krzysiej/bookinfo
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Updated a way of parsing a single book page to find language, publisher and book description. Also, url of a page is now attached to the book info object.

Browse Source
This commit is contained in:
krzysiej
2022-05-27 10:54:39 +02:00
parent 825348ce7a
commit 293a776d16
3 changed files with 11 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/Api/AbstractBookInfo.php
View File

@@ -14,6 +14,7 @@ abstract class AbstractBookInfo
public int $pages; public int $pages;
public string $cycle; public string $cycle;
public int $volume; public int $volume;
public string $language; public ?string $language;
public string $datePublished; public string $datePublished;
public ?string $publisher;
} }

6
src/BookFinder.php
View File

@@ -7,7 +7,7 @@ use Techtube\Bookinfo\Api\AbstractBookInfo;
class BookFinder class BookFinder
{ {
private static $searchUrl = 'https://lubimyczytac.pl/szukaj/ksiazki?phrase='; private static string $searchUrl = 'https://lubimyczytac.pl/szukaj/ksiazki?phrase=';
private DataParser $parser; private DataParser $parser;
@@ -21,12 +21,12 @@ class BookFinder
return $this->parser->searchPage(new Document($this->getSearchUrl($phrase), true)); return $this->parser->searchPage(new Document($this->getSearchUrl($phrase), true));
} }
public function byUrl($url): AbstractBookInfo public function byUrl(string $url): AbstractBookInfo
{ {
return $this->parser->singlePage(new Document($url, true)); return $this->parser->singlePage(new Document($url, true));
} }
public function getSearchUrl(string $phrase): string private function getSearchUrl(string $phrase): string
{ {
return self::$searchUrl . $phrase; return self::$searchUrl . $phrase;
} }

10
src/DataParser.php
View File

@@ -18,21 +18,23 @@ class DataParser
{ {
$info = new Info(); $info = new Info();
$jsonInfo = json_decode($document->first('script[type="application/ld+json"]')->text()); $jsonInfo = json_decode($document->first('script[type="application/ld+json"]')->text());
$info->url = $document->getDocument()->baseURI;
$info->publisher = $document->first('a[href*="wydawnictwo"]')?->text();
$info->author = $document->first('meta[property="books:author"]')->getAttribute('content'); $info->author = $document->first('meta[property="books:author"]')->getAttribute('content');
$info->isbn = $document->first('meta[property="books:isbn"]')->getAttribute('content'); $info->isbn = $document->first('meta[property="books:isbn"]')->getAttribute('content');
$info->description = $document->first('meta[property="og:description"]')->getAttribute('content'); $info->description = trim($document->first('#book-description p')->text());
$info->title = trim($document->first('h1.book__title')->text()); $info->title = trim($document->first('h1.book__title')->text());
$info->category = trim($document->first('.book__category')->text()); $info->category = trim($document->first('.book__category')->text());
$info->cover_url = $this->generateCoverUrls( $info->cover_url = $this->generateCoverUrls(
$document->first('meta[property="og:image"]')->getAttribute('content') $document->first('meta[property="og:image"]')->getAttribute('content')
); );
$info->pages = (int)$document->first('span.book__pages')?->text(); $info->pages = (int)$document->first('span.book__pages')?->text();
if (preg_match('#(.*) \(tom (\d*)\)#ism', trim($document->first('a[href*="/cykl/"]')?->text()), $series)) { if (preg_match('#(.*) \(tom (\d*)\)#ism', trim($document->first('a[href*="/cykl/"]')?->text() ?? ''), $series)) {
$info->cycle = $series[1]; $info->cycle = $series[1];
$info->volume = $series[2]; $info->volume = $series[2];
} }
$info->language = $jsonInfo->inLanguage ?? null; $info->language = $jsonInfo?->inLanguage ?? trim($document->xpath("//*[contains(text(), 'Język:')]")[0]->nextSibling('dd')->text());
$info->datePublished = $jsonInfo->datePublished ?? null; $info->datePublished = $jsonInfo?->datePublished ?? null;
return $info; return $info;
} }