12345678910111213141516171819202122 |
- from crawler import BreadthCrawler
- from crawler.engines import BingSearchEngine
- def main():
- engines_lst = [BingSearchEngine()]
- BreadthCrawler(
- init_validator=True,
- url_weight=20,
- org_weight=5,
- keyword_weight=15,
- engines=engines_lst,
- max_query_page=30,
- loop_sync_interval=1200,
- loop_query_interval=30,
- loop_excavate_interval=10,
- excavate_workers=1,
- ).start()
- if __name__ == '__main__':
- main()
|