public function scrap($username, $password)
{
$client = new Client();
$crawler = $client->request('GET', 'http://studentinfo.bdu.edu.et/login.aspx');
$form = $crawler->selectButton('Login')->form();
$form['dnn$ctr$Login$Login_DNN$txtUsername'] = $username;
$form['dnn$ctr$Login$Login_DNN$txtPassword'] = $password;
$crawler = $client->submit($form);
return $client->request('POST', 'MyGrades.aspx');
}
/**
* Add product data
*
* @param Crawler $node
*/
private function addProduct(Crawler $node)
{
$product = new \stdClass();
/** @var Crawler $title */
$title = $node->filter('h3 a');
$product->title = trim($title->text());
$product->unit_price = $this->getPrice($node->filter('.pricePerUnit'));
$productCrawler = $this->client->request('GET', $title->attr('href'));
$product->size = $this->bytesToKb(strlen($this->client->getResponse()->getContent()));
$product->description = '';
$description = $productCrawler->filterXPath('//h3[.="Description"]');
if ($description->count() > 0) {
foreach ($description->siblings() as $sibling) {
// product pages have different structures!
if ($sibling->tagName == 'h3') {
break;
}
if ($product->description != "") {
$product->description .= "\n";
}
// @TODO address formatting issues - breaks to new lines
$product->description .= trim(preg_replace("/[^\\S\r\n]+/", " ", $sibling->nodeValue));
// remove excess whitespace but not new lines
}
}
$this->total += $product->unit_price;
// increment total
$this->results[] = $product;
}
/**
* @param int $id
*
* @throws SubjectNotFoundException
*
* @return JusticeRecord|false
*/
public function findById($id)
{
Assertion::integer($id);
$crawler = $this->client->request('GET', sprintf(self::URL_SUBJECTS, $id));
$detailUrl = $this->extractDetailUrlFromCrawler($crawler);
if (false === $detailUrl) {
return false;
}
$people = [];
$crawler = $this->client->request('GET', $detailUrl);
$crawler->filter('.aunp-content .div-table')->each(function (Crawler $table) use(&$people) {
$title = $table->filter('.vr-hlavicka')->text();
try {
if ('jednatel: ' === $title) {
$person = JusticeJednatelPersonParser::parseFromDomCrawler($table);
$people[$person->getName()] = $person;
} elseif ('Společník: ' === $title) {
$person = JusticeSpolecnikPersonParser::parseFromDomCrawler($table);
$people[$person->getName()] = $person;
}
} catch (\Exception $e) {
}
});
return new JusticeRecord($people);
}
/**
* Gets all shows and store them in json.
*/
public function updateShows()
{
$url = $this->builder->getAddictedShowsUrl();
printf("Trying to get shows from [%s].\n", $url);
$crawler = $this->client->request('GET', $url);
$showsLinkAndName = $crawler->filter('table.tabel90 > tr > td > h3 > a')->extract(['_text', 'href']);
$showsSeasons = $crawler->filter('table.tabel90 > tr > td.newsDate')->extract(['_text']);
if (count($showsLinkAndName) != count($showsSeasons)) {
throw new \Exception("Inconsistencies detected while updating shows.");
}
printf("Found [%s] shows.\n", count($showsLinkAndName));
$shows = [];
foreach ($showsLinkAndName as $n => $show) {
$id = $this->extractShowId($show[1]);
if ($this->nonEmptyShow($showsSeasons[$n])) {
$name = Episode::sanitizeShowName($show[0]);
// if multiple shows name reference the same id
if (isset($this->mappedShowsNames()[$name])) {
foreach ($this->mappedShowsNames()[$name] as $name) {
$shows[$name] = $id;
}
} else {
$shows[$name] = $id;
}
}
}
$this->io->saveShows($shows);
}
public function getCrawler()
{
if (!isset($this->crawler)) {
$this->crawler = $this->client->request('GET', $this->getUri());
}
return $this->crawler;
}
public function testLoggedIn()
{
// we don't use the trait method here since we want our
// test to span two page requests, and we need to have
// the session persist on the remote server
// create a web client and hit the login page
$url = "http://localhost/login";
$client = new Client();
$crawler = $client->request('GET', $url);
$response_code = $client->getResponse()->getStatus();
// we should get 200 back
$this->assertEquals(200, $response_code);
// select the form on the page and populate values
// since we are using Goutte\Client, we don't need
// to worry about parsing the HTML to find the csrf _token
$form = $crawler->selectButton('Sign in')->form();
$form->setValues(['email' => '*****@*****.**', 'password' => 'verysecret']);
// submit the form
$client->submit($form);
$response_code_after_submit = $client->getResponse()->getStatus();
// make sure the HTML page displayed (response code 200
$this->assertEquals(200, $response_code_after_submit);
// make sure we can get to the testimonial page
$client->request('GET', 'http://localhost/add-testimonial');
$response_code = $client->getResponse()->getStatus();
$this->assertEquals(200, $response_code);
}
/**
* Extracts prices from HTML table.
*
* @param string $button Submit button text
* @param array $location Region or county
* @return array
*/
protected function extractPricesFromTable($button, array $location)
{
$prices = [];
$crawler = $this->client->request('GET', 'http://www.ccs.cz/pages/phm2.php');
$form = $crawler->selectButton($button)->form();
$crawler = $this->client->submit($form, $location);
$columnIterator = 0;
$rowIterator = 0;
$crawler->filter('table[class="dynamic"] td')->each(function (DomCrawler $node) use(&$prices, &$columnIterator, &$rowIterator) {
switch ($columnIterator) {
case 0:
$prices[$rowIterator]['date'] = new \DateTime($node->text());
break;
case 1:
$prices[$rowIterator]['natural95'] = $node->text();
break;
case 3:
$prices[$rowIterator]['diesel'] = $node->text();
break;
}
$columnIterator = ++$columnIterator % 5;
$rowIterator += $columnIterator == 0 ? 1 : 0;
});
return $prices;
}
/**
* Requests a URL.
*
* @param string $url The URL to request
* @param string $method The HTTP method
* @return Crawler
* @throws ConnectException
*/
private function request($url, $method = 'GET')
{
try {
return $this->client->request(strtoupper($method), $url);
} catch (ConnectException $error) {
throw $error;
}
}
/**
* @param Url $url
*
* @return \Symfony\Component\DomCrawler\Crawler|null
*/
public function scrape(Url $url)
{
try {
return $this->client->request('GET', $url->getUrl());
} catch (RequestException $e) {
return;
}
}
private function scrap(Song $song)
{
$arr = [];
$crawler = $this->client->request('GET', $song->url());
$arr["title"] = $crawler->filter("title")->text();
$arr["thumbnail_url"] = sprintf('http://img.youtube.com/vi/%s/1.jpg', $song->videoId());
return $arr;
}
public function actionIndex()
{
/** @var $entity RivegaucheLink */
$entity = new RivegaucheLink();
$offset = 0;
do {
$links = $entity->getLinks($offset, 5);
if (!empty($links)) {
foreach ($links as $link) {
\Yii::info(sprintf('Обрабатываем: %s ', $link['link']), 'cron');
$client = new Client();
$guzzle = $client->getClient();
$client->getClient()->setDefaultOption('config/curl/' . CURLOPT_PROXY, 'http://141.101.118.147:80');
//$client->getClient()->setDefaultOption('config/curl/'.CURLOPT_TIMEOUT, 10);
$client->getClient()->setDefaultOption('config/curl/' . CURLOPT_CONNECTTIMEOUT, 10);
$client->setClient($guzzle);
/*$guzzle = $client->getClient();
$guzzle->setDefaultOption('timeout', 10);
$client->getClient()->setDefaultOption('config/curl/'.CURLOPT_TIMEOUT_MS, 100);
$client->getClient()->setDefaultOption('config/curl/'.CURLOPT_CONNECTTIMEOUT, 5);
$client->getClient()->setDefaultOption('config/curl/'.CURLOPT_RETURNTRANSFER, true);
$client->setClient($guzzle);*/
$crawler = $client->request('GET', $link['link']);
\Yii::info(sprintf('Извлекаем тело: %s ', $link['link']), 'cron');
$head = $this->getHtml($crawler, true);
\Yii::info(sprintf('HEAD тело: %s ', $link['link']), 'cron');
if (!empty($head['links'])) {
foreach ($head['links'] as $l) {
$crawler = $client->request('GET', $l);
$subHead = $this->getHtml($crawler, false);
$subHead['link'] = $l;
$this->saveResult($subHead, $link);
}
}
if (empty($head['title'])) {
$head = $this->getPromoHTML($crawler, true);
}
if (empty($head['title'])) {
$head = $this->getPromo2HTML($crawler, true);
}
$head['link'] = $link['link'];
$this->saveResult($head, $link);
unset($node);
unset($subNode);
unset($head);
}
$z = 1;
$offset += 5;
unset($links);
unset($client);
} else {
$z = 0;
}
} while ($z > 0);
return 0;
}
/**
* Checks at the NABV site if the given card is correct
* @param Card $card
*
* @return bool
*/
public function isValidCard(Card $card)
{
$crawler = $this->client->request('POST', $this->url, ['relation_number' => $card->toString()]);
$status = false;
$crawler->filter('.alert.alert-success')->each(function () use(&$status) {
$status = true;
});
return $status;
}
/**
* Extract entries from given crawler object.
*
* @param \Symfony\Component\DomCrawler\Crawler $crawler
* @return array
*/
public function extractEntries(Crawler $crawler)
{
$links = $this->linksExtractor->extractEntries($crawler);
$entries = array();
if (count($links)) {
foreach ($links as $link) {
$entries[] = $this->entryExtractor->extractEntry($this->client->request('GET', $link));
}
}
return $entries;
}
/**
* @param Client $client
*/
public function request(Client $client)
{
if (isset($this->provider)) {
$class = static::$providers[$this->provider];
if (isset($class::$endpoint)) {
$client->request('GET', $class::$endpoint . rawurlencode($this->url));
$this->content = json_decode($client->getResponse()->getContent());
} else {
$this->content = $client->request('GET', $this->url);
}
}
}
/**
* その日に草が生えてるかをチェックする
*
* @param string $userName
*
* @return bool
*/
public function checkContribution($userName)
{
// Getting user page souce
$body = $this->goutteClient->request('GET', $this->getGitHubUrl($userName));
// parse response body
$contribution = null;
$body->filter('rect')->last()->each(function ($name) {
$contribution = $name->attr('fill');
});
// #eeeeeeはSaboってる
return $contribution !== '#eeeeee';
}
/**
* Get the list of all available ads
*
* Returns an array of ads where one ad has the following format:
*
* array(7) {
* ["url"]=>
* string(52) "https://www.leboncoin.fr/velos/934826585.htm?ca=12_s"
* ["image"]=>
* string(81) "https://img1.leboncoin.fr/thumbs/010/010a091e6f370cf14f1bf446be768a92e6342d7f.jpg"
* ["title"]=>
* string(50) "Collier BBB 31.8mm ALU dérailleur avant à BRASER"
* ["category"]=>
* string(6) "Vélos"
* ["location"]=>
* string(33) "Carrières-sous-Poissy / Yvelines"
* ["price"]=>
* string(7) "10 €"
* ["date"]=>
* string(18) "Aujourd'hui, 14:12"
* }
*
* @param srring $url the url that leads to search results
* @param int $maxAds max number of ads to fetch (0 = gets all ads)
*
* @return array $ads
*/
public function getAds($url, $maxAds = 0)
{
$ads = [];
$pageNumber = 1;
$fetchedAds = 0;
do {
$crawler = $this->client->request('GET', $url, ['o' => $pageNumber]);
$totalAds = str_replace(' ', '', $crawler->filter('#listingAds section header nav a')->first()->filter('span')->text());
$nbAdsInPage = $crawler->filter('#listingAds > section > ul > li')->count();
$ads += $this->_fetchAds($crawler, $fetchedAds, $maxAds);
$fetchedAds += $nbAdsInPage;
$pageNumber++;
} while ($fetchedAds < $totalAds && ($maxAds == 0 || $fetchedAds < $maxAds));
return array_slice($ads, 0, $maxAds ? $maxAds : count($ads));
}
public function testUserSeesWelcomeMessage()
{
$client = new Client();
$crawler = $client->request('GET', 'http://tinkoff');
$this->assertEquals(200, $client->getResponse()->getStatus());
$this->assertCount(1, $crawler->filter('h1:contains("Welcome to Tinkoff")'));
}
protected static function fetchData(Client $client)
{
$page = $client->request('GET', 'http://www.movie.com.uy/teatro/');
$premieres = self::getPlays($page->filter('div#proximos_est'));
$billboard = self::getPlays($page->filter('div#cartelera_prin'));
return array_merge(SpiderHelper::getPosterData($page), ['billboard' => array_merge($premieres, $billboard)]);
}
private function parseURLPDF()
{
$client = new Client();
$crawler = $client->request('GET', 'https://www.pcfactory.cl/ventabodega');
$href = $crawler->filter('a[class="main_link1"][href]')->first()->attr('href');
return 'https://www.pcfactory.cl/' . $href;
}
/**
* Initializing the plugin's behavior
*
* @return void
*/
public function init()
{
$that = $this;
$this->bot->onMessages('/^!php(doc)? (.*)/i', function (Event $event) use($that) {
$request = $event->getRequest();
$matches = $event->getMatches();
$match = array_pop($matches);
$client = new Client();
$crawler = $client->request('GET', sprintf('http://www.php.net/%s', str_replace('_', '-', $match)));
if ($crawler->filter('.refnamediv h1.refname')->count() !== 0) {
$function = $crawler->filter('.refnamediv h1.refname')->first()->text();
$description = $crawler->filter('.refnamediv span.dc-title')->first()->text();
$version = $crawler->filter('.refnamediv p.verinfo')->first()->text();
$synopsis = $crawler->filter('.methodsynopsis')->first()->text();
$synopsis = preg_replace('/\\s+/', ' ', $synopsis);
$synopsis = preg_replace('/(\\r\\n|\\n|\\r)/m', ' ', $synopsis);
$synopsis = trim($synopsis);
$event->addResponse(Response::msg($request->getSource(), sprintf('%s - %s %s', $function, $description, $version)));
$event->addResponse(Response::msg($request->getSource(), sprintf('Synopsis: %s', $synopsis)));
} else {
$suggestion = $crawler->filter('#quickref_functions li a b')->first()->text();
$event->addResponse(Response::msg($request->getSource(), sprintf('Could not find the requested PHP function. Did you mean: %s?', $suggestion)));
}
});
}
/**
* simulate worldjournal ajax call to fetch content data
*/
public function actionTrypostdata()
{
$hostname = 'www.wjlife.com';
$optionVaules = ["relation" => "AND", "0" => ["relation" => "AND", "0" => ["key" => "wj_order_id"]]];
//all help wanted
$currentURL = "/cls_category/03-ny-help-wanted/";
//temp page number
$pno = 0;
$queryObject = ["keyword" => "", "pagesize" => 40, "pno" => $pno, "optionVaules" => $optionVaules, "currentURL" => "http://" . $hostname . $currentURL, "currentCatId" => 327, "currentStateId" => 152];
//language: chinese simplified
$wjlang = "zh-cn";
$requestUrl = "http://" . $hostname . "/wp-content/themes/wjlife/includes/classified-core.php?regions=state_ny&variant=" . $wjlang . "&t=" . time();
// echo "start...\n";
$client = new Client();
$crawler = $client->request("POST", $requestUrl, $queryObject, [], ['HTTP_X-Requested-With' => 'XMLHttpRequest', 'contentType' => 'application/x-www-form-urlencoded;charset=utf-8']);
$rowHtml = $crawler->html();
// if you want to echo out with correct encoding, do `echo utf8_decode($rowHtml)`
// echo utf8_decode($rowHtml);
// echo "end...\n";
$subCrawler = new Crawler();
$subCrawler->addHtmlContent($rowHtml);
$linkArray = $subCrawler->filter(".catDesc a")->each(function ($node, $index) {
return $href = $node->attr('href');
});
print_r($linkArray);
}
/**
* Show the form for creating a new resource.
*
* @return \Illuminate\Http\Response
*/
public function index()
{
for ($i = 68; $i <= 78; $i++) {
//$photos=Image::paginate(50);
$client = new Client();
$baseURL = 'http://www.cutecatgifs.com/page';
$urlEndpoint = '/' . $i++;
$crawler = $client->request('GET', $baseURL . $urlEndpoint);
$photos = $crawler->filter('img.alignnone')->extract(array('src', 'alt'));
foreach ($photos as $photo) {
$url = $photo[0];
$title = $photo[1];
$extension = pathinfo($url, PATHINFO_EXTENSION);
$filename = str_random(4) . '-' . str_slug($title) . '.' . $extension;
// get file content from url and save in directory
$file = file_get_contents($url);
$save_file = file_put_contents('uploads/' . $filename, $file);
// Create record in database
$image = new \App\Image();
$image->name = $photo[1];
$image->url = $filename;
$image->user_id = 1;
$image->description = $photo[1];
$image->save();
}
}
}
/**
* Crawl single URL
* @param string $url
* @param int $depth
*/
protected function traverseSingle($url, $depth)
{
try {
$client = new Client();
$client->followRedirects();
$crawler = $client->request('GET', $url);
$statusCode = $client->getResponse()->getStatus();
$hash = $this->getPathFromUrl($url);
$this->links[$hash]['status_code'] = $statusCode;
if ($statusCode === 200) {
$content_type = $client->getResponse()->getHeader('Content-Type');
if (strpos($content_type, 'text/html') !== false) {
//traverse children in case the response in HTML document only
$this->extractTitleInfo($crawler, $hash);
$childLinks = array();
if (isset($this->links[$hash]['external_link']) === true && $this->links[$hash]['external_link'] === false) {
$childLinks = $this->extractLinksInfo($crawler, $hash);
}
$this->links[$hash]['visited'] = true;
$this->traverseChildren($childLinks, $depth - 1);
}
}
} catch (CurlException $e) {
$this->links[$url]['status_code'] = '404';
$this->links[$url]['error_code'] = $e->getCode();
$this->links[$url]['error_message'] = $e->getMessage();
} catch (\Exception $e) {
$this->links[$url]['status_code'] = '404';
$this->links[$url]['error_code'] = $e->getCode();
$this->links[$url]['error_message'] = $e->getMessage();
}
}
public static function getHoje()
{
$nomes = ["Cantareira", "Guarapiranga", "Alto Cotia", "Alto Tietê", "Rio Claro", "Rio Grande"];
$client = new Client();
$crawler = $client->request('GET', 'http://www.apolo11.com/reservatorios.php?step=d');
$tables = $crawler->filter("font[face='arial']");
$data = $crawler->filter("font[face='verdana']");
$obj = new stdClass();
$obj->data = $data->eq(10)->text() . "/" . date('y');
$obj->niveis = array();
$tmp = array();
for ($i = 0; $i < 6; $i++) {
$nivel = new stdClass();
$nivel->nome = $nomes[$i];
$nivel->hoje = $tables->eq($i * 9 + 16)->text();
$nivel->ontem = $tables->eq($i * 9 + 15)->text();
$nivel->chuva = preg_replace("/[^0-9,.]/", "", $tables->eq(5 - $i)->text());
$tmp[] = $nivel;
}
$obj->niveis[0] = $tmp[0];
$obj->niveis[1] = $tmp[3];
$obj->niveis[2] = $tmp[1];
$obj->niveis[3] = $tmp[2];
$obj->niveis[4] = $tmp[5];
$obj->niveis[5] = $tmp[4];
return $obj;
}
/**
* @param boolean $allPages
*/
public function run($allPages)
{
$client = new Client();
$client->getClient()->setDefaultOption('config/curl/' . CURLOPT_TIMEOUT, 30);
$client->setHeader('User-Agent', $this->config['user_agent']);
try {
$crawler = $client->request('GET', $this->config['url']);
} catch (TransferException $e) {
echo $e->getMessage() . PHP_EOL;
exit(1);
}
if ($client->getResponse()->getStatus() == 200) {
$this->getUrlsAndDownload($crawler);
if ($allPages) {
$link = $this->getNextLink($crawler);
while ($link) {
$crawler = $client->click($link);
$this->getUrlsAndDownload($crawler);
$link = $this->getNextLink($crawler);
}
}
} else {
echo "site not available\n";
}
}
/**
* Helper for submitting a message (post or private message)
*
* @param string $posting_url
* @param string $posting_contains
* @param array $form_data
* @return \Symfony\Component\DomCrawler\Crawler the crawler object
*/
protected function submit_message($posting_url, $posting_contains, $form_data)
{
if (time() == self::$last_post_timestamp) {
// Travis is too fast, so we have to wait to not mix up the post/topic order
sleep(1);
}
self::$last_post_timestamp = time();
$crawler = self::request('GET', $posting_url);
$this->assertContains($this->lang($posting_contains), $crawler->filter('html')->text());
if (!empty($form_data['upload_files'])) {
for ($i = 0; $i < $form_data['upload_files']; $i++) {
$file = array('tmp_name' => __DIR__ . '/../functional/fixtures/files/valid.jpg', 'name' => 'valid.jpg', 'type' => 'image/jpeg', 'size' => filesize(__DIR__ . '/../functional/fixtures/files/valid.jpg'), 'error' => UPLOAD_ERR_OK);
$crawler = self::$client->request('POST', $posting_url, array('add_file' => $this->lang('ADD_FILE')), array('fileupload' => $file));
}
unset($form_data['upload_files']);
}
$hidden_fields = array($crawler->filter('[type="hidden"]')->each(function ($node, $i) {
return array('name' => $node->attr('name'), 'value' => $node->attr('value'));
}));
foreach ($hidden_fields as $fields) {
foreach ($fields as $field) {
$form_data[$field['name']] = $field['value'];
}
}
// Bypass time restriction that said that if the lastclick time (i.e. time when the form was opened)
// is not at least 2 seconds before submission, cancel the form
$form_data['lastclick'] = 0;
// I use a request because the form submission method does not allow you to send data that is not
// contained in one of the actual form fields that the browser sees (i.e. it ignores "hidden" inputs)
// Instead, I send it as a request with the submit button "post" set to true.
return self::request('POST', $posting_url, $form_data);
}
/**
* 現在の株価を取得する
*
* @param 整数値 $code 取得する株価コード
* @return bool true 成功
*/
public function getStockPrice($code)
{
try {
$client = new Client();
$crawler = $client->request('GET', "http://stocks.finance.yahoo.co.jp/stocks/detail/?code={$code}.T");
// 前日終値、始値、高値、安値を取得する
$array = $crawler->filter('dd')->each(function ($element) {
$array = $element->filter('strong')->each(function ($element) {
return $element->text();
});
// Debug::logPrintR($array);
return count($array) > 0 ? $array[0] : null;
});
// Debug::logPrintR($array);
// $array の要素は以下の様になっている
// [2] 前日終値
// [3] 始値
// [4] 高値
// [5] 安値
if (count($array) >= 6) {
$this->beforeClosingPrice = $this->removeComma($array[2]);
$this->openingPrice = $this->removeComma($array[3]);
$this->highPrice = $this->removeComma($array[4]);
$this->lowPrice = $this->removeComma($array[5]);
}
// 現在値を取得する
$element = $crawler->filter('td.stoksPrice')->last();
$this->nowPrice = $this->removeComma($element->text());
} catch (exception $e) {
// Debug::logPrintR($e);
return false;
}
return true;
}
function devtips_get($url)
{
$tip = new DevTip(array("url" => $url));
$client = new Client();
$crawler = $client->request('GET', $url);
$crawler->filter('div.dt-content')->each(function ($node) use(&$tip) {
$html = trim($node->html());
// add line breaks
$html = str_replace("><", ">\n<", $html);
// remove aside
$pos = strpos($html, "<aside");
if ($pos !== false) {
$html = substr($html, 0, $pos);
}
// convert <p>'s to just line breaks
$html = str_replace("<p>", "\n", $html);
$html = str_replace("</p>", "\n", $html);
$tip->set('content', $html);
});
$crawler->filter('h3')->each(function ($node) use(&$tip) {
$tip->set('title', $node->text());
});
$sources = $crawler->filter('div.dt-content *[src]')->extract(array('src'));
$tip->set('assets', $sources);
return $tip;
}
/**
* @param $url
* @return Crawler
*/
function getDataURL($url)
{
$client = new Client();
$jsonURL = AlloSurfGetData::getJsonUrl($url);
$crawler = $client->request('GET', $jsonURL);
return $crawler;
}
/**
* Obtém a lista de medicamentos do sistema da Anvisa e retorna um array
* com os resultados.
*
* @param string $medicamento Nome de medicamento
* @param string $empresa Nome da fabricante do medicamento
* @param string $expediente Número do expediente da bula
*
* @throws \Exception Caso não for possível trazer os resultados
*
* @return \Collections\ArrayList Todas as bulas encontradas
*/
public static function buscarMedicamentos($medicamento = '', $empresa = '', $expediente = '')
{
if (empty($medicamento) && empty($empresa) && empty($expediente)) {
throw new \InvalidArgumentException('Informe pelo menos um parâmetro para o método!');
}
$Client = new Client();
$crawler = $Client->request('POST', 'http://www.anvisa.gov.br/datavisa/fila_bula/frmResultado.asp', ['hddLetra' => '', 'txtMedicamento' => $medicamento, 'txtEmpresa' => $empresa, 'txtNuExpediente' => $expediente, 'txtDataPublicacaoI' => '', 'txtDataPublicacaoF' => '', 'txtPageSize' => '1000', 'btnPesquisar' => '']);
$Medicamentos = new ArrayList();
try {
$trs = $crawler->filter('#tblResultado > tbody > tr');
if ($trs->first()->filter('td')->count() > 1) {
$trs->each(function ($node) use(&$Medicamentos) {
if (trim($node->filter('td')->eq(0)->text()) != 'Nenhuma bula na fila de análise') {
$nomeMedicamento = trim($node->filter('td')->eq(0)->text());
$nomeEmpresa = trim($node->filter('td')->eq(1)->text());
$exp = trim($node->filter('td')->eq(2)->text());
$dataPub = trim($node->filter('td')->eq(3)->text());
$dadosBulaPaciente = self::stripJsFunction($node->filter('td')->eq(4)->filter('a')->attr('onclick'));
$dadosBulaProfissional = self::stripJsFunction($node->filter('td')->eq(5)->filter('a')->attr('onclick'));
$Bula = new Bula();
$Bula->setMedicamento($nomeMedicamento);
$Bula->setEmpresa($nomeEmpresa);
$Bula->setExpediente($exp);
$Bula->setDataPublicacao($dataPub);
$Bula->setBulaPaciente(new DadosBula($dadosBulaPaciente['transacao'], $dadosBulaPaciente['anexo']));
$Bula->setBulaProfissional(new DadosBula($dadosBulaProfissional['transacao'], $dadosBulaProfissional['anexo']));
$Medicamentos->add($Bula);
}
});
}
} catch (\Exception $ex) {
throw new Exception('Houve um erro ao obter os medicamentos do sistema da Anvisa!');
}
return $Medicamentos;
}
