extracter.py 文件源码

def __crawl_summary(self):
        """
        Crawl summary

        :return: summary [numpy array]
        """
        summary_list = []
        print 'Crawling Summary....'
        num_lines = 0
        with open(self.raw_data_file) as infile:
            for line in infile:
                if line.startswith('review/summary'):
                    if num_lines >= self.num_reviews:
                        break
                    num_lines += 1
                    _,summary = line.split('/summary: ')
                    summary_list.append(summary)

        return np.array(summary_list)