Fatal编程技术网
  • python/
  • 无法将txt转换为Python

无法将txt转换为Python

python csv python-3.x

无法将txt转换为Python,python,csv,python-3.x,data-retrieval,quandl,Python,Csv,Python 3.x,Data Retrieval,Quandl,我试图通过以下代码获取特定公司的关键财务数据（股票代码如下）： netIncomeAr = [] endLink = 'order=asc' # order=asc& try: netIncome = urllib.request.urlopen('https://www.quandl.com/api/v3/datasets/RAYMOND/'+stock.upper()+'_NET_INCOME_A.csv

我试图通过以下代码获取特定公司的关键财务数据（股票代码如下）：

        netIncomeAr = []

        endLink = 'order=asc'   # order=asc&
        try:

            netIncome = urllib.request.urlopen('https://www.quandl.com/api/v3/datasets/RAYMOND/'+stock.upper()+'_NET_INCOME_A.csv?'+endLink).read()

            splitNI = netIncome.split('\n')
            print('Net Income:')
            for eachNI in splitNI[1:-1]:
                print(eachNI)
                netIncomeAr.append(eachNI)


            incomeDate, income = np.loadtxt(netIncomeAr, delimiter=',',unpack=True,
                                            converters={ 0: mdates.strpdate2num('%Y-%m-%d')})

        except Exception as e:
            print('failed in the Quandl grab')
            print(str(e))
            time.sleep(555)
但我得到了我设计的错误消息“Quandl抓取失败”。我知道错误一定在从Quandl执行urllib.request的第一行中

有人知道为什么这个代码不起作用吗

好的，谢谢罗兰

我已将代码更改为这个有限的概念验证片段：

import urllib.request, urllib.error, urllib.parse
import time
import datetime
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.ticker as mticker
import matplotlib.dates as mdates

evenBetter = ['GOOG','AAPL']


def graphData(stock, MA1, MA2):
    #######################################
    #######################################
    '''
        Use this to dynamically pull a stock from Quandl:
    '''
    print('Currently Pulling',stock)

    netIncomeAr = []
#    revAr = []
#    ROCAr = []

    endLink = 'order=asc'

    netIncome = str(urllib.request.urlopen('https://www.quandl.com/api/v3/datasets/RAYMOND/'+stock.upper()+'_NET_INCOME_A.csv?'+endLink).read())[2:-1]
    # convert to string, remove leading "b'" and trailing "'" characters.
    # netIncome = 'head\\ndata\\ndata\\n...'


    splitNI = netIncome.split('\\')[1:-1]
    # data segments still have leading 'n' character.
    # the [1:-1] is more pythonic and releases memory.
    for i in range (len(splitNI)):
        splitNI[i] = splitNI[i][1:]
    # data segments are now converted.

    print('Net Income:')
    for eachNI in splitNI:
        print(eachNI)
        netIncomeAr.append(eachNI)


    incomeDate, income = np.loadtxt(netIncomeAr, delimiter=',',unpack=True,
                                    converters={ 0: mdates.strpdate2num('%Y-%m-%d')})

for stock in evenBetter:
    graphData(stock,25,50)
现在，我已经解决了urllib.request问题，现在又遇到了另一个问题。。。以下错误：

Currently Pulling GOOG
Net Income:
2009-12-31,6520448000.0
2010-12-31,8505000000.0
2011-12-31,9737000000.0
2012-12-31,10737000000.0
2013-12-31,12920000000.0
Traceback (most recent call last):

  File "<ipython-input-3-5ce0b8405254>", line 1, in <module>
    runfile('C:/Users/Morten/Google Drev/SpyderProject/test/Test_sentdex_comp_screener_own_webscraper2.py', wdir='C:/Users/Morten/Google Drev/SpyderProject/test')

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site-packages\spyderlib\widgets\externalshell\sitecustomize.py", line 682, in runfile
    execfile(filename, namespace)

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site-packages\spyderlib\widgets\externalshell\sitecustomize.py", line 85, in execfile
    exec(compile(open(filename, 'rb').read(), filename, 'exec'), namespace)

  File "C:/Users/Morten/Google Drev/SpyderProject/test/Test_sentdex_comp_screener_own_webscraper2.py", line 57, in <module>
    graphData(stock,25,50)

  File "C:/Users/Morten/Google Drev/SpyderProject/test/Test_sentdex_comp_screener_own_webscraper2.py", line 54, in graphData
    converters={ 0: mdates.strpdate2num('%Y-%m-%d')})

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site-packages\numpy\lib\npyio.py", line 860, in loadtxt
    items = [conv(val) for (conv, val) in zip(converters, vals)]

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site-packages\numpy\lib\npyio.py", line 860, in <listcomp>
    items = [conv(val) for (conv, val) in zip(converters, vals)]

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site-packages\matplotlib\dates.py", line 261, in __call__
    return date2num(datetime.datetime(*time.strptime(s, self.fmt)[:6]))

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\_strptime.py", line 494, in _strptime_time
    tt = _strptime(data_string, format)[0]

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\_strptime.py", line 306, in _strptime
    raise TypeError(msg.format(index, type(arg)))

TypeError: strptime() argument 0 must be str, not <class 'bytes'>
我看到这个错误：

Currently Pulling GOOG
Net Income:
C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site-packages\numpy\lib\npyio.py:823: UserWarning: loadtxt: Empty input file: "[]"
  warnings.warn('loadtxt: Empty input file: "%s"' % fname)
Traceback (most recent call last):

  File "<ipython-input-1-c3f1db0f3995>", line 1, in <module>
    runfile('C:/Users/Morten/Google Drev/SpyderProject/test/sentdex_Test_comp_screener_own_webscraper2.py', wdir='C:/Users/Morten/Google Drev/SpyderProject/test')

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site-packages\spyderlib\widgets\externalshell\sitecustomize.py", line 682, in runfile
    execfile(filename, namespace)

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site-packages\spyderlib\widgets\externalshell\sitecustomize.py", line 85, in execfile
    exec(compile(open(filename, 'rb').read(), filename, 'exec'), namespace)

  File "C:/Users/Morten/Google Drev/SpyderProject/test/sentdex_Test_comp_screener_own_webscraper2.py", line 60, in <module>
    graphData(stock)

  File "C:/Users/Morten/Google Drev/SpyderProject/test/sentdex_Test_comp_screener_own_webscraper2.py", line 56, in graphData
    converters={ 0: mdates.strpdate2num('%Y-%m-%d')})

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site-packages\numpy\lib\npyio.py", line 845, in loadtxt
    converters[i] = conv

IndexError: list assignment index out of range
根据Davse Bamse今天（2015年10月13日）的输入，我得到以下错误：

Currently Pulling GOOG
Net Income:
2009-12-31,6520448000.0
2010-12-31,8505000000.0
2011-12-31,9737000000.0
2012-12-31,10737000000.0
2013-12-31,12920000000.0
Traceback (most recent call last):

  File "<ipython-input-13-5ce0b8405254>", line 1, in <module>
    runfile('C:/Users/Morten/Google Drev/SpyderProject/test/Test_sentdex_comp_screener_own_webscraper2.py', wdir='C:/Users/Morten/Google Drev/SpyderProject/test')

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site-packages\spyderlib\widgets\externalshell\sitecustomize.py", line 682, in runfile
    execfile(filename, namespace)

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site-packages\spyderlib\widgets\externalshell\sitecustomize.py", line 85, in execfile
    exec(compile(open(filename, 'rb').read(), filename, 'exec'), namespace)

  File "C:/Users/Morten/Google Drev/SpyderProject/test/Test_sentdex_comp_screener_own_webscraper2.py", line 54, in <module>
    graphData(stock,25,50)

  File "C:/Users/Morten/Google Drev/SpyderProject/test/Test_sentdex_comp_screener_own_webscraper2.py", line 51, in graphData
    converters={ 0: mdates.strpdate2num('%Y-%m-%d')})

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site-packages\numpy\lib\npyio.py", line 740, in loadtxt
    fh = iter(open(fname))

OSError: [Errno 22] Invalid argument: '2009-12-31,6520448000.0\n2010-12-31,8505000000.0\n2011-12-31,9737000000.0\n2012-12-31,10737000000.0\n2013-12-31,12920000000.0'
但这给了我和以前一样的错误。。。有什么想法吗

将转换器线路更改为：

incomeDate, income = np.loadtxt(StringIO('\n'.join(netIncomeAr)), delimiter=',',unpack=True,
                                converters={ 0: mdates.strpdate2num('%Y-%m-%d')})
提供以下堆栈跟踪：

Currently Pulling GOOG
Net Income:
2009-12-31,6520448000.0
2010-12-31,8505000000.0
2011-12-31,9737000000.0
2012-12-31,10737000000.0
2013-12-31,12920000000.0
Traceback (most recent call last):

  File "<ipython-input-26-5ce0b8405254>", line 1, in <module>
    runfile('C:/Users/Morten/Google Drev/SpyderProject/test/Test_sentdex_comp_screener_own_webscraper2.py', wdir='C:/Users/Morten/Google Drev/SpyderProject/test')

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site-packages\spyderlib\widgets\externalshell\sitecustomize.py", line 682, in runfile
    execfile(filename, namespace)

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site-packages\spyderlib\widgets\externalshell\sitecustomize.py", line 85, in execfile
    exec(compile(open(filename, 'rb').read(), filename, 'exec'), namespace)

  File "C:/Users/Morten/Google Drev/SpyderProject/test/Test_sentdex_comp_screener_own_webscraper2.py", line 60, in <module>
    graphData(stock,25,50)

  File "C:/Users/Morten/Google Drev/SpyderProject/test/Test_sentdex_comp_screener_own_webscraper2.py", line 57, in graphData
    converters={ 0: mdates.strpdate2num('%Y-%m-%d')})

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site-packages\numpy\lib\npyio.py", line 860, in loadtxt
    items = [conv(val) for (conv, val) in zip(converters, vals)]

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site-packages\numpy\lib\npyio.py", line 860, in <listcomp>
    items = [conv(val) for (conv, val) in zip(converters, vals)]

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site-packages\matplotlib\dates.py", line 261, in __call__
    return date2num(datetime.datetime(*time.strptime(s, self.fmt)[:6]))

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\_strptime.py", line 494, in _strptime_time
    tt = _strptime(data_string, format)[0]

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\_strptime.py", line 306, in _strptime
    raise TypeError(msg.format(index, type(arg)))

TypeError: strptime() argument 0 must be str, not <class 'bytes'>
输出

Currently Pulling GOOG
Net Income:
2009-12-31,6520448000.0
2010-12-31,8505000000.0
2011-12-31,9737000000.0
2012-12-31,10737000000.0
2013-12-31,12920000000.0
Traceback (most recent call last):

  File "<ipython-input-10-5ce0b8405254>", line 1, in <module>
    runfile('C:/Users/Morten/Google Drev/SpyderProject/test/Test_sentdex_comp_screener_own_webscraper2.py', wdir='C:/Users/Morten/Google Drev/SpyderProject/test')

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site-packages\spyderlib\widgets\externalshell\sitecustomize.py", line 682, in runfile
    execfile(filename, namespace)

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site-packages\spyderlib\widgets\externalshell\sitecustomize.py", line 85, in execfile
    exec(compile(open(filename, 'rb').read(), filename, 'exec'), namespace)

  File "C:/Users/Morten/Google Drev/SpyderProject/test/Test_sentdex_comp_screener_own_webscraper2.py", line 50, in <module>
    graphData(stock,25,50)

  File "C:/Users/Morten/Google Drev/SpyderProject/test/Test_sentdex_comp_screener_own_webscraper2.py", line 47, in graphData
    converters={ 0: mdates.strpdate2num('%Y-%m-%d')})

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site-packages\numpy\lib\npyio.py", line 1366, in genfromtxt
    fhd = iter(np.lib._datasource.open(fname, 'rb'))

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site-packages\numpy\lib\_datasource.py", line 151, in open
    return ds.open(path, mode)

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site-packages\numpy\lib\_datasource.py", line 501, in open
    raise IOError("%s not found." % path)

OSError: 2009-12-31,6520448000.0
2010-12-31,8505000000.0
2011-12-31,9737000000.0
2012-12-31,10737000000.0
2013-12-31,12920000000.0 not found.

当前正在拉GOOG
净收入：
2009-12-31,6520448000.0
2010-12-31,8505000000.0
2011-12-31,9737000000.0
2012-12-31,10737000000.0
2013-12-31,12920000000.0
回溯（最近一次呼叫最后一次）：
文件“”，第1行，在
运行文件（'C:/Users/Morten/Google-Drev/SpyderProject/test/test\u sentdex\u comp\u screener\u own\u webscraper2.py'，wdir='C:/Users/Morten/Google-Drev/SpyderProject/test'）
文件“C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site packages\spyderlib\widgets\externalshell\sitecustomize.py”，第682行，在runfile中
execfile（文件名、命名空间）
文件“C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site packages\spyderlib\widgets\externalshell\sitecustomize.py”，第85行，在execfile中
exec（编译（打开（文件名'rb'）.read（），文件名'exec'），命名空间）
文件“C:/Users/Morten/Google-Drev/SpyderProject/test/test\u sentdex\u comp\u screener\u own\u webscraper2.py”，第50行，在
graphData（库存，25,50）
文件“C:/Users/Morten/Google Drev/SpyderProject/test/test\u sentdex\u comp\u screener\u own\u webscraper2.py”，第47行，以图形数据形式显示
转换器={0:mdates.strpdate2num（“%Y-%m-%d”）}
文件“C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site packages\numpy\lib\npyio.py”，第1366行，格式为genfromtxt
fhd=iter（np.lib.\u datasource.open（fname，'rb'））
文件“C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site packages\numpy\lib\\ u datasource.py”，第151行，打开
返回ds.open（路径、模式）
文件“C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site packages\numpy\lib\\ u datasource.py”，第501行，打开
raise IOError（“%s未找到”。%path）
操作错误：2009-12-316520448000.0
2010-12-31,8505000000.0
2011-12-31,9737000000.0
2012-12-31,10737000000.0
2013-12-3112920000000.0未找到。
我不知道这是好是坏…

在Python 3.x中，urllib.request.urlopen（…）.read（）函数如果成功，将返回一个ByteArray-而不是字符串对象

将ByteArray转换为字符串的解决方案如下：

...
netIncome = str(urllib.request.urlopen('https://www.quandl.com/api/v3/datasets/RAYMOND/'+stock.upper()+'_NET_INCOME_A.csv?'+endLink).read())[2:-1]
# convert to string, remove leading "b'" and trailing "'" characters.
# netIncome = 'head\\ndata\\ndata\\n...'
...

splitNI = netIncome.split('\\')[1:-1]
# data segments still have leading 'n' character.
# the [1:-1] is more pythonic and releases memory.
for i in range (len(splitNI)):
    splitNI[i] = splitNI[i][1:]
# data segments are now converted.

print('Net Income:')
for eachNI in splitNI:
    print(eachNI)
    netIncomeAr.append(eachNI)
在Python3.x中，urllib.request.urlopen（…）.read（）函数如果成功，将返回ByteArray-而不是字符串对象

将ByteArray转换为字符串的解决方案如下：

...
netIncome = str(urllib.request.urlopen('https://www.quandl.com/api/v3/datasets/RAYMOND/'+stock.upper()+'_NET_INCOME_A.csv?'+endLink).read())[2:-1]
# convert to string, remove leading "b'" and trailing "'" characters.
# netIncome = 'head\\ndata\\ndata\\n...'
...

splitNI = netIncome.split('\\')[1:-1]
# data segments still have leading 'n' character.
# the [1:-1] is more pythonic and releases memory.
for i in range (len(splitNI)):
    splitNI[i] = splitNI[i][1:]
# data segments are now converted.

print('Net Income:')
for eachNI in splitNI:
    print(eachNI)
    netIncomeAr.append(eachNI)
正如罗兰指出的，问题在于返回的是bytearray，而不是字符串

但是，代码应如下所示：

netIncomeBytes = urllib.request.urlopen('https://www.quandl.com/api/v3/datasets/RAYMOND/'+stock.upper()+'_NET_INCOME_A.csv?'+endLink).read()
netIncome = netIncomeBytes.decode("utf-8")
这将把字节数组转换成utf-8中的字符串。

正如罗兰指出的，问题在于返回的是字节数组，而不是字符串

但是，代码应如下所示：

netIncomeBytes = urllib.request.urlopen('https://www.quandl.com/api/v3/datasets/RAYMOND/'+stock.upper()+'_NET_INCOME_A.csv?'+endLink).read()
netIncome = netIncomeBytes.decode("utf-8")
这将把bytearray转换为utf-8格式的字符串。

什么是
打印（str（e））
打印？删除代码块周围的try/catch，再次运行它，然后打印堆栈跟踪。“Exception as e:”行掩盖了错误。感谢罗兰，Stacktrace现在包含在上述问题中。什么是
print（str（e））
prints？删除代码块周围的try/catch，再次运行，然后打印Stacktrace。“例外情况除外为e:”行掩盖了故障。感谢罗兰，Stacktrace现在包括在上述问题中。感谢大卫，我想这不是一个容易破解的问题。现在我得到了另一个错误，根本看不到任何数据。请看我在上面问题中的编辑。这确实解决了第一个问题。现在问题出在您创建转换器的线路上。尝试将其添加为列表（用[and]括起来）。它表示它无法获取第i个转换器，因此我猜测它必须是一个列表。你能找到你正在调用的函数的文档吗？它似乎在没有列表的情况下工作[]。或者我不确定您将在哪里制作列表…？好的，在转换器中添加了一个列表。请参阅我最初问题中的编辑。仍然看到错误。？？我已经阅读了loadtext函数的文档。转换器是一个dict，而不是我认为的列表。无需使用[和]。谢谢David，我想这不是一个容易破解的问题。现在我遇到了另一个错误，根本看不到任何数据。请参阅我在上述问题中的编辑。这确实解决了第一个问题。问题现在出现在您创建转换器的行中。请尝试将其作为列表添加（用[and]包围）。它说它无法获取第i个转换器，因此我猜测它必须是一个列表。你能找到你正在调用的函数的文档吗？它似乎在没有列表的情况下工作[]。或者我不确定您将在何处创建列表…？好的，在转换器中添加了一个列表。请参阅我最初问题中的编辑。仍然看到错误。？？我已经阅读了loadtext函数的文档。转换器是一个dict，而不是我认为的列表。无需使用[和]。 
Currently Pulling GOOG
Net Income:
2009-12-31,6520448000.0
2010-12-31,8505000000.0
2011-12-31,9737000000.0
2012-12-31,10737000000.0
2013-12-31,12920000000.0
Traceback (most recent call last):

  File "<ipython-input-10-5ce0b8405254>", line 1, in <module>
    runfile('C:/Users/Morten/Google Drev/SpyderProject/test/Test_sentdex_comp_screener_own_webscraper2.py', wdir='C:/Users/Morten/Google Drev/SpyderProject/test')

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site-packages\spyderlib\widgets\externalshell\sitecustomize.py", line 682, in runfile
    execfile(filename, namespace)

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site-packages\spyderlib\widgets\externalshell\sitecustomize.py", line 85, in execfile
    exec(compile(open(filename, 'rb').read(), filename, 'exec'), namespace)

  File "C:/Users/Morten/Google Drev/SpyderProject/test/Test_sentdex_comp_screener_own_webscraper2.py", line 50, in <module>
    graphData(stock,25,50)

  File "C:/Users/Morten/Google Drev/SpyderProject/test/Test_sentdex_comp_screener_own_webscraper2.py", line 47, in graphData
    converters={ 0: mdates.strpdate2num('%Y-%m-%d')})

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site-packages\numpy\lib\npyio.py", line 1366, in genfromtxt
    fhd = iter(np.lib._datasource.open(fname, 'rb'))

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site-packages\numpy\lib\_datasource.py", line 151, in open
    return ds.open(path, mode)

  File "C:\Program Files\WinPython-64bit-3.3.5.7\python-3.3.5.amd64\lib\site-packages\numpy\lib\_datasource.py", line 501, in open
    raise IOError("%s not found." % path)

OSError: 2009-12-31,6520448000.0
2010-12-31,8505000000.0
2011-12-31,9737000000.0
2012-12-31,10737000000.0
2013-12-31,12920000000.0 not found.

...
netIncome = str(urllib.request.urlopen('https://www.quandl.com/api/v3/datasets/RAYMOND/'+stock.upper()+'_NET_INCOME_A.csv?'+endLink).read())[2:-1]
# convert to string, remove leading "b'" and trailing "'" characters.
# netIncome = 'head\\ndata\\ndata\\n...'
...

splitNI = netIncome.split('\\')[1:-1]
# data segments still have leading 'n' character.
# the [1:-1] is more pythonic and releases memory.
for i in range (len(splitNI)):
    splitNI[i] = splitNI[i][1:]
# data segments are now converted.

print('Net Income:')
for eachNI in splitNI:
    print(eachNI)
    netIncomeAr.append(eachNI)

netIncomeBytes = urllib.request.urlopen('https://www.quandl.com/api/v3/datasets/RAYMOND/'+stock.upper()+'_NET_INCOME_A.csv?'+endLink).read()
netIncome = netIncomeBytes.decode("utf-8")