domainUrl = 'https://s.weibo.com';/*** URL内容* @var mixed|null*/protected mixed $output = null;/*** 热搜列表* @var array*/protected array $hotSearchList = [];/*** 缓存key* @var string*/protected string $key = 'WEIBO_HOT_SEARCH_LIST_CACHE';/*** 微博热搜Cookie* @var string*/protected string $cookie = 'SUB=1;_s_tentry=weibo.com;';/*** 微博热搜url* @var string*/protected string $url = 'https://s.weibo.com/top/summary?cate=realtimehot';/*** 获取微博热搜列表缓存* @return array|array[]|mixed*/public function getWeiBoHotSearchListCache(){$str = RedisUtil::getInstance()->get($this->key);if (!empty($str)) {return json_decode($str, true);} else {return $this->refreshWeiboHotSearch();}}/*** 刷新微博热搜列表缓存* @return array|array[]*/public function refreshWeiboHotSearch(){try {$output = HttpUtil::getInstance()->getUrlContent($this->url, $this->cookie);// 获取html元素中table表格preg_match_all('/<table>[\s\S]*?<\/table>/i', $output, $match);// 获取table表格$table = $match[0][0];// 去除table标签$table = preg_replace("'<table[^>]*?>'si", "", $table);// 去除tr标签$table = preg_replace("'<tr[^>]*?>'si", "", $table);// 去除td标签$table = preg_replace("'<td[^>]*?>'si", "", $table);// 将tr标签替换为{tr}$table = str_replace("</tr>", "{tr}", $table);// 将td标签替换为{td}$table = str_replace("</td>", "{td}", $table);//去掉剩余HTML元素并将<a>标签保留是为了拿到跳转链接$table = preg_replace("/<(?!a\b|\/a\b)[^>]*>/i", "", $table);//去掉空白字符$table = preg_replace("'([rn])[s]+'", "", $table);// 去除空格
// $table = str_replace(" ", "", $table);// 将table标签按照{tr}拆分$table = explode('{tr}', $table);foreach ($table as $key => $value) {// 自己可添加对应的替换$tr = str_replace("\n", "", $value);// 去除数组中的<!--{td}-->$tr = preg_replace("<!--{td}-->", "", $tr);$td = explode('{td}', $tr);$td_array[] = $td;}// 删除数组第一项，删除数组最后一项array_shift($td_array);array_pop($td_array);// 处理数组$this->hotSearchList = array_map(function ($item) {// 第二项$item[1] = get_href_content_dom($item[1],$this->domainUrl);$item[2] = trim($item[2]);// 将二三项合并$item[1]['tip'] = $item[2];return $item[1];}, $td_array);Log::record("微博热搜获取数据成功" . json_encode($this->hotSearchList), 'info');} catch (Exception $e) {Log::record("微博热搜获取数据异常" . $e->getMessage(), 'error');}RedisUtil::getInstance()->set($this->key, json_encode($this->hotSearchList), $this->expireTime);return $this->hotSearchList;}
}上面的RedisUtil就是一个工具类，其中只用了String类型的set和get方法
下期使用Python实现