def _load(self):
url = '{}?method=download&searchType=13'.format(
self._COMPANY_LIST_URL_)
if self.market_type == 'allMkt':
pass
elif self.market_type == 'etcMkt':
raise ValueError('ETC market is not supported')
else:
url = '{}&marketType={}'.format(url, self.market_type)
resp = request_get(url=url, timeout=120)
soup = BeautifulSoup(resp.text, 'html.parser')
rows = soup.find_all('tr')
for row in rows:
cols = row.find_all('td')
if len(cols) > 0:
crp_nm = cols[0].text.strip()
crp_cd = cols[1].text.strip()
crp_ctp = cols[2].text.strip()
crp_prod = cols[3].text.strip()
crp_info = {
'crp_cd': crp_cd,
'crp_nm': crp_nm,
'crp_ctp': crp_ctp,
'crp_prod': crp_prod
}
self.__crp_list.append(Crp(**crp_info))
def _get_report(self):
""" 보고서 html 불러오기"""
params = dict(rcpNo=self.rcp_no)
if self.dcm_no:
params['dcmNo'] = self.dcm_no
resp = request_get(url=self._REPORT_URL_, params=params)
self.html = BeautifulSoup(resp.text, 'html.parser')
def api_key(self, api_key: str) -> None:
if not isinstance(api_key, str):
raise ValueError(
'The Dart Api key must be provided through the api_key variable'
)
url = 'http://opendart.fss.or.kr/api/list.json'
params = dict()
params['crtfc_key'] = api_key
resp = request_get(url=url, params=params)
data = resp.json()
check_err_code(**data)
self.__api_key = api_key
def load(self):
""" 종목 정보 로딩 """
api_key = DartAuth().api_key
url = self._SEARCH_URL_ + 'company.json'
params = dict(
auth=api_key,
crp_cd=self.crp_cd
)
resp = request_get(url=url, params=params)
data = resp.json()
data['crp_cd'] = data.pop('stock_cd')
check_err_code(**data)
self.crp_nm = data.get('crp_nm')
self._info = {key: value for key, value in data.items()
if key not in ['err_code', 'err_msg', 'crp_cd', 'crp_nm']}
def extract_attached_files(self):
""" 첨부된 파일 리스트 추출 및 반환
Returns
-------
list of AttachedFile
첨부된 파일리스트
"""
if self.html is None:
self._get_report()
results = []
a_href = self.html.find('a', href='#download')
a_onclick = a_href.attrs.get('onclick', '')
raw_data = re.search(r'openPdfDownload\(.*?(\d+).*?(\d+).*?\)',
a_onclick)
if raw_data is None:
return results
rcp_no = raw_data.group(1)
dcm_no = raw_data.group(2)
params = dict(rcp_no=rcp_no, dcm_no=dcm_no)
resp = request_get(url=self._DOWNLOAD_URL_, params=params)
soup = BeautifulSoup(resp.text, 'html.parser')
tr_list = soup.find_all('tr')
attached_files = []
for tr in tr_list:
if tr.find('a'):
td_list = tr.find_all('td')
filename = td_list[0].text.strip()
file_url = td_list[1].a.get('href')
if not file_url:
continue
info = dict()
info['rcp_no'] = self.rcp_no
info['url'] = file_url
info['filename'] = filename
attached_files.append(AttachedFile(**info))
self._attached_files = attached_files
return self._attached_files
def download(self, path):
"""
첨부파일 다운로드 Method
Parameters
----------
path: str
다운롣드 받을 경로
Returns
-------
str
다운받은 첨부파일 경로
"""
from dart_fss.spinner import Spinner
create_folder(path)
url = self.url
r = request_get(url=url, stream=True)
headers = r.headers.get('Content-Disposition')
if not re.search('attachment', headers):
raise Exception('invalid data found')
# total_size = int(r.headers.get('content-length', 0))
block_size = 8192
filename = unquote(re.findall(r'filename="(.*?)"', headers)[0])
filename = '{}_{}'.format(self.rcp_no, filename)
spinner = Spinner('Downloading ' + filename)
spinner.start()
file_path = os.path.join(path, filename)
with open(file_path, 'wb') as f:
for chunk in r.iter_content(chunk_size=block_size):
if chunk is not None:
f.write(chunk)
r.close()
spinner.stop()
return file_path
def load(self):
""" page loading 함수 """
def change_url(bs, tag):
tags = bs.find_all(attrs={tag: re.compile(r'.*')})
if tags:
for t in tags:
t[tag] = "http://dart.fss.or.kr" + t[tag]
return bs
def add_prefix(match_obj):
return r"window.open('http://dart.fss.or.kr" + match_obj.group(
1) + r"'"
params = {
'rcpNo': self.rcp_no,
'dcmNo': self.dcm_no,
'eleId': self.ele_id,
'offset': self._offset,
'length': self._length,
'dtd': self._dtd
}
html = request_get(url=self._BASE_URL_, params=params).content
try:
html = html.decode()
except UnicodeDecodeError:
html = html.decode('cp949')
finally:
soup = BeautifulSoup(html, 'html.parser')
meta = soup.find('meta', {'content': re.compile(r'charset')})
if meta:
meta['content'] = meta['content'].replace('euc-kr', 'utf-8')
soup = change_url(soup, 'href')
soup = change_url(soup, 'src')
html = str(soup)
html = re.sub(r'window.open\(\'(.*?)\'', add_prefix, html)
self._html = html
def search_report(crp_cd: str = None,
start_dt: str = None,
end_dt: str = None,
fin_rpt: bool = False,
dsp_tp: List_or_str = None,
bsn_tp: List_or_str = None,
sort: str = 'date',
series: str = 'desc',
page_no: int = 1,
page_set: int = 10,
return_dict: bool = False) -> SearchResults_or_dict:
""" DART 공시 정보 검색
DART 에 공시된 정보를 검색하는 함수로, Parameters 가 설정되지 않을 경우 당일 접수 10건을 검색함
Parameters
----------
crp_cd: str
종목 코드
start_dt: str
검색 시작일자(YYYYMMDD)
end_dt: str
검색 종료일자(YYYYMMDD)
fin_rpt: bool
최종보고서만 검색여부, 기본값: False
dsp_tp: list of str or str
공시 유형(DSP_TYPES)
bsn_tp: list of str or str
공시 상세 유형(BSN_TYPES)
sort: str
정렬 방법, 접수일자(date), 회사명(crp), 보고서명(rpt), 기본값 : date
series: str
오름차순(asc), 내림차순(desc) 기본값 : desc
page_no: int
페이지 번호, 기본값: 1
page_set: int
페이지당 건수(1-100) 기본값: 10, 최대값: 100
return_dict: bool
dict 타입으로 반환할지 여부, 기본은 SearchResults
Returns
-------
SearchResults or dict of str
검색결과
"""
api_key = DartAuth().api_key
url = 'http://dart.fss.or.kr/api/search.json'
params = dict()
params['auth'] = api_key
params = _set_params(params,
crp_cd=crp_cd,
start_dt=start_dt,
end_dt=end_dt,
fin_rpt=fin_rpt,
dsp_tp=dsp_tp,
bsn_tp=bsn_tp,
sort=sort,
series=series)
if isinstance(page_no, int) and 1 <= page_no:
params['page_no'] = page_no
if isinstance(page_set, int) and (1 <= page_set <= 100):
params['page_set'] = page_set
resp = request_get(url=url, params=params)
data = resp.json()
data['report_list'] = data.pop('list')
params.pop('auth')
if return_dict:
return {'params': params, 'data': data}
return SearchResults(params=params, data=data)