抓取豆瓣电影中韩国的最新的120条名称与LOGO
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<?php | |
require 'vendor/autoload.php'; | |
use Facebook\WebDriver\WebDriverBy; | |
use Facebook\WebDriver\WebDriverPlatform; | |
use Facebook\WebDriver\Chrome\ChromeOptions; | |
use Facebook\WebDriver\Remote\RemoteWebDriver; | |
use Facebook\WebDriver\Remote\DesiredCapabilities; | |
use Facebook\WebDriver\WebDriverExpectedCondition; | |
use Facebook\WebDriver\Remote\WebDriverCapabilityType; | |
$options = new ChromeOptions(); | |
$options->addArguments([ | |
'--window-size=1400,900', | |
'--no-sandbox', | |
]); | |
$capabilities = DesiredCapabilities::chrome(); | |
$capabilities->setCapability(ChromeOptions::CAPABILITY, $options); | |
$host = 'http://localhost:4444'; | |
$driver = RemoteWebDriver::create($host, $capabilities); | |
$driver->manage()->timeouts()->implicitlyWait(10); | |
$driver->get('https://movie.douban.com/tag/#/?sort=R&range=0,10&tags=%E9%9F%A9%E5%9B%BD'); | |
for ($i = 1; $i <= 5; $i++) { | |
sleep(1); | |
$driver->findElement(WebDriverBy::cssSelector('a.more'))->click(); | |
$driver->wait(20, 1000)->until( | |
function () use ($driver, $i) { | |
$elements = $driver->findElements(WebDriverBy::cssSelector('#app .list-wp .item')); | |
echo sprintf("count: %d, num: %d\n", count($elements), $i * 20); | |
return count($elements) > $i * 20; | |
} | |
); | |
} | |
$dir = __DIR__ . '/douban'; | |
!is_dir($dir) && mkdir($dir, 0755); | |
$item_elements = $driver->findElements(WebDriverBy::cssSelector('#app .list-wp .item')); | |
foreach ($item_elements as $item) { | |
$alt = $item->findElement(WebDriverBy::cssSelector('.pic img'))->getAttribute('alt'); | |
$alt = preg_replace('/[\/\\\\:*?"<>|]/', '', $alt); | |
$src = $item->findElement(WebDriverBy::cssSelector('.pic img'))->getAttribute('src'); | |
$ext = pathinfo($src, PATHINFO_EXTENSION); | |
file_put_contents($dir . '/' . $alt . '.' . $ext, file_get_contents($src)); | |
echo sprintf("alt: %s, src: %s\n", $alt, $src); | |
usleep(50); | |
} | |
echo "complete\n"; | |
$driver->quit(); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment