run.py 文件源码

def get_top_blogs():
    """
    Get URLs of most popular blog posts for most popular programming languages
    on GitHub.
    """
    languages = get_top_languages(30, settings['LANGUAGES_DATA'])
    process = CrawlerProcess(settings)
    process.crawl(BlogsSpider, languages)
    process.start()  # the script will block here until the crawling is done