Created
July 24, 2025 15:37
-
-
Save codearachnid/816586134dbbd679cd0b0b03abe50c44 to your computer and use it in GitHub Desktop.
Simple parser to convert csv export from brightdata into json output for normalization
This file contains hidden or 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 | |
| function parseCsvRowToJson($csvRow) { | |
| $keys = [ | |
| 'url', 'domain', 'country_code', 'model_number', 'sku', 'product_id', 'product_name', 'manufacturer', | |
| 'final_price', 'initial_price', 'currency', 'in_stock', 'root_category', 'category', 'category_tree', | |
| 'rating', 'reviews_count', 'answered_questions_count', 'main_image', 'image_urls', 'features', | |
| 'dimensions', 'weight', 'details', 'warranty', 'related_documents', 'top_reviews', 'answered_questions', | |
| 'upc', 'upcgtin13', 'price_range', 'availability_text', 'promotion_fulltext', 'available_to_delivery', | |
| 'zipcode', 'store_name', 'store_number', 'description', 'timestamp', 'input', 'discovery_input', | |
| 'error', 'error_code', 'warning', 'warning_code' | |
| ]; | |
| $data = str_getcsv($csvRow); | |
| $result = []; | |
| foreach ($keys as $index => $key) { | |
| $value = $data[$index] ?? ''; | |
| // Handle specific data types | |
| switch ($key) { | |
| case 'final_price': | |
| case 'initial_price': | |
| case 'rating': | |
| $result[$key] = floatval($value); | |
| break; | |
| case 'reviews_count': | |
| case 'answered_questions_count': | |
| case 'available_to_delivery': | |
| case 'zipcode': | |
| $result[$key] = intval($value); | |
| break; | |
| case 'in_stock': | |
| $result[$key] = $value === 'TRUE'; | |
| break; | |
| case 'root_category': | |
| case 'category': | |
| case 'input': | |
| case 'discovery_input': | |
| $result[$key] = $value ? json_decode($value, true) : []; | |
| break; | |
| case 'category_tree': | |
| case 'image_urls': | |
| case 'features': | |
| case 'dimensions': | |
| case 'details': | |
| case 'related_documents': | |
| case 'top_reviews': | |
| case 'answered_questions': | |
| $result[$key] = $value ? json_decode($value, true) : []; | |
| break; | |
| default: | |
| $result[$key] = $value; | |
| break; | |
| } | |
| } | |
| return json_encode($result, JSON_PRETTY_PRINT); | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment