Last active
November 20, 2016 08:08
-
-
Save sawadyrr5/8deb8d4421e6a6861a2eb069501145f5 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/local/bin python | |
# -*- coding: UTF-8 -*- | |
from pandas_datareader.base import _DailyBaseReader | |
from datetime import datetime | |
import pandas as pd | |
import urllib.request | |
import numpy as np | |
from time import sleep | |
_SLEEP_TIME = 0.5 | |
class _JsfDataReader(_DailyBaseReader): | |
@property | |
def url(self): | |
return 'http://www.taisyaku.jp/search_admin/comp/' | |
def _get_params(self): | |
params = dict( | |
start=self.start, | |
end=self.end | |
) | |
return params | |
def _read_one_data(self, url, params): | |
results = [] | |
for date in self._date_strings(self.start, self.end): | |
params['date'] = date | |
csv = urllib.request.urlopen(url.format(**params)) | |
try: | |
dtypes = {'コード': np.object} | |
table = pd.read_csv(csv, encoding='Shift-JIS', skiprows=4, dtype=dtypes) | |
except ValueError: | |
table = pd.DataFrame() | |
results.append(table) | |
sleep(_SLEEP_TIME) | |
result = pd.concat(results, ignore_index=True) | |
return result | |
@staticmethod | |
def _date_strings(start, end): | |
dates = [datetime.strftime(date, '%Y%m%d') for date in pd.date_range(start, end, freq='D')] | |
return sorted(dates) | |
class JsfShinaDataReader(_JsfDataReader): | |
_url_base = 'pcsl/shina{date}.csv' | |
def read(self): | |
# Use _DailyBaseReader's definition | |
result = self._read_one_data(self.url + self._url_base, params=self._get_params()) | |
if not result.empty: | |
for col in ('貸借申込日', '決済日', '決算等'): | |
result[col] = pd.to_datetime(result[col], format='%Y%m%d') | |
return result | |
class JsfZandakaDataReader(_JsfDataReader): | |
_url_base = 'balance/zandaka{date}.csv' | |
def read(self): | |
# Use _DailyBaseReader's definition | |
result = self._read_one_data(self.url + self._url_base, params=self._get_params()) | |
if not result.empty: | |
result['申込日'] = pd.to_datetime(result['申込日'], format='%Y/%m/%d') | |
return result |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment