1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
|
"""SEC Company Filings Model."""
# pylint: disable=unused-argument
from datetime import (
date as dateType,
datetime,
)
from typing import Any, Dict, List, Optional, Union
from aiohttp_client_cache import SQLiteBackend
from aiohttp_client_cache.session import CachedSession
from openbb_core.app.utils import get_user_cache_directory
from openbb_core.provider.abstract.fetcher import Fetcher
from openbb_core.provider.standard_models.company_filings import (
CompanyFilingsData,
CompanyFilingsQueryParams,
)
from openbb_core.provider.utils.descriptions import QUERY_DESCRIPTIONS
from openbb_core.provider.utils.errors import EmptyDataError
from openbb_core.provider.utils.helpers import amake_request, amake_requests
from openbb_sec.utils.definitions import FORM_TYPES, HEADERS
from openbb_sec.utils.helpers import symbol_map
from pandas import DataFrame
from pydantic import Field, field_validator
class SecCompanyFilingsQueryParams(CompanyFilingsQueryParams):
"""SEC Company Filings Query.
Source: https://sec.gov/
"""
symbol: Optional[str] = Field(
description=QUERY_DESCRIPTIONS.get("symbol", ""),
default=None,
)
cik: Optional[Union[str, int]] = Field(
description="Lookup filings by Central Index Key (CIK) instead of by symbol.",
default=None,
)
form_type: Union[None, FORM_TYPES] = Field(
description="Type of the SEC filing form.",
default=None,
)
use_cache: bool = Field(
description="Whether or not to use cache. If True, cache will store for one day.",
default=True,
)
class SecCompanyFilingsData(CompanyFilingsData):
"""SEC Company Filings Data."""
__alias_dict__ = {
"filing_date": "filingDate",
"accepted_date": "acceptanceDateTime",
"filing_url": "filingDetailUrl",
"report_url": "primaryDocumentUrl",
"report_type": "form",
}
report_date: Optional[dateType] = Field(
description="The date of the filing.",
default=None,
alias="reportDate",
)
act: Optional[Union[str, int]] = Field(
description="The SEC Act number.", default=None
)
items: Optional[Union[str, float]] = Field(
description="The SEC Item numbers.", default=None
)
primary_doc_description: Optional[str] = Field(
description="The description of the primary document.",
default=None,
alias="primaryDocDescription",
)
primary_doc: Optional[str] = Field(
description="The filename of the primary document.",
default=None,
alias="primaryDocument",
)
accession_number: Optional[Union[str, int]] = Field(
description="The accession number.",
default=None,
alias="accessionNumber",
)
file_number: Optional[Union[str, int]] = Field(
description="The file number.",
default=None,
alias="fileNumber",
)
film_number: Optional[Union[str, int]] = Field(
description="The film number.",
default=None,
alias="filmNumber",
)
is_inline_xbrl: Optional[Union[str, int]] = Field(
description="Whether the filing is an inline XBRL filing.",
default=None,
alias="isInlineXBRL",
)
is_xbrl: Optional[Union[str, int]] = Field(
description="Whether the filing is an XBRL filing.",
default=None,
alias="isXBRL",
)
size: Optional[Union[str, int]] = Field(
description="The size of the filing.", default=None
)
complete_submission_url: Optional[str] = Field(
description="The URL to the complete filing submission.",
default=None,
alias="completeSubmissionUrl",
)
filing_detail_url: Optional[str] = Field(
description="The URL to the filing details.",
default=None,
alias="filingDetailUrl",
)
@field_validator("report_date", mode="before", check_fields=False)
@classmethod
def validate_report_date(cls, v: Optional[Union[str, dateType]]):
"""Validate report_date."""
if isinstance(v, dateType):
return v
v = v if v != "" else None
return (
datetime.strptime(v, "%Y-%m-%d").date()
if v and isinstance(v, str)
else None
)
class SecCompanyFilingsFetcher(
Fetcher[SecCompanyFilingsQueryParams, List[SecCompanyFilingsData]]
):
"""Transform the query, extract and transform the data from the SEC endpoints."""
@staticmethod
def transform_query(params: Dict[str, Any]) -> SecCompanyFilingsQueryParams:
"""Transform query params."""
return SecCompanyFilingsQueryParams(**params)
@staticmethod
async def aextract_data(
query: SecCompanyFilingsQueryParams,
credentials: Optional[Dict[str, str]],
**kwargs: Any,
) -> List[Dict]:
"""Extract the data from the SEC endpoint."""
filings = DataFrame()
if query.symbol and not query.cik:
query.cik = await symbol_map(
query.symbol.lower(), use_cache=query.use_cache
)
if not query.cik:
raise ValueError(f"CIK not found for symbol {query.symbol}")
if query.cik is None:
raise ValueError("Error: CIK or symbol must be provided.")
# The leading 0s need to be inserted but are typically removed from the data to store as an integer.
if len(query.cik) != 10: # type: ignore
cik_: str = ""
temp = 10 - len(query.cik) # type: ignore
for i in range(temp):
cik_ = cik_ + "0"
query.cik = cik_ + str(query.cik) # type: ignore
url = f"https://data.sec.gov/submissions/CIK{query.cik}.json"
data: Union[dict, List[dict]] = []
if query.use_cache is True:
cache_dir = f"{get_user_cache_directory()}/http/sec_company_filings"
async with CachedSession(
cache=SQLiteBackend(cache_dir, expire_after=3600 * 24)
) as session:
try:
data = await amake_request(url, headers=HEADERS, session=session) # type: ignore
finally:
await session.close()
else:
data = await amake_request(url, headers=HEADERS) # type: ignore
# This seems to work for the data structure.
filings = (
DataFrame.from_records(data["filings"].get("recent")) # type: ignore
if "filings" in data
else DataFrame()
)
results = filings.to_dict("records")
# If there are lots of filings, there will be custom pagination.
if (
(query.limit and len(filings) >= 1000)
or query.form_type is not None
or query.limit == 0
):
async def callback(response, session):
"""Response callback for excess company filings."""
result = await response.json()
if result:
new_data = DataFrame.from_records(result)
results.extend(new_data.to_dict("records"))
urls: List = []
new_urls = (
DataFrame(data["filings"].get("files")) # type: ignore
if "filings" in data
else DataFrame()
)
for i in new_urls.index:
new_cik: str = data["filings"]["files"][i]["name"] # type: ignore
new_url: str = "https://data.sec.gov/submissions/" + new_cik
urls.append(new_url)
if query.use_cache is True:
cache_dir = f"{get_user_cache_directory()}/http/sec_company_filings"
async with CachedSession(
cache=SQLiteBackend(cache_dir, expire_after=3600 * 24)
) as session:
try:
await amake_requests(urls, headers=HEADERS, session=session, response_callback=callback) # type: ignore
finally:
await session.close()
else:
await amake_requests(urls, headers=HEADERS, response_callback=callback) # type: ignore
return results
@staticmethod</
|
