Bookshelf/umbra-bookshelf/includes/books/class-umbra-goodreads-scraper.php

<?php
// Copyright 2026 Umbra Tools (umbratools.com)
// SPDX-License-Identifier: Apache-2.0

/**
 * Goodreads Scraper class
 *
 * Fetches author and book data from Goodreads
 *
 * @package Umbra_Bookshelf
 */

if (!defined('ABSPATH')) {
    exit;
}

class Umbra_Goodreads_Scraper {

    private $user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36';

    /**
     * Get author info from Goodreads
     */
    public function get_author_info($author_id) {
        $url = "https://www.goodreads.com/author/show/{$author_id}";
        
        $response = wp_remote_get($url, [
            'timeout' => 30,
            'headers' => [
                'User-Agent' => $this->user_agent,
                'Accept' => 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
                'Accept-Language' => 'en-US,en;q=0.5',
            ],
        ]);
        
        if (is_wp_error($response)) {
            return ['error' => $response->get_error_message()];
        }
        
        $body = wp_remote_retrieve_body($response);
        
        return $this->parse_author_page($body, $author_id);
    }

    /**
     * Get books from Goodreads author page
     */
    public function get_author_books($author_id) {
        $url = "https://www.goodreads.com/author/list/{$author_id}";
        
        $response = wp_remote_get($url, [
            'timeout' => 30,
            'headers' => [
                'User-Agent' => $this->user_agent,
                'Accept' => 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
                'Accept-Language' => 'en-US,en;q=0.5',
            ],
        ]);
        
        if (is_wp_error($response)) {
            return ['error' => $response->get_error_message()];
        }
        
        $body = wp_remote_retrieve_body($response);
        
        return $this->parse_books_list($body);
    }

    /**
     * Get full book details from individual book page
     */
    public function get_book_details($goodreads_id) {
        $url = "https://www.goodreads.com/book/show/{$goodreads_id}";
        
        $response = wp_remote_get($url, [
            'timeout' => 30,
            'headers' => [
                'User-Agent' => $this->user_agent,
                'Accept' => 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
                'Accept-Language' => 'en-US,en;q=0.5',
            ],
        ]);
        
        if (is_wp_error($response)) {
            return ['error' => $response->get_error_message()];
        }
        
        $body = wp_remote_retrieve_body($response);
        
        return $this->parse_book_details($body, $goodreads_id);
    }

    /**
     * Parse author page HTML
     */
    private function parse_author_page($html, $author_id) {
        $author = [
            'id' => $author_id,
            'name' => '',
            'photo' => '',
            'bio' => '',
            'website' => '',
            'genre' => '',
            'books_count' => 0,
            'average_rating' => 0,
        ];
        
        // Extract author name
        if (preg_match('/<h1[^>]*class="[^"]*authorName[^"]*"[^>]*>(.*?)<\/h1>/si', $html, $matches)) {
            $author['name'] = trim(strip_tags($matches[1]));
        }
        
        // Extract photo
        if (preg_match('/<img[^>]*class="[^"]*authorImage[^"]*"[^>]*src="([^"]+)"/si', $html, $matches)) {
            $author['photo'] = $matches[1];
        }
        
        // Extract bio
        if (preg_match('/<div[^>]*class="[^"]*authorAbout[^"]*"[^>]*>.*?<div[^>]*class="[^"]*aboutRight[^"]*"[^>]*>(.*?)<\/div>/si', $html, $matches)) {
            $author['bio'] = trim(strip_tags($matches[1]));
        }
        
        // Extract website
        if (preg_match('/<a[^>]*class="[^"]*authorLink[^"]*"[^>]*href="([^"]+)"/si', $html, $matches)) {
            $author['website'] = $matches[1];
        }
        
        // Extract books count
        if (preg_match('/(\d+)\s*books?/si', $html, $matches)) {
            $author['books_count'] = absint($matches[1]);
        }
        
        return $author;
    }

    /**
     * Parse books list HTML
     */
    private function parse_books_list($html) {
        $books = [];
        
        // Match book rows
        if (preg_match_all('/<tr[^>]*itemtype="http:\/\/schema.org\/Book"[^>]*>(.*?)<\/tr>/si', $html, $matches)) {
            foreach ($matches[1] as $row) {
                $book = $this->parse_book_row($row);
                if ($book) {
                    $books[] = $book;
                }
            }
        }
        
        return $books;
    }

    /**
     * Parse individual book row
     */
    private function parse_book_row($html) {
        $book = [
            'title' => '',
            'author' => '',
            'isbn' => '',
            'isbn13' => '',
            'rating' => 0,
            'ratings_count' => 0,
            'reviews_count' => 0,
            'cover_image' => '',
            'description' => '',
            'published' => '',
            'goodreads_id' => '',
            'goodreads_url' => '',
        ];
        
        // Extract title from bookTitle span (role=heading)
        if (preg_match('/<span[^>]*itemprop=["\']name["\'][^>]*role=["\']heading["\'][^>]*>(.*?)<\/span>/si', $html, $matches)) {
            $book['title'] = trim(strip_tags($matches[1]));
        } elseif (preg_match('/<a[^>]*class="[^"]*bookTitle[^"]*"[^>]*>.*?<span[^>]*>(.*?)<\/span>/si', $html, $matches)) {
            $book['title'] = trim(strip_tags($matches[1]));
        } elseif (preg_match('/<a[^>]*class="[^"]*bookTitle[^"]*"[^>]*>(.*?)<\/a>/si', $html, $matches)) {
            $book['title'] = trim(strip_tags($matches[1]));
        }
        
        // Extract Goodreads URL and ID
        if (preg_match('/<a[^>]*class="[^"]*bookTitle[^"]*"[^>]*href="([^"]+)"/si', $html, $matches)) {
            $book['goodreads_url'] = trim($matches[1]);
            if (preg_match('/\/book\/show\/(\d+)/', $matches[1], $id_matches)) {
                $book['goodreads_id'] = $id_matches[1];
            }
        }
        
        // Extract author
        if (preg_match('/<a[^>]*class="[^"]*authorName[^"]*"[^>]*>.*?<span[^>]*itemprop=["\']name["\'][^>]*>(.*?)<\/span>/si', $html, $matches)) {
            $book['author'] = trim(strip_tags($matches[1]));
        } elseif (preg_match('/<a[^>]*class="[^"]*authorName[^"]*"[^>]*>(.*?)<\/a>/si', $html, $matches)) {
            $book['author'] = trim(strip_tags($matches[1]));
        }
        
        // Extract cover image (class="bookCover" in list, class="bookImage" elsewhere)
        if (preg_match('/<img[^>]*class="[^"]*bookCover[^"]*"[^>]*src="([^"]+)"/si', $html, $matches)) {
            $book['cover_image'] = $matches[1];
        } elseif (preg_match('/<img[^>]*class="[^"]*bookImage[^"]*"[^>]*src="([^"]+)"/si', $html, $matches)) {
            $book['cover_image'] = $matches[1];
        }
        
        // Extract rating from minirating span
        if (preg_match('/([\d.]+)\s*avg\s*rating\s*(?:&mdash;|—|--)\s*(\d[\d,]*)\s*rating/i', $html, $matches)) {
            $book['rating'] = (float) $matches[1];
            $book['ratings_count'] = absint(str_replace(',', '', $matches[2]));
        } elseif (preg_match('/<span[^>]*class="[^"]*rating[^"]*"[^>]*>\s*(\d+\.?\d*)/si', $html, $matches)) {
            $book['rating'] = (float) $matches[1];
        }
        
        // Extract ratings count (fallback)
        if ($book['ratings_count'] === 0 && preg_match('/(\d+[\d,]*)\s*ratings?/si', $html, $matches)) {
            $book['ratings_count'] = absint(str_replace(',', '', $matches[1]));
        }
        
        // Extract reviews count
        if (preg_match('/(\d+[\d,]*)\s*reviews?/si', $html, $matches)) {
            $book['reviews_count'] = absint(str_replace(',', '', $matches[1]));
        }
        
        // Extract ISBN
        if (preg_match('/isbn(?:13)?[:\s]*(\d{10,13})/si', $html, $matches)) {
            $book['isbn'] = $matches[1];
        }
        
        // Extract published date
        if (preg_match('/published[^:]*:\s*([A-Za-z]+\s+\d{1,2},?\s*\d{4})/si', $html, $matches)) {
            $book['published'] = trim($matches[1]);
        }
        
        // Upgrade cover image to larger version
        if (!empty($book['cover_image'])) {
            $book['cover_image'] = $this->upgrade_cover_url($book['cover_image']);
        }
        
        // Only return if we have a title
        if (empty($book['title'])) {
            return null;
        }
        
        return $book;
    }

    /**
     * Parse book details page
     */
    private function parse_book_details($html, $goodreads_id) {
        $book = [
            'goodreads_id' => $goodreads_id,
            'title' => '',
            'author' => '',
            'isbn' => '',
            'isbn13' => '',
            'rating' => 0,
            'ratings_count' => 0,
            'reviews_count' => 0,
            'cover_image' => '',
            'description' => '',
            'published' => '',
            'pages' => 0,
            'genre' => '',
        ];
        
        // Extract title
        if (preg_match('/<h1[^>]*id="bookTitle"[^>]*>(.*?)<\/h1>/si', $html, $matches)) {
            $book['title'] = trim(strip_tags($matches[1]));
        }
        
        // Extract author
        if (preg_match('/<a[^>]*class="[^"]*authorName[^"]*"[^>]*>(.*?)<\/a>/si', $html, $matches)) {
            $book['author'] = trim(strip_tags($matches[1]));
        }
        
        // Extract cover image
        if (preg_match('/<img[^>]*id="coverImage"[^>]*src="([^"]+)"/si', $html, $matches)) {
            $book['cover_image'] = $matches[1];
        }
        
        // Extract description
        if (preg_match('/<div[^>]*id="description"[^>]*>.*?<span[^>]*>(.*?)<\/span>/si', $html, $matches)) {
            $book['description'] = trim(strip_tags($matches[1]));
        }
        
        // Extract ISBN13
        if (preg_match('/isbn13[:\s]*(\d{13})/si', $html, $matches)) {
            $book['isbn13'] = $matches[1];
        }
        
        // Extract ISBN
        if (preg_match('/isbn[:\s]*(\d{10})/si', $html, $matches)) {
            $book['isbn'] = $matches[1];
        }
        
        // Extract rating
        if (preg_match('/<span[^>]*class="[^"]*RatingStatistics__rating[^"]*"[^>]*>(\d+\.?\d*)/si', $html, $matches)) {
            $book['rating'] = (float) $matches[1];
        }
        
        // Extract pages
        if (preg_match('/(\d+)\s*pages?/si', $html, $matches)) {
            $book['pages'] = absint($matches[1]);
        }
        
        // Extract published date
        if (preg_match('/published[^:]*:?\s*([A-Za-z]+\s+\d{1,2},?\s*\d{4})/si', $html, $matches)) {
            $book['published'] = trim($matches[1]);
        }
        
        return $book;
    }

    /**
     * Upgrade a Goodreads cover URL to a larger version
     *
     * Goodreads uses _SY75_ for thumbnails. We can change to _SX300_ for larger.
     */
    private function upgrade_cover_url($url) {
        // Replace thumbnail size with larger version
        $url = preg_replace('/\._SY\d+_/', '._SX300_', $url);
        $url = preg_replace('/\._SX\d+_/', '._SX300_', $url);
        return $url;
    }
}