csv_collection.py 文件源码

def get_iterator(self):
        tweet_parser = TweetParser()
        if self.compression == 'bz2':
            self.mode = binary_mode(self.mode)
            csv_handle = bz2.open(self.filepath, self.mode, encoding=self.encoding)
        elif self.compression == 'gzip':
            self.mode = binary_mode(self.mode)
            csv_handle = gzip.open(self.filepath, self.mode, encoding=self.encoding)
        else:       
            csv_handle = open(self.filepath, self.mode, encoding=self.encoding)
        for count, tweet in enumerate(csv.DictReader(csv_handle)):
            if self.limit < count+1 and self.limit != 0:
                csv_handle.close()
                return
            elif tweet_parser.tweet_passes_filter(self.filter, tweet) \
            and tweet_parser.tweet_passes_custom_filter_list(self.custom_filters, tweet):
                if self.should_strip:
                    yield tweet_parser.strip_tweet(self.keep_fields, tweet) 
                else: 
                    yield dict(tweet)
        csv_handle.close()