Spaces:
Sleeping
Sleeping
removing old test_scraper.py
Browse files- scripts/test_scraper.py +0 -34
scripts/test_scraper.py
DELETED
|
@@ -1,34 +0,0 @@
|
|
| 1 |
-
from mediaunmasked.scrapers.article_scraper import ArticleScraper
|
| 2 |
-
import logging
|
| 3 |
-
|
| 4 |
-
# Configure logging
|
| 5 |
-
logging.basicConfig(level=logging.INFO)
|
| 6 |
-
logger = logging.getLogger(__name__)
|
| 7 |
-
|
| 8 |
-
def test_scraper():
|
| 9 |
-
scraper = ArticleScraper()
|
| 10 |
-
url = "https://www.channelnewsasia.com/singapore/singapore-mccy-sg-culture-pass-arts-culture-heritage-4951451"
|
| 11 |
-
|
| 12 |
-
logger.info(f"Testing scraper with URL: {url}")
|
| 13 |
-
|
| 14 |
-
try:
|
| 15 |
-
result = scraper.scrape_article(url)
|
| 16 |
-
|
| 17 |
-
if result:
|
| 18 |
-
print("\nScraping Successful!")
|
| 19 |
-
print("-" * 50)
|
| 20 |
-
print(f"Headline: {result['headline']}")
|
| 21 |
-
print("-" * 50)
|
| 22 |
-
print("Content Preview (first 500 chars):")
|
| 23 |
-
print(result['content'][:500])
|
| 24 |
-
print("...")
|
| 25 |
-
print("-" * 50)
|
| 26 |
-
print(f"Total content length: {len(result['content'])} characters")
|
| 27 |
-
else:
|
| 28 |
-
print("Scraping failed - no result returned")
|
| 29 |
-
|
| 30 |
-
except Exception as e:
|
| 31 |
-
logger.error(f"Error during scraping: {str(e)}", exc_info=True)
|
| 32 |
-
|
| 33 |
-
if __name__ == "__main__":
|
| 34 |
-
test_scraper()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|