extracter.py 文件源码

def __crawl_review(self):
        """
        Crawl review

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

        return np.array(review_list)