base_collection.py 文件源码

def dump_to_csv(self, output_csv, input_fields, write_header=True, top_level=False, mode='a', encoding='utf-8', compression=None):
        if compression == 'bz2':
            mode = binary_mode(mode)
            filehandle = bz2.open(output_csv, mode)
        elif compression == 'gzip':
            mode = binary_mode(mode)
            filehandle = gzip.open(output_csv, mode)
        else:
            filehandle = open(output_csv, mode)

        writer = csv.writer(filehandle)
        if write_header:
            writer.writerow(input_fields)
        tweet_parser = TweetParser()

        for tweet in self.get_iterator():
            if top_level:
                ret = list(zip(input_fields, [tweet.get(field) for field in input_fields]))
            else:
                ret = tweet_parser.parse_columns_from_tweet(tweet,input_fields)
            ret_values = [col_val[1] for col_val in ret]
            writer.writerow(ret_values)
        filehandle.close()