Download csv file from yahoo

urllib urlretrieve

/*
  python2： from urllib import urlretrieve
*/

// Python3
from urllib import request

// download csv file to local
request.urlretrieve('http://table.finance.yahoo.com/table.csv?s=000001.sz', 'pingan.csv')

CSV Module

import csv, os

with open('pingan.csv', 'r') as rf:
    reader = csv.reader(rf)
    print(reader)
    for row in reader:
        print(row)
    
    rf.seek(0)  // rf指针要归0，否则，下面next的时候会报错
    # rf.seek(0, os.SEEK_SET)  

    with open('pingan_copy.csv', 'wb') as wf:
        writer = csv.writer(wf)
        writer.writerow(next(reader))
        writer.writerow(next(reader))
        writer.writerow(next(reader))

        wf.flush() // 文本中马上可见

'''
// 这里读写方式要把'rb'/'wb'改为'r'/'w'才行
# with open('pingan.csv', 'rb') as rf:
# with open('pingan_copy.csv', 'wb') as wf:
# _csv.Error: iterator should return strings, not bytes (did you open the file in text mode?)

// 这里要把reader.next()改为next(reader)才行
# writer.writerow(reader.next())
# '_csv.reader' object has no attribute 'next'

'''

Final code

import csv

with open('pingan.csv', 'r') as rf:
    reader = csv.reader(rf)
    with open('pingan2.csv', 'w') as wf:
        writer = csv.writer(wf)
        headers = next(reader)  # 越过第一行，因为是标题行，不是数据
        writer.writerow(headers)
        '''
        ['Date', 'Open', 'High', 'Low', 'Close', 'Volume', 'Adj Close']
        ['2016-09-09', '9.40', '9.43', '9.36', '9.38', '32743100', '9.38']
        
        每列的数据，可以直接取，比如日期Date：row[0]，如成交量Volume：row[5]，但是这里取到的是string，而不是数值
        '''
        for row in reader:
            if row[0] < '2016-01-01':  # 日期可以直接比较
                break
            if int(row[5]) >= 50000000:
                writer.writerow(row)

print('end')