[{"createTime":1735734952000,"id":1,"img":"hwy_ms_500_252.jpeg","link":"https://activity.huaweicloud.com/cps.html?fromacct=261f35b6-af54-4511-a2ca-910fa15905d1&utm_source=V1g3MDY4NTY=&utm_medium=cps&utm_campaign=201905","name":"华为云秒杀","status":9,"txt":"华为云38元秒杀","type":1,"updateTime":1735747411000,"userId":3},{"createTime":1736173885000,"id":2,"img":"txy_480_300.png","link":"https://cloud.tencent.com/act/cps/redirect?redirect=1077&cps_key=edb15096bfff75effaaa8c8bb66138bd&from=console","name":"腾讯云秒杀","status":9,"txt":"腾讯云限量秒杀","type":1,"updateTime":1736173885000,"userId":3},{"createTime":1736177492000,"id":3,"img":"aly_251_140.png","link":"https://www.aliyun.com/minisite/goods?userCode=pwp8kmv3","memo":"","name":"阿里云","status":9,"txt":"阿里云2折起","type":1,"updateTime":1736177492000,"userId":3},{"createTime":1735660800000,"id":4,"img":"vultr_560_300.png","link":"https://www.vultr.com/?ref=9603742-8H","name":"Vultr","status":9,"txt":"Vultr送$100","type":1,"updateTime":1735660800000,"userId":3},{"createTime":1735660800000,"id":5,"img":"jdy_663_320.jpg","link":"https://3.cn/2ay1-e5t","name":"京东云","status":9,"txt":"京东云特惠专区","type":1,"updateTime":1735660800000,"userId":3},{"createTime":1735660800000,"id":6,"img":"new_ads.png","link":"https://www.iodraw.com/ads","name":"发布广告","status":9,"txt":"发布广告","type":1,"updateTime":1735660800000,"userId":3},{"createTime":1735660800000,"id":7,"img":"yun_910_50.png","link":"https://activity.huaweicloud.com/discount_area_v5/index.html?fromacct=261f35b6-af54-4511-a2ca-910fa15905d1&utm_source=aXhpYW95YW5nOA===&utm_medium=cps&utm_campaign=201905","name":"底部","status":9,"txt":"高性能云服务器2折起","type":2,"updateTime":1735660800000,"userId":3}]
我目前正试图从Python
2.7中的.csv文件读取数据，最多1百万行和200列(文件范围从100mb到1.6gb)。我可以这样做(非常慢)对于300,000行以下的文件，但一旦我走上，我得到内存错误。我的代码看起来像这样：
def getdata(filename, criteria):
data=[]
for criterion in criteria:
data.append(getstuff(filename, criteron))
return data
def getstuff(filename, criterion):
import csv
data=[]
with open(filename, "rb") as csvfile:
datareader=csv.reader(csvfile)
for row in datareader:
if row[3]=="column header":
data.append(row)
elif len(data)<2 and row[3]!=criterion:
pass
elif row[3]==criterion:
data.append(row)
else:
return data
getstuff函数中的else子句的原因是所有符合条件的元素将一起列在csv文件中，所以我离开循环，当我得到它们以节省时间。
我的问题是：
>我如何能够使这个工作与更大的文件？
>有什么办法可以让它更快吗？
我的电脑有8GB RAM，运行64位Windows 7，处理器是3.40 GHz(不确定你需要什么信息)。
非常感谢任何帮助！
