krzysiej/packtpub-browser
1
0
Fork 0
Code Issues 2 Pull Requests Releases Wiki Activity

A big mess of packt class.

Browse Source
This commit is contained in:
krzysiej
2018-08-31 12:11:32 +02:00
parent 22d0bb4f04
commit 05b5148eaa
1 changed files with 182 additions and 64 deletions
Download Patch File Download Diff File Expand all files Collapse all files

246
packt.php
View File

@@ -4,15 +4,7 @@ include 'vendor/autoload.php';
use DiDom\Document; use DiDom\Document;
set_time_limit(-1); set_time_limit(-1);
$settings = include 'settings.php'; $credentials = include 'settings.php';
$loginData = [
'email' => $settings['email'],
'password' => $settings['password'],
'op' => 'Login',
'form_build_id' => 'form-fba4b62ee04aafbf045b1d9ae019d90b',
'form_id' => 'packt_user_login_form'
];
class Packt class Packt
@@ -21,7 +13,12 @@ class Packt
private $credentials = []; private $credentials = [];
const BASE_URL = 'https://www.packtpub.com/'; const BASE_URL = 'https://www.packtpub.com/';
const MY_BOOKS_PAGE = self::BASE_URL . 'account/my-ebooks';
const LOGIN_PAGE = 'https://www.packtpub.com/mapt-rest/users/tokens';
// private $accessToken = 'eyJhbGciOiJSUzI1NiIsInR5cCI6IkpXVCJ9.eyJ1c2VySWQiOiJmNjUyODNlYy00OTE1LTQ3ZTktYjM1Mi1mYzkzM2FhOTUxYWIiLCJ1c2VybmFtZSI6ImtyenlzaWVqQGdtYWlsLmNvbSIsInBlcm1pc3Npb25zIjpbXSwiaWF0IjoxNTMyMDcxNjQ0LCJleHAiOjE1MzIwNzUyNDR9.Gp3no55EkmoXJJ4TLk2MwPsix7dzvudiWqJEA4To3W9xkubhFFAtkISJoMO9AHLuQJITns-zMAjg1VBnnQSp3G6U7lzi7PDzM_CThuZJHKy6jBA_HtBnHJ-GoAK6hVxqifooTECmXIAignMz8sEbThHAUqY75djXuDYnaAlJaBvzwlt-mRkbsvRjGHr379LsvoezPeYCgJtme1J_xPonjaJZJ9nP04QfiwbnUSEiGb71Fvixc1Vo3F8QO11fHgI_fXLZSidgB4WGkz_m9AvjmqOXc02fbxf-WgfPe8Oj-qndLoq6ZAWIy86XjAx8inFHWrPbvyoIdLRSty1a9aEDkQ';
private $accessToken = 'eyJhbGciOiJSUzI1NiIsInR5cCI6IkpXVCJ9.eyJ1c2VySWQiOiJmNjUyODNlYy00OTE1LTQ3ZTktYjM1Mi1mYzkzM2FhOTUxYWIiLCJ1c2VybmFtZSI6ImtyenlzaWVqQGdtYWlsLmNvbSIsInBlcm1pc3Npb25zIjpbXSwiaWF0IjoxNTMyMzI5MDk4LCJleHAiOjE1MzIzMzI2OTh9.uUyYz2uMT3mZ77-Uc2yoVH4y5qqI_WfpXB9kKw81qhUKRuonD6jhLZKbCAQSObkKyEJz1bYB0cQVfwsKZiwAuY58VrCQ0ykQUPrQh3MfAEJ5zpE3CquAf5o892ToLbIwGieC05ElHXsMUCfgimA6ECtHzIT9dC4l93FYaoDpsnyZFA9ikxUJIAKI51rOS879J_B98UPdw-NOlsCl1-2CcTnjf5He4CQuYWYvnj0NpV0_GP3w5rnNy8989prqks_m7WKFMJXzhH9OlexKVgF3J4IS3216yEJrL8ViQ_gkAZBRRuKJYeYUiAJ4H7Hy_IohN90-SpaH4jvIt81SApVc2A';
// private $accessToken;
private $database = null; private $database = null;
public function __construct($credentials) public function __construct($credentials)
@@ -50,43 +47,43 @@ class Packt
return str_replace('https://www.packtpub.com', '', $bookUrl); return str_replace('https://www.packtpub.com', '', $bookUrl);
} }
public function getBookInfo($bookUrl) // public function getBookInfo($bookUrl)
{ // {
//
$bookUrl = resolveBookUrl($bookUrl); // $bookUrl = resolveBookUrl($bookUrl);
$bookData = []; // $bookData = [];
$bookPage = new Document($bookUrl, true); // $bookPage = new Document($bookUrl, true);
$bookData['datepublished'] = $bookPage->first('.book-top-block-info-authors time[itemprop="datePublished"]::attr(datetime)'); // $bookData['datepublished'] = $bookPage->first('.book-top-block-info-authors time[itemprop="datePublished"]::attr(datetime)');
$bookData['numberofpages'] = $bookPage->first('span[itemprop="numberOfPages"]::text'); // $bookData['numberofpages'] = $bookPage->first('span[itemprop="numberOfPages"]::text');
$bookData['isbn'] = $bookPage->first('span[itemprop="isbn"]::text'); // $bookData['isbn'] = $bookPage->first('span[itemprop="isbn"]::text');
$bookData['reviewCount'] = $bookPage->first('meta[itemprop="reviewCount"]::attr(content)'); // $bookData['reviewCount'] = $bookPage->first('meta[itemprop="reviewCount"]::attr(content)');
$bookData['ratingValue'] = $bookPage->first('meta[itemprop="ratingValue"]::attr(content)'); // $bookData['ratingValue'] = $bookPage->first('meta[itemprop="ratingValue"]::attr(content)');
//
$bookData['toc'] = []; // $bookData['toc'] = [];
foreach ($bookPage->find('#book-info-toc.onlyDesktop .book-toc-chapter') as $chapter) { // foreach ($bookPage->find('#book-info-toc.onlyDesktop .book-toc-chapter') as $chapter) {
if (!is_null($chapter->first('div[class*="book-toc-chapter-title"]'))) { // if (!is_null($chapter->first('div[class*="book-toc-chapter-title"]'))) {
$tocSection = []; // $tocSection = [];
$tocSection['title'] = trim($chapter->first('div[class*="book-toc-chapter-title"]')->text()); // $tocSection['title'] = trim($chapter->first('div[class*="book-toc-chapter-title"]')->text());
$tocSection['subchapters'] = $chapter->find('div[class*="book-toc-section-text"]::text'); // $tocSection['subchapters'] = $chapter->find('div[class*="book-toc-section-text"]::text');
$bookData['toc'][] = $tocSection; // $bookData['toc'][] = $tocSection;
} // }
} // }
//
$bookData['description'] = $bookPage->find('div.book-info-bottom-indetail-text[itemprop="description"] p::text'); // $bookData['description'] = implode(' ', $bookPage->find('div.book-info-bottom-indetail-text[itemprop="description"] p::text'));
$bookData['willLearn'] = $bookPage->find('div.book-info-will-learn-text li::text'); // $bookData['willLearn'] = $bookPage->find('div.book-info-will-learn-text li::text');
//
$bookData['category'] = $bookPage->first('div[data-product-id="' . $bookData['isbn'] . '"]::attr(data-product-category)'); // $bookData['category'] = $bookPage->first('div[data-product-id="' . $bookData['isbn'] . '"]::attr(data-product-category)');
//
$bookData['authors'] = []; // $bookData['authors'] = [];
foreach ($bookPage->find('[itemprop="author"]') as $author) { // foreach ($bookPage->find('[itemprop="author"]') as $author) {
//
$authorData = []; // $authorData = [];
$authorData['name'] = trim($author->first('.book-info-bottom-author-title')->text()); // $authorData['name'] = trim($author->first('.book-info-bottom-author-title')->text());
$authorData['bio'] = preg_replace('#\s{2,}#', ' ', trim($author->first('.book-info-bottom-author-body')->text())); // $authorData['bio'] = preg_replace('#\s{2,}#', ' ', trim($author->first('.book-info-bottom-author-body')->text()));
$bookData['authors'][] = $authorData; // $bookData['authors'][] = $authorData;
} // }
return $bookData; // return $bookData;
} // }
public function saveBookChapters($data, $bookId) public function saveBookChapters($data, $bookId)
{ {
@@ -151,12 +148,36 @@ class Packt
return 'books' . DIRECTORY_SEPARATOR . $filePathParts[1] . DIRECTORY_SEPARATOR . $filePathParts[1] . '.' . (isset($filePathParts[2]) ? $filePathParts[2] : 'zip'); return 'books' . DIRECTORY_SEPARATOR . $filePathParts[1] . DIRECTORY_SEPARATOR . $filePathParts[1] . '.' . (isset($filePathParts[2]) ? $filePathParts[2] : 'zip');
} }
public function getBooks()
/**
* funkcja której zadaniem jest logowanie uzytkownika na stronie
*/
private function login()
{
if (is_null($this->accessToken)) {
$loginData = c(self::LOGIN_PAGE, json_encode($this->credentials));
$loginJson = json_decode($loginData);
print_r($loginJson);
if (isset($loginJson->httpStatus, $loginJson->status) && $loginJson->httpStatus == 200 && $loginJson->status == 'success') {
$this->accessToken = $loginJson->data->access;
} else {
throw new Exception($loginJson->message, $loginJson->httpStatus);
}
}
}
/**
* @param int $page
* @return Generator
* @throws Exception
*/
public function getBooks(int $page = 0)
{ {
//logowanie //logowanie
c('https://www.packtpub.com/', $this->credentials); $this->login();
//pobieranie listy ksiązek //pobieranie listy ksiązek
$return = c('https://www.packtpub.com/account/my-ebooks'); $return = $this->c('https://www.packtpub.com/account/my-ebooks?page=' . $page);
$document = new Document($return); $document = new Document($return);
$books = $document->find('.product-line.unseen'); $books = $document->find('.product-line.unseen');
@@ -175,6 +196,30 @@ class Packt
} }
} }
public function getAllBooks()
{
$this->login();
$data = $this->c(self::BASE_URL . 'mapt-rest/users/me/purchases?limit=100&offset=0&order=DESC&sort=purchase_date');
$jsonData = json_decode($data);
if (isset($jsonData->httpStatus, $loginJson->status) && $jsonData->httpStatus == 200 && $jsonData->status == 'success'){
return $jsonData['data'];
}
}
/**
* zwraca ilość stron książek
*/
public function getNumberOfPages()
{
$this->login();
$return = $this->c(self::MY_BOOKS_PAGE);
$document = new Document($return);
return (int)$document->first('.solr-pager-page-selector a:last-child')->text();
}
/** /**
* @param int $nid * @param int $nid
* @return bool * @return bool
@@ -187,13 +232,60 @@ class Packt
return $result->fetchArray(SQLITE3_ASSOC) === false ? false : true; return $result->fetchArray(SQLITE3_ASSOC) === false ? false : true;
} }
/**
* @param int $nid
* @return array
*/
public function getBookByNid(int $nid)
{
$stmt = $this->getDatabase()->prepare('SELECT * FROM book WHERE nid = :nid');
$stmt->bindValue(':nid', $nid, SQLITE3_INTEGER);
$result = $stmt->execute();
return $result->fetchArray(SQLITE3_ASSOC);
}
public function c($url, $post = [], $localFilePath = false)
{
$cookie = "cookie.txt";
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $url);
if (!is_null($this->accessToken)) {
$authorization = "Authorization: Bearer " . $this->accessToken;
curl_setopt($ch, CURLOPT_HTTPHEADER, array('Content-Type: application/json', $authorization));
}
if (!empty($post) && count($post)) {
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_POSTFIELDS, http_build_query($post));
}
if ($localFilePath) {
$fp = fopen($localFilePath, 'w+');
curl_setopt($ch, CURLOPT_FILE, $fp);
} else {
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
}
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
curl_setopt($ch, CURLOPT_COOKIEJAR, $cookie);
curl_setopt($ch, CURLOPT_COOKIEFILE, $cookie);
$server_output = curl_exec($ch);
curl_close($ch);
return $server_output;
}
public function saveBooks() public function saveBooks()
{ {
foreach ($this->getBooks() as $basicBookInfo) { foreach ($this->getBooks() as $basicBookInfo) {
if ($this->isBookByNid($basicBookInfo['nid'])) { if ($this->isBookByNid($basicBookInfo['nid'])) {
$stmt = $this->getDatabase()->prepare('UPDATE book SET nid = :nid, title = :title, ebook_isbn = :ebook_isbn, img = :img, url = :url, pdf = :pdf, epub = :epub, mobi = :mobi, code = :code, upd_dt = (DATETIME(\'now\')) WHERE nid = :nid'); $stmt = $this->getDatabase()->prepare('UPDATE book SET nid = :nid, title = :title, ebook_isbn = :ebook_isbn, img = :img, url = :url, pdf = :pdf, epub = :epub, mobi = :mobi, code = :code, upd_dt = (DATETIME(\'now\')) WHERE nid = :nid');
} else { } else {
$stmt = $this->getDatabase()->prepare('INSERT INTO book (nid, title, isbn, img, url, pdf, epub, mobi, code) $stmt = $this->getDatabase()->prepare('INSERT INTO book (nid, title, ebook_isbn, img, url, pdf, epub, mobi, code)
VALUES (:nid, :title, :ebook_isbn, :img, :url, :pdf, :epub, :mobi, :code)'); VALUES (:nid, :title, :ebook_isbn, :img, :url, :pdf, :epub, :mobi, :code)');
} }
$stmt->bindValue(':nid', $basicBookInfo['nid'], SQLITE3_INTEGER); $stmt->bindValue(':nid', $basicBookInfo['nid'], SQLITE3_INTEGER);
@@ -213,7 +305,7 @@ VALUES (:nid, :title, :ebook_isbn, :img, :url, :pdf, :epub, :mobi, :code)');
{ {
print_r($bookDetails['nid']); print_r($bookDetails['nid']);
if ($this->isBookByNid($bookDetails['nid'])) { if ($this->isBookByNid($bookDetails['nid'])) {
print_r($bookDetails); print_r($bookDetails);
echo 'xxx'; echo 'xxx';
@@ -254,13 +346,10 @@ VALUES (:nid, :title, :ebook_isbn, :img, :url, :pdf, :epub, :mobi, :code)');
} }
$bookData['title'] = $bookPage->first('h1[itemprop="name"]::text'); $bookData['title'] = $bookPage->first('h1[itemprop="name"]::text');
$bookData['description'] = $bookPage->find('div.book-info-bottom-indetail-text[itemprop="description"] p::text'); $bookData['description'] = implode(' ', $bookPage->find('div.book-info-bottom-indetail-text[itemprop="description"] p::text'));
$bookData['willLearn'] = $bookPage->find('div.book-info-will-learn-text li::text'); $bookData['willLearn'] = $bookPage->find('div.book-info-will-learn-text li::text');
$bookData['category'] = $bookPage->first('div[data-product-id="' . $bookData['paper_isbn'] . '"]::attr(data-product-category)'); $bookData['category'] = $bookPage->first('div[data-product-id="' . $bookData['paper_isbn'] . '"]::attr(data-product-category)');
// $bookData['price'] = $bookPage->first('div[data-product-id="' . $bookData['isbn'] . '"]::attr(data-product-price)');
// $bookData['price'] = $bookPage->first('div[data-product-id="' . $bookData['paper_isbn'] . '"][data-product-type="ebooks"]');
// $bookData['nid'] = $bookPage->first('div[data-product-id="' . $bookData['paper_isbn'] . '"]::attr(data-product-nid)');
$bookData['nid'] = $bookPage->first('div.digital-product[data-product-type="ebooks"]::attr(data-product-nid)'); $bookData['nid'] = $bookPage->first('div.digital-product[data-product-type="ebooks"]::attr(data-product-nid)');
$bookData['authors'] = []; $bookData['authors'] = [];
@@ -274,34 +363,63 @@ VALUES (:nid, :title, :ebook_isbn, :img, :url, :pdf, :epub, :mobi, :code)');
return $bookData; return $bookData;
} }
public function getRandomDatabaseBook()
{
$stmt = $this->getDatabase()->prepare('SELECT * FROM book ORDER BY RANDOM() LIMIT 1');
$result = $stmt->execute();
return $result->fetchArray(SQLITE3_ASSOC);
}
} }
echo '<pre>'; echo '<pre>';
$packt = new Packt($loginData); $packt = new Packt($credentials);
//$books = $packt->saveBooks(); //var_dump($packt->getNumberOfPages());
//print_r($books);
$packt->getAllBooks();
die();
$books = $packt->getBooks();
print_r(iterator_to_array($books));
die();
echo '<pre>'; echo '<pre>';
$bookDetails = $packt->getBookDetails('/web-development/dependency-injection-angularjs');
//$getRandomDatabaseBook = $packt->getRandomDatabaseBook();
//print_r($getRandomDatabaseBook);
//if(!empty($getRandomDatabaseBook['url'])){
$bookDetails = $packt->getBookDetails("/networking-and-servers/windows-server-2016-automation-powershell-cookbook-second-edition");
print_r($bookDetails); print_r($bookDetails);
//$packt->saveBookDetails($bookDetails); $packt->saveBookDetails($bookDetails);
//}
//print_r($packt->getBookByNid($bookDetails['nid']));
die(); die();
function c($url, $post = [], $localFilePath = null) $bookDetails = $packt->getBookDetails('networking-and-servers/windows-server-2016-automation-powershell-cookbook-second-edition');
print_r($bookDetails);
$packt->saveBookDetails($bookDetails);
die();
function c($url, $post = '', $localFilePath = null)
{ {
$cookie = "cookie.txt"; $cookie = "cookie.txt";
$ch = curl_init(); $ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $url); curl_setopt($ch, CURLOPT_URL, $url);
if (!empty($post) && count($post)) { if (!empty($post)) {
curl_setopt($ch, CURLOPT_POST, 1); curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_POSTFIELDS, http_build_query($post)); curl_setopt($ch, CURLOPT_POSTFIELDS, $post);
} }
/** /**
@@ -356,7 +474,7 @@ function getBookInfo($bookUrl)
} }
} }
$bookData['description'] = $bookPage->find('div.book-info-bottom-indetail-text[itemprop="description"] p::text'); $bookData['description'] = implode(' ', $bookPage->find('div.book-info-bottom-indetail-text[itemprop="description"] p::text'));
$bookData['willLearn'] = $bookPage->find('div.book-info-will-learn-text li::text'); $bookData['willLearn'] = $bookPage->find('div.book-info-will-learn-text li::text');
$bookData['category'] = $bookPage->first('div[data-product-id="' . $bookData['isbn'] . '"]::attr(data-product-category)'); $bookData['category'] = $bookPage->first('div[data-product-id="' . $bookData['isbn'] . '"]::attr(data-product-category)');