PHP爬蟲 -- 017 實戰2 爬取貓眼電影top100

時間 2019-11-26

標籤 php 爬蟲實戰貓眼 top100 欄目 PHP 简体版

原文原文鏈接

分析網站

貓眼top100: maoyan.com/board/4?off…

須要爬取的數據

先創建數據表, 用來保存電影數據

CREATE TABLE `movies` (
  `id` int(11) NOT NULL AUTO_INCREMENT,
  `title` varchar(255) NOT NULL,
  `rank` varchar(255) NOT NULL,
  `score` varchar(255) NOT NULL,
  `actor` varchar(255) NOT NULL,
  `date` varchar(255) NOT NULL,
  `img` varchar(255) NOT NULL,
  PRIMARY KEY (`id`)
) ENGINE=MyISAM DEFAULT CHARSET=utf8;
複製代碼

使用IP代理池獲取數據, 並打印輸出

<?php

require 'vendor/autoload.php';
use QL\QueryList;
$base = "https://maoyan.com/board/4?offset=";

for ($i=0; $i < 10; $i++) { 
    $page = $i*10;
    $url = $base.$page;
    echo $url."\n";
    get_content($url);
}

function get_content($url){
    
    $data = QueryList::html(get_html_source($url))->rules([
        'title'=>['#app > div > div > div.main > dl > dd > div > div > div.movie-item-info > p.name > a','title'],
        'rank'=>['#app > div > div > div.main > dl > dd > i','text'],
        'img'=>['#app > div > div > div.main > dl > dd > a > img.board-img','data-src'],
        'actor'=>['#app > div > div > div.main > dl > dd > div > div > div.movie-item-info > p.star','text'],
        'date'=>['#app > div > div > div.main > dl > dd> div > div > div.movie-item-info > p.releasetime','text'],
        'score'=>['#app > div > div > div.main > dl > dd > div > div > div.movie-item-number.score-num > p','text'],
    ])->queryData();
    var_dump($data);
}
function get_html_source($url) {
    // 要訪問的目標頁面
    $targetUrl = $url;
    // 代理服務器
    $proxyServer = "http://http-dyn.abuyun.com:9020";
    // 隧道身份信息
    $proxyUser = "H19D75L76VK89Q8D";
    $proxyPass = "8C17B0A80F475BD8";
    $ch = curl_init();
    curl_setopt($ch, CURLOPT_URL, $targetUrl);
    curl_setopt($ch, CURLOPT_HTTPPROXYTUNNEL, false);
    curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);
    // 設置代理服務器
    curl_setopt($ch, CURLOPT_PROXYTYPE, CURLPROXY_HTTP);
    curl_setopt($ch, CURLOPT_PROXY, $proxyServer);
    // 設置隧道驗證信息
    curl_setopt($ch, CURLOPT_PROXYAUTH, CURLAUTH_BASIC);
    curl_setopt($ch, CURLOPT_PROXYUSERPWD, "{$proxyUser}:{$proxyPass}");
    curl_setopt($ch, CURLOPT_USERAGENT, "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 2.0.50727;)");
    curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, 3);
    curl_setopt($ch, CURLOPT_TIMEOUT, 5);
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
    $result = curl_exec($ch);
    //$info = curl_getinfo($ch);
    curl_close($ch);
    return $result;
}
複製代碼

把數據保存到數據庫

<?php
require 'vendor/autoload.php';
use QL\QueryList;
use Medoo\Medoo;
// 建立數據庫鏈接
$database = new medoo([
    'database_type' => 'mysql',
    'database_name' => 'demo_db',
    'server' => 'localhost',
    'username' => 'root',
    'password' => 'root',
    'charset' => 'utf8',
]);



/* * @Description: 從html頁面中經過css選擇器, 獲取咱們想要的數據 * @param: 目標url * @return: 包含咱們須要數據的二維數組 */ 
function get_data($url) {
    echo "function get_data is running ... \n";
    $data = QueryList::html(get_html_source($url))->rules([
        "img" => ['#app > div > div > div.main > dl > dd > a > img.board-img', 'data-src'],
        "actor" => ['#app > div > div > div.main > dl > dd > div > div > div.movie-item-info > p.star', 'text'],
        "date" => ['#app > div > div > div.main > dl > dd > div > div > div.movie-item-info > p.releasetime', 'text'],
        "rank" => ['#app > div > div > div.main > dl > dd > i', 'text'],
        "score" => ['#app > div > div > div.main > dl > dd > div > div > div.movie-item-number.score-num > p', 'text'],
        "title" => ['#app > div > div > div.main > dl > dd > div > div > div.movie-item-info > p.name > a', 'text'],
    ])->queryData();
    return $data;
}

/* * @Description: 保存數據到電影表, 傳一個二維數組, 批量插入 * @param: 二維數組 * @return: 沒有返回值 */ 
function save_movie($data){
    echo "function save_movie is running ... \n";
    global $database;
    $database->insert('movies',$data);
}

/* * @Description: 使用IP代理, 獲取html代碼 * @param: 目標url * @return: html代碼 */ 
function get_html_source($url) {
    echo "function get_html_source is running ... \n";
    $result = false;
    while (!$result) {
        $targetUrl = $url;
        $proxyServer = "http://http-dyn.abuyun.com:9020";
        $proxyUser = "H19D75L76VK89Q8D";
        $proxyPass = "8C17B0A80F475BD8";
        $ch = curl_init();
        curl_setopt($ch, CURLOPT_URL, $targetUrl);
        curl_setopt($ch, CURLOPT_HTTPPROXYTUNNEL, false);
        curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);
        curl_setopt($ch, CURLOPT_PROXYTYPE, CURLPROXY_HTTP);
        curl_setopt($ch, CURLOPT_PROXY, $proxyServer);
        curl_setopt($ch, CURLOPT_PROXYAUTH, CURLAUTH_BASIC);
        curl_setopt($ch, CURLOPT_PROXYUSERPWD, "{$proxyUser}:{$proxyPass}");
        curl_setopt($ch, CURLOPT_USERAGENT, "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 2.0.50727;)");
        curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, 3);
        curl_setopt($ch, CURLOPT_TIMEOUT, 5);
        curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
        $result = curl_exec($ch);
        if (!$result) {
            sleep(2);
        }
        curl_close($ch);
    }
    return $result;
}


// 基礎的url, 爲後面拼接具體的url作準備
$base_url = "https://maoyan.com/board/4?offset=";
// 只修改最後的數字, 拼接出來10條url
for ($i = 0; $i < 100; $i += 10) {
    $current_url = $base_url . $i;
    echo $current_url;
    $data = get_data($current_url);
    save_movie($data);
}
複製代碼

提取數據並生成markdown文檔

<?php
require 'vendor\autoload.php';
use Medoo\Medoo;
// 建立數據庫鏈接
$database = new medoo([
    'database_type' => 'mysql',
    'database_name' => 'demo_db',
    'server' => 'localhost',
    'username' => 'root',
    'password' => 'root',
    'charset' => 'utf8',
]);
/* * @Description: 從數據庫中取出電影的相關信息 * @return: 二維數組 */ 
function get_data(){
    global $database;
    $data = $database->select('movies','*');
    return $data;
}
/* * @Description: 生成markdown文件 * @param: 二維數組(電影信息) * @return: 沒有返回值 */ 
function make_markdown($data){
    $md_obj = fopen('maoyanmd.md','w+');
    foreach ($data as $key => $value) {
        $img = $value['img'];
        $img = str_replace("@160w_220h_1e_1c","@320w_440h_1e_1c",$img);
        $rank = $value['rank'];
        $title = $value['title'];
        $score = $value['score'];
        $date = $value['date'];
        $actor = $value['actor'];
        fwrite($md_obj,"![]({$img})\n");
        fwrite($md_obj,"## {$rank}-{$title}-{$score}\n");
        fwrite($md_obj,"> {$date}\n");
        fwrite($md_obj,"> {$actor}\n");
        fwrite($md_obj,"---\n\n\n");
    }
    fclose($md_obj);
}


make_markdown(get_data());
複製代碼