ubuntu 中未提取人偶脚本的内容

Question

场景 - 我有一个木偶脚本，它接收一个 url 和一个 json 对象作为执行参数。 - 从 html 文件的 php 脚本中调用它 - puppeteer 脚本转到 url，获取页面内容，console.log s 它，因此内容在包含上述 php 脚本的 html 中可用.

问题 - 在 windows 上它是运行完美的，给出了所需的输出。然而，我现在已经将我的项目转移到 ubuntu，这就是麻烦开始的地方。 - 内容未加载，以空白页结束。 - 我运行来自控制台的 puppeteer 脚本，它运行良好，注销页面内容。但是当我使用 system() 从 php 脚本调用它时，它没有。但即使在 php 脚本中，它也能在 windows 上完美运行。

这是我的 php 代码

    <?php
    if(isset($_POST['url'])){
        $split_url = str_replace('.', '_', explode('/', $_POST['url']));
        $dir = "site_config/";
        $content = '';
        if( is_dir($dir) ){
            if ($dh = opendir($dir)){
                while (($file = readdir($dh)) !== false){
                    $filename = str_replace('.txt','',$file);
                    if($filename === $split_url[2]){
                        $content = file_get_contents($dir.$split_url[2].'.txt');
                    }
                }
                closedir($dh);
            }  
        }
        echo '<script>document.getElementById("website-input-form").style.display = "none";</script>';
        /*to run with phantomjs*/
        //system('phantomjs get_page_phantomjs.js "'.$_REQUEST['url'].'" '.$content);            
        /*to run with puppeteer*/
        system('node get_page_puppeteer.js "'.$_REQUEST['url'].'" '.$content); 
        // system('node sample.js "'.$_REQUEST['url'].'" '.$content);           
    }
?>

你可以在最后一行看到我是运行另一个示例 nodejs 脚本。它执行得很完美。

所以我不知道，也许人偶脚本有问题？

const puppeteer = require('puppeteer');

const url = process.argv[2];    //url from command line argument
const json = process.argv[3];   //config content from command line argument

/*_________________________STEP 1____________________________________*/
    async function run() {
        const browser = await puppeteer.launch();
        const page = await browser.newPage();
        await page.goto(url, {
                waitUntil: 'networkidle2',
                timeout: 3000000
            });
        await page.evaluate(function(json){

            //removing unwanted elements from html content
            Array.prototype.slice.call(document.getElementsByTagName("script")).filter(function(script) {
                return script.type != "application/ld+json";
            }).forEach(function(script) {
                script.parentNode.removeChild(script);
            });
            Array.prototype.slice.call(document.getElementsByTagName("style")).filter(function(style) {
                return style.type != "application/ld+json";
            }).forEach(function(style) {
                style.parentNode.removeChild(style);
            });
            Array.prototype.slice.call(document.getElementsByTagName("iframe")).filter(function(iframe) {
                return iframe.type != "application/ld+json";
            }).forEach(function(iframe) {
                iframe.parentNode.removeChild(iframe);
            });
            Array.prototype.slice.call(document.getElementsByTagName("video")).filter(function(video) {
                return video.type != "application/ld+json";
            }).forEach(function(video) {
                video.parentNode.removeChild(video);
            });
            Array.prototype.slice.call(document.getElementsByTagName("img")).filter(function(img) {
                img.setAttribute('style','max-width: 50% !important;');
                return img.src.endsWith('.svg') === true;
            }).forEach(function(img) {
                img.parentNode.removeChild(img);
            });

            //providing the site's config through an element
            var inp = document.createElement('div');
            inp.setAttribute('textcontent', json);
            inp.setAttribute('id', 'config_available');
            var XMLS = new XMLSerializer();
            var inp_xmls = XMLS.serializeToString(inp);
            document.body.insertAdjacentHTML('afterbegin', inp_xmls);

            //injecting the logic script
            inp = document.createElement('script');
            inp.setAttribute('src', './scraperJavascript.js');
            inp.setAttribute('type', 'text/javascript');
            XMLS = new XMLSerializer();
            inp_xmls = XMLS.serializeToString(inp);
            document.body.insertAdjacentHTML('afterbegin', inp_xmls);
        }, json)

        //rendering page's html
        const renderedContent = await page.evaluate(() => new XMLSerializer().serializeToString(document));
        console.log(renderedContent);

        await browser.close();
    }

    run();

但是如果脚本有问题，为什么运行从控制台（在 ubuntu 和 windows 上）和 php 脚本（在 windows) 但不是来自 php 脚本（在 ubuntu 上）

更新我运行在木偶操纵端进行异常检查。确实发生异常，这是它的消息 Error: Failed to launch chrome! [0608/095818.625603:ERROR:icu_util.cc(133)] Invalid file descriptor to ICU data received. [0608/095818.625662:FATAL:content_main_delegate.cc(57)] Check failed: false. #0 0x55dc5336182c base::debug::StackTrace::StackTrace() #1 0x55dc532e8290 logging::LogMessage::~LogMessage() #2 0x55dc51598de3 content::ContentMainDelegate::TerminateForFatalInitializationError() #3 0x55dc53017941 content::ContentMainRunnerImpl::Initialize() #4 0x55dc53021c12 service_manager::Main() #5 0x55dc53016184 content::ContentMain() #6 0x55dc571eea39 headless::(anonymous namespace)::RunContentMain() #7 0x55dc571eeac2 headless::HeadlessBrowserMain() #8 0x55dc5301ef8f headless::HeadlessShellMain() #9 0x55dc515971ac ChromeMain #10 0x7f5204329830 __libc_start_main #11 0x55dc5159702a _start TROUBLESHOOTING: https://github.com/GoogleChrome/puppeteer/blob/master/docs/troubleshooting.md at onClose (/var/www/html/master/scraper_puppeteer/node_modules/puppeteer/lib/Launcher.js:255:14) at Interface.helper.addEventListener (/var/www/html/master/scraper_puppeteer/node_modules/puppeteer/lib/Launcher.js:244:50) at emitNone (events.js:111:20) at Interface.emit (events.js:208:7) at Interface.close (readline.js:370:8) at Socket.onend (readline.js:149:10) at emitNone (events.js:111:20) at Socket.emit (events.js:208:7) at endReadableNT (_stream_readable.js:1055:12) at _combinedTickCallback (internal/process/next_tick.js:138:11)

Answer 1

可能是您的服务器不允许使用系统功能。查询方式：

<?php echo ini_get('disable_functions');

这是一个可能的结果：

exec,passthru,shell_exec,system,proc_open,popen,curl_multi_exec,parse_ini_file,show_source

另一个可能的原因：如果启用安全模式，您只能在该模式的特殊目录中执行文件：

<?php 

    if(ini_get("safe_mode")) {
        echo "Can only execute files inside of this dir: " . ini_get("safe_mode_exec_dir");
    }

如果以上检查成功，则可能是权限有问题。修改您的 system 调用以获取退出代码，它是非零的，存在问题：

system('node get_page_puppeteer.js "'.$_REQUEST['url'].'" '.$content, $return_code);
var_dump($return_code);

0 — no error
126 — command is found but is not executable source
127 — system doesn't know a file you're calling source

更新来自你的人偶错误

Failed to launch chrome! [...] Invalid file descriptor to ICU data received

根据 this issue 的说法，可能存在权限问题。该用户的解决方案是

cd /usr/local/lib/node_modules/puppeteer/.local-chromium
find . -type d | xargs -L1 -Ixx sudo chmod 755 xx
find . -type f -perm /u+x | xargs -L1 -Ixx sudo chmod 755 xx
find . -type f -not -perm /u+x | xargs -L1 -Ixx sudo chmod 644 xx

ubuntu 中未提取人偶脚本的内容

Content from puppeteer script not being fetched in ubuntu

javascript

php

node.js

google-chrome-headless

puppeteer