利用python读取csv中url并下载

import urllib2
import pandas as pd
import os

导入pandas库读取csv文件

data = pd.read_csv('train_attrs(2).csv')

data.head()

	id	img_url	xml_url
0	2	http://img1.ytgrading.com/sample/attr/2017/12/…	http://img1.ytgrading.com/sample/attr/2017/12/…
1	3	http://img1.ytgrading.com/sample/attr/2017/12/…	http://img1.ytgrading.com/sample/attr/2017/12/…
2	4	http://img1.ytgrading.com/sample/attr/2017/12/…	http://img1.ytgrading.com/sample/attr/2017/12/…
3	5	http://img1.ytgrading.com/sample/attr/2017/12/…	http://img1.ytgrading.com/sample/attr/2017/12/…
4	6	http://img1.ytgrading.com/sample/attr/2017/12/…	http://img1.ytgrading.com/sample/attr/2017/12/…

data.iloc[1]

id                                                         3
img_url    http://img1.ytgrading.com/sample/attr/2017/12/...
xml_url    http://img1.ytgrading.com/sample/attr/2017/12/...
Name: 1, dtype: object

导入urllib2.urlopen下载jpg文件以及xml文件

for i in range(data.shape[0]):
    id1, pic, xml = data.iloc[i]
    f = urllib2.urlopen(pic)
    da = f.read()
    with open('./pic/{0}.jpg'.format(id1), 'wb') as code:
        code.write(da)
    f = urllib2.urlopen(xml)
    da = f.read()
    with open('./xml/{0}.xml'.format(id1), 'wb') as code:
        code.write(da)
    if i % 100 == 0:
        print i

0
100
200
300