Question

我正在使用Python从Googles adwords API中提取数据。我想将这些数据放入Pandas DataFrame中，以便我可以对数据进行分析。我正在使用Google提供的示例here.

下面是我试图将输出作为pandas数据帧读取的尝试：

from googleads import adwords
import pandas as pd
import numpy as np

# Initialize appropriate service.

adwords_client = adwords.AdWordsClient.LoadFromStorage()

report_downloader = adwords_client.GetReportDownloader(version='v201710')

# Create report query.
report_query = ('''
select Date, Clicks
from ACCOUNT_PERFORMANCE_REPORT
during LAST_7_DAYS''')

df = pd.read_csv(report_downloader.DownloadReportWithAwql(
    report_query, 
    'CSV',
    client_customer_id='xxx-xxx-xxxx', # denotes which adw account to pull from
    skip_report_header=True, 
    skip_column_header=False,
    skip_report_summary=True, 
    include_zero_impressions=True))

输出是看起来像csv格式和错误的数据。

Day,Clicks
2017-11-05,42061
2017-11-07,45792
2017-11-03,36874
2017-11-02,39790
2017-11-06,44934
2017-11-08,45631
2017-11-04,36031
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-5-cc25e32c9f3a> in <module>()
     25     skip_column_header=False,
     26     skip_report_summary=True,
---> 27     include_zero_impressions=True))

/anaconda/lib/python3.6/site-packages/pandas/io/parsers.py in parser_f(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, squeeze, prefix, mangle_dupe_cols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, dayfirst, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, escapechar, comment, encoding, dialect, tupleize_cols, error_bad_lines, warn_bad_lines, skipfooter, skip_footer, doublequote, delim_whitespace, as_recarray, compact_ints, use_unsigned, low_memory, buffer_lines, memory_map, float_precision)
    653                     skip_blank_lines=skip_blank_lines)
    654 
--> 655         return _read(filepath_or_buffer, kwds)
    656 
    657     parser_f.__name__ = name

/anaconda/lib/python3.6/site-packages/pandas/io/parsers.py in _read(filepath_or_buffer, kwds)
    390     compression = _infer_compression(filepath_or_buffer, compression)
    391     filepath_or_buffer, _, compression = get_filepath_or_buffer(
--> 392         filepath_or_buffer, encoding, compression)
    393     kwds['compression'] = compression
    394 

/anaconda/lib/python3.6/site-packages/pandas/io/common.py in get_filepath_or_buffer(filepath_or_buffer, encoding, compression)
    208     if not is_file_like(filepath_or_buffer):
    209         msg = "Invalid file path or buffer object type: {_type}"
--> 210         raise ValueError(msg.format(_type=type(filepath_or_buffer)))
    211 
    212     return filepath_or_buffer, None, compression

ValueError: Invalid file path or buffer object type: <class 'NoneType'>

我知道我缺少一些基本的东西，我不完全了解如何将数据导入pandas数据帧。任何帮助将不胜感激。

Answer 1

所以如果有人好奇或者我遇到同样的问题，我能够找到自己问题的答案。我不得不import io并将adwords查询的输出写入我命名为output的字符串。然后我使用seek()方法从头开始，并使用pandas read_csv读取它。

from googleads import adwords
import pandas as pd
import numpy as np
import io

# Define output as a string
output = io.StringIO()

# Initialize appropriate service.
adwords_client = adwords.AdWordsClient.LoadFromStorage()

report_downloader = adwords_client.GetReportDownloader(version='v201710')

# Create report query.
report_query = ('''
select Date, HourOfDay, Clicks
from ACCOUNT_PERFORMANCE_REPORT
during LAST_7_DAYS''')

# Write query result to output file
report_downloader.DownloadReportWithAwql(
    report_query, 
    'CSV',
    output,
    client_customer_id='xxx-xxx-xxx', # denotes which adw account to pull from
    skip_report_header=True, 
    skip_column_header=False,
    skip_report_summary=True, 
    include_zero_impressions=False)


output.seek(0)

df = pd.read_csv(output)

df.head()

Answer 2

您不需要特别将报告下载为AWQL，您可以将其下载为字符串并将其保存在数据框对象中，以便在需要时进行进一步的操作。

import io 
import sys
from googleads import adwords
import locale
import sys
import _locale
import pandas as pd
import numpy as np

_locale._getdefaultlocale = (lambda *args: ['en_US', 'UTF-8'])

# The chunk size used for the report download.
CHUNK_SIZE = 16 * 1024


def main(client):
  report_downloader = client.GetReportDownloader(version='v201809')
  print("here")
  # Create report definition.
  report = {
      'reportName': 'AD_PERFORMANCE_REPORT',
      'dateRangeType': 'CUSTOM_DATE',
      'reportType': 'AD_PERFORMANCE_REPORT',
      'downloadFormat': 'CSV',
      'selector': {
          'fields': ['AccountDescriptiveName',
                     'Device', 
                     'Date', 
                     'CampaignName',
                     'CampaignId', 
                     'AdGroupName',  
                     'Id', 
                     'DisplayUrl', 
                     'LongHeadline',
                     'HeadlinePart1',
                     'HeadlinePart2',
                     'Description',
                     'Description1',
                     'Description2',
                     'Headline',
                     'Path1',
                     'Path2',
                     "BusinessName",
                     'AdType',
                     'AccountCurrencyCode',
                     'Clicks', 
                     'Impressions', 
                     'Ctr', 
                     'AverageCpc', 
                     'AverageCpm',
                     'Cost'

                     ],
          'dateRange': {'min':'20191207','max':'20191217'}
      }
  }
  #date format: yyyymmdd
  # print(report)
  output = io.StringIO()
  # #report_data = open('ad_performance.csv', mode ='w')
  report_downloader.DownloadReport(
    report, output, skip_report_header=True, skip_column_header=False,
    skip_report_summary=True)
  output.seek(0)

  df = pd.read_csv(output)

  print(df)

if __name__ == '__main__':
  print("hello")
  adwords_client = adwords.AdWordsClient.LoadFromStorage()
  main(adwords_client)

如何从Adwords API中提取数据并放入Pandas Dataframe

2 个答案: