datasinking 0.1.0__tar.gz → 0.2.0__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {datasinking-0.1.0 → datasinking-0.2.0}/PKG-INFO +31 -29
- {datasinking-0.1.0 → datasinking-0.2.0}/README.md +25 -25
- {datasinking-0.1.0 → datasinking-0.2.0}/datasinking/client.py +33 -27
- datasinking-0.2.0/datasinking/mcp_server.py +119 -0
- {datasinking-0.1.0 → datasinking-0.2.0}/datasinking.egg-info/PKG-INFO +31 -29
- {datasinking-0.1.0 → datasinking-0.2.0}/datasinking.egg-info/SOURCES.txt +2 -0
- datasinking-0.2.0/datasinking.egg-info/entry_points.txt +2 -0
- datasinking-0.2.0/datasinking.egg-info/requires.txt +4 -0
- {datasinking-0.1.0 → datasinking-0.2.0}/pyproject.toml +10 -4
- datasinking-0.1.0/datasinking.egg-info/requires.txt +0 -1
- {datasinking-0.1.0 → datasinking-0.2.0}/LICENSE +0 -0
- {datasinking-0.1.0 → datasinking-0.2.0}/datasinking/__init__.py +0 -0
- {datasinking-0.1.0 → datasinking-0.2.0}/datasinking.egg-info/dependency_links.txt +0 -0
- {datasinking-0.1.0 → datasinking-0.2.0}/datasinking.egg-info/top_level.txt +0 -0
- {datasinking-0.1.0 → datasinking-0.2.0}/setup.cfg +0 -0
|
@@ -1,13 +1,13 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: datasinking
|
|
3
|
-
Version: 0.
|
|
4
|
-
Summary: Python client for DataSinking — full-text
|
|
3
|
+
Version: 0.2.0
|
|
4
|
+
Summary: Python client for DataSinking — full-text Asian financial reports (China, Korea, Japan) as Markdown.
|
|
5
5
|
Author: DataSinking
|
|
6
6
|
License: MIT
|
|
7
7
|
Project-URL: Homepage, https://datasink.ing
|
|
8
8
|
Project-URL: Documentation, https://datasink.ing/docs
|
|
9
9
|
Project-URL: Repository, https://github.com/heubme2020/datasinking
|
|
10
|
-
Keywords: a-share,china,financial reports,markdown,api,
|
|
10
|
+
Keywords: a-share,china,korea,japan,financial reports,markdown,api,mcp,model-context-protocol,rag,llm
|
|
11
11
|
Classifier: Programming Language :: Python :: 3
|
|
12
12
|
Classifier: License :: OSI Approved :: MIT License
|
|
13
13
|
Classifier: Operating System :: OS Independent
|
|
@@ -15,20 +15,23 @@ Classifier: Topic :: Office/Business :: Financial
|
|
|
15
15
|
Requires-Python: >=3.8
|
|
16
16
|
Description-Content-Type: text/markdown
|
|
17
17
|
License-File: LICENSE
|
|
18
|
-
|
|
18
|
+
Provides-Extra: mcp
|
|
19
|
+
Requires-Dist: mcp>=1.0.0; extra == "mcp"
|
|
20
|
+
Requires-Dist: requests>=2.28; extra == "mcp"
|
|
19
21
|
Dynamic: license-file
|
|
20
22
|
|
|
21
23
|
# DataSinking
|
|
22
24
|
|
|
23
|
-
|
|
25
|
+
[](https://pypi.org/project/datasinking/)
|
|
24
26
|
|
|
25
|
-
|
|
26
|
-
|
|
27
|
-
|
|
28
|
-
|
|
29
|
-
|
|
30
|
-
|
|
31
|
-
|
|
27
|
+
**Full-text financial reports across Asia, as clean Markdown.**
|
|
28
|
+
|
|
29
|
+
[DataSinking](https://datasink.ing) serves **full-text financial reports** — annual, semi-annual
|
|
30
|
+
and quarterly — from **China, Korea and Japan** as clean **Markdown**, ready for LLM reading
|
|
31
|
+
and RAG. Query by FMP-style symbol (`600519.SS`, `005930.KS`, `7203.T`) or filter by exchange,
|
|
32
|
+
report period, or **section** — pull just the MD&A / risk section instead of the whole report.
|
|
33
|
+
Reports are sourced from official disclosure platforms and parsed into structured Markdown with
|
|
34
|
+
YAML frontmatter, preserved headings, paragraphs and tables.
|
|
32
35
|
|
|
33
36
|
---
|
|
34
37
|
|
|
@@ -40,25 +43,23 @@ Examples, research and tutorials showing how to work with financial report data,
|
|
|
40
43
|
datasinking/
|
|
41
44
|
├── examples/ # Example scripts: pull data from the API and analyze it
|
|
42
45
|
├── research/ # Research notes / blog posts (reproducing paper-style presentation)
|
|
43
|
-
├── datasinking/ # Python client — pip install datasinking
|
|
44
|
-
├──
|
|
46
|
+
├── datasinking/ # Python client + MCP server — pip install "datasinking[mcp]"
|
|
47
|
+
├── mcp-server.md # How to configure the MCP server (for AI agents: Claude / Cursor / Codex / DeepSeek)
|
|
48
|
+
├── llm-examples.md # Ask an LLM — no code needed (8 end-to-end examples)
|
|
49
|
+
├── api-examples.md # 7 examples × 3 interfaces (curl / Python / LLM)
|
|
45
50
|
└── README.md
|
|
46
51
|
```
|
|
47
52
|
|
|
48
53
|
## Quick start
|
|
49
54
|
|
|
50
55
|
1. Get an API key at [datasink.ing](https://datasink.ing)
|
|
51
|
-
2.
|
|
56
|
+
2. One line (FMP-style `?apikey=`):
|
|
52
57
|
|
|
53
58
|
```bash
|
|
54
|
-
|
|
55
|
-
curl "https://api.datasink.ing/exchanges?apikey=YOUR_KEY"
|
|
56
|
-
|
|
57
|
-
# List all of Kweichow Moutai's reports
|
|
58
|
-
curl "https://api.datasink.ing/documents?symbol=600519.SS&apikey=YOUR_KEY"
|
|
59
|
+
curl "https://api.datasink.ing/documents?symbol=600519.SS&with_content=1&apikey=YOUR_KEY"
|
|
59
60
|
```
|
|
60
61
|
|
|
61
|
-
|
|
62
|
+
Or in Python:
|
|
62
63
|
|
|
63
64
|
```bash
|
|
64
65
|
pip install datasinking
|
|
@@ -68,17 +69,17 @@ pip install datasinking
|
|
|
68
69
|
from datasinking import DataSinking
|
|
69
70
|
|
|
70
71
|
ds = DataSinking("YOUR_KEY")
|
|
71
|
-
|
|
72
|
-
# Latest 3 reports of Kweichow Moutai (full markdown content included)
|
|
73
72
|
for r in ds.get_stock_reports("600519.SS", limit=3):
|
|
74
73
|
print(r["report_period"], r["title"], len(r["content"]), "chars")
|
|
75
74
|
```
|
|
76
75
|
|
|
76
|
+
All five functions (curl / Python / LLM): [`api-examples.md`](api-examples.md).
|
|
77
|
+
|
|
77
78
|
## Ask an LLM (no code)
|
|
78
79
|
|
|
79
80
|
Don't want to write code? Point any LLM at [datasink.ing](https://datasink.ing),
|
|
80
81
|
give it your API key, and ask in plain language. See
|
|
81
|
-
[`llm-examples.md`](llm-examples.md) for
|
|
82
|
+
[`llm-examples.md`](llm-examples.md) for eight end-to-end examples — explore
|
|
82
83
|
coverage, list a company's reports, and extract a figure with correct units.
|
|
83
84
|
|
|
84
85
|
## Examples (`examples/`)
|
|
@@ -91,7 +92,7 @@ coverage, list a company's reports, and extract a figure with correct units.
|
|
|
91
92
|
|
|
92
93
|
Every example pulls from the live API and runs as-is.
|
|
93
94
|
|
|
94
|
-
> `03_download_exchange.py` fetches every report on an exchange (e.g. all of Shenzhen —
|
|
95
|
+
> `03_download_exchange.py` fetches every report on an exchange (e.g. all of Shenzhen — 150k+ documents). Free keys work too, but fall back to slow per-document fetching (1 req/s + shared daily quota); a **paid (yearly)** key is strongly recommended for full-exchange downloads.
|
|
95
96
|
|
|
96
97
|
## Research (`research/`)
|
|
97
98
|
|
|
@@ -107,16 +108,17 @@ Start from [`research/TEMPLATE.md`](research/TEMPLATE.md).
|
|
|
107
108
|
|
|
108
109
|
| | |
|
|
109
110
|
|---|---|
|
|
110
|
-
| Coverage | SSE / SZSE / BSE
|
|
111
|
+
| Coverage | China (SSE / SZSE / BSE) · Korea (KOSPI / KOSDAQ / KONEX) · Japan (TSE) |
|
|
111
112
|
| Document types | annual / semiannual / q1 / q3 / amendment |
|
|
113
|
+
| Update frequency | Daily — Korea/Japan via official DART/EDINET APIs (new filings within ~24h of publication) |
|
|
112
114
|
| Format | Full-text Markdown (with YAML frontmatter) |
|
|
113
|
-
| API | REST — `GET /documents`, batch download, `with_content=1` for full text |
|
|
114
|
-
| Symbols | FMP style: `600519.SS` / `
|
|
115
|
+
| API | REST — `GET /documents`, batch download, `with_content=1` for full text, `?section=` + `/sections` for chapter-level access |
|
|
116
|
+
| Symbols | FMP style: `600519.SS` / `005930.KS` / `7203.T` |
|
|
115
117
|
| Auth | `?apikey=` query parameter (FMP style) |
|
|
116
118
|
|
|
117
119
|
## Data source
|
|
118
120
|
|
|
119
|
-
|
|
121
|
+
Reports are sourced from official regulatory disclosure platforms in each market and converted in-house to clean Markdown.
|
|
120
122
|
|
|
121
123
|
## License
|
|
122
124
|
|
|
@@ -1,14 +1,15 @@
|
|
|
1
1
|
# DataSinking
|
|
2
2
|
|
|
3
|
-
|
|
3
|
+
[](https://pypi.org/project/datasinking/)
|
|
4
4
|
|
|
5
|
-
|
|
6
|
-
|
|
7
|
-
|
|
8
|
-
|
|
9
|
-
|
|
10
|
-
|
|
11
|
-
|
|
5
|
+
**Full-text financial reports across Asia, as clean Markdown.**
|
|
6
|
+
|
|
7
|
+
[DataSinking](https://datasink.ing) serves **full-text financial reports** — annual, semi-annual
|
|
8
|
+
and quarterly — from **China, Korea and Japan** as clean **Markdown**, ready for LLM reading
|
|
9
|
+
and RAG. Query by FMP-style symbol (`600519.SS`, `005930.KS`, `7203.T`) or filter by exchange,
|
|
10
|
+
report period, or **section** — pull just the MD&A / risk section instead of the whole report.
|
|
11
|
+
Reports are sourced from official disclosure platforms and parsed into structured Markdown with
|
|
12
|
+
YAML frontmatter, preserved headings, paragraphs and tables.
|
|
12
13
|
|
|
13
14
|
---
|
|
14
15
|
|
|
@@ -20,25 +21,23 @@ Examples, research and tutorials showing how to work with financial report data,
|
|
|
20
21
|
datasinking/
|
|
21
22
|
├── examples/ # Example scripts: pull data from the API and analyze it
|
|
22
23
|
├── research/ # Research notes / blog posts (reproducing paper-style presentation)
|
|
23
|
-
├── datasinking/ # Python client — pip install datasinking
|
|
24
|
-
├──
|
|
24
|
+
├── datasinking/ # Python client + MCP server — pip install "datasinking[mcp]"
|
|
25
|
+
├── mcp-server.md # How to configure the MCP server (for AI agents: Claude / Cursor / Codex / DeepSeek)
|
|
26
|
+
├── llm-examples.md # Ask an LLM — no code needed (8 end-to-end examples)
|
|
27
|
+
├── api-examples.md # 7 examples × 3 interfaces (curl / Python / LLM)
|
|
25
28
|
└── README.md
|
|
26
29
|
```
|
|
27
30
|
|
|
28
31
|
## Quick start
|
|
29
32
|
|
|
30
33
|
1. Get an API key at [datasink.ing](https://datasink.ing)
|
|
31
|
-
2.
|
|
34
|
+
2. One line (FMP-style `?apikey=`):
|
|
32
35
|
|
|
33
36
|
```bash
|
|
34
|
-
|
|
35
|
-
curl "https://api.datasink.ing/exchanges?apikey=YOUR_KEY"
|
|
36
|
-
|
|
37
|
-
# List all of Kweichow Moutai's reports
|
|
38
|
-
curl "https://api.datasink.ing/documents?symbol=600519.SS&apikey=YOUR_KEY"
|
|
37
|
+
curl "https://api.datasink.ing/documents?symbol=600519.SS&with_content=1&apikey=YOUR_KEY"
|
|
39
38
|
```
|
|
40
39
|
|
|
41
|
-
|
|
40
|
+
Or in Python:
|
|
42
41
|
|
|
43
42
|
```bash
|
|
44
43
|
pip install datasinking
|
|
@@ -48,17 +47,17 @@ pip install datasinking
|
|
|
48
47
|
from datasinking import DataSinking
|
|
49
48
|
|
|
50
49
|
ds = DataSinking("YOUR_KEY")
|
|
51
|
-
|
|
52
|
-
# Latest 3 reports of Kweichow Moutai (full markdown content included)
|
|
53
50
|
for r in ds.get_stock_reports("600519.SS", limit=3):
|
|
54
51
|
print(r["report_period"], r["title"], len(r["content"]), "chars")
|
|
55
52
|
```
|
|
56
53
|
|
|
54
|
+
All five functions (curl / Python / LLM): [`api-examples.md`](api-examples.md).
|
|
55
|
+
|
|
57
56
|
## Ask an LLM (no code)
|
|
58
57
|
|
|
59
58
|
Don't want to write code? Point any LLM at [datasink.ing](https://datasink.ing),
|
|
60
59
|
give it your API key, and ask in plain language. See
|
|
61
|
-
[`llm-examples.md`](llm-examples.md) for
|
|
60
|
+
[`llm-examples.md`](llm-examples.md) for eight end-to-end examples — explore
|
|
62
61
|
coverage, list a company's reports, and extract a figure with correct units.
|
|
63
62
|
|
|
64
63
|
## Examples (`examples/`)
|
|
@@ -71,7 +70,7 @@ coverage, list a company's reports, and extract a figure with correct units.
|
|
|
71
70
|
|
|
72
71
|
Every example pulls from the live API and runs as-is.
|
|
73
72
|
|
|
74
|
-
> `03_download_exchange.py` fetches every report on an exchange (e.g. all of Shenzhen —
|
|
73
|
+
> `03_download_exchange.py` fetches every report on an exchange (e.g. all of Shenzhen — 150k+ documents). Free keys work too, but fall back to slow per-document fetching (1 req/s + shared daily quota); a **paid (yearly)** key is strongly recommended for full-exchange downloads.
|
|
75
74
|
|
|
76
75
|
## Research (`research/`)
|
|
77
76
|
|
|
@@ -87,16 +86,17 @@ Start from [`research/TEMPLATE.md`](research/TEMPLATE.md).
|
|
|
87
86
|
|
|
88
87
|
| | |
|
|
89
88
|
|---|---|
|
|
90
|
-
| Coverage | SSE / SZSE / BSE
|
|
89
|
+
| Coverage | China (SSE / SZSE / BSE) · Korea (KOSPI / KOSDAQ / KONEX) · Japan (TSE) |
|
|
91
90
|
| Document types | annual / semiannual / q1 / q3 / amendment |
|
|
91
|
+
| Update frequency | Daily — Korea/Japan via official DART/EDINET APIs (new filings within ~24h of publication) |
|
|
92
92
|
| Format | Full-text Markdown (with YAML frontmatter) |
|
|
93
|
-
| API | REST — `GET /documents`, batch download, `with_content=1` for full text |
|
|
94
|
-
| Symbols | FMP style: `600519.SS` / `
|
|
93
|
+
| API | REST — `GET /documents`, batch download, `with_content=1` for full text, `?section=` + `/sections` for chapter-level access |
|
|
94
|
+
| Symbols | FMP style: `600519.SS` / `005930.KS` / `7203.T` |
|
|
95
95
|
| Auth | `?apikey=` query parameter (FMP style) |
|
|
96
96
|
|
|
97
97
|
## Data source
|
|
98
98
|
|
|
99
|
-
|
|
99
|
+
Reports are sourced from official regulatory disclosure platforms in each market and converted in-house to clean Markdown.
|
|
100
100
|
|
|
101
101
|
## License
|
|
102
102
|
|
|
@@ -8,46 +8,52 @@
|
|
|
8
8
|
get_stock_reports(symbol, ..., limit=7) 拉某股票的报告(全文)
|
|
9
9
|
|
|
10
10
|
返回类型约定: list_* 一律返回 list, get_report 返回单个 dict, get_stock_reports 返回 list。
|
|
11
|
+
|
|
12
|
+
零第三方依赖, 只用标准库 urllib。
|
|
11
13
|
"""
|
|
14
|
+
import json
|
|
12
15
|
import time
|
|
13
|
-
|
|
14
|
-
import
|
|
16
|
+
import urllib.request
|
|
17
|
+
import urllib.error
|
|
18
|
+
import urllib.parse
|
|
15
19
|
|
|
16
20
|
|
|
17
21
|
class DataSinking:
|
|
18
22
|
def __init__(self, api_key, base_url="https://api.datasink.ing"):
|
|
19
23
|
self.base_url = base_url.rstrip("/")
|
|
20
24
|
self.api_key = api_key
|
|
21
|
-
self.session = requests.Session()
|
|
22
25
|
|
|
23
|
-
# ----
|
|
24
|
-
def
|
|
25
|
-
|
|
26
|
+
# ---- 内部: HTTP ----
|
|
27
|
+
def _request(self, method, path, params=None, body=None, retries=5):
|
|
28
|
+
p = dict(params or {})
|
|
29
|
+
p["apikey"] = self.api_key
|
|
30
|
+
url = f"{self.base_url}{path}?{urllib.parse.urlencode(p)}"
|
|
31
|
+
data = None
|
|
32
|
+
headers = {"User-Agent": "Mozilla/5.0 (compatible; DataSinking/0.1.0)"}
|
|
33
|
+
if body is not None:
|
|
34
|
+
data = json.dumps(body).encode("utf-8")
|
|
35
|
+
headers["Content-Type"] = "application/json"
|
|
36
|
+
req = urllib.request.Request(url, data=data, headers=headers, method=method)
|
|
37
|
+
last = None
|
|
26
38
|
for i in range(retries):
|
|
27
39
|
try:
|
|
28
|
-
|
|
29
|
-
|
|
40
|
+
with urllib.request.urlopen(req, timeout=60) as resp:
|
|
41
|
+
return json.loads(resp.read().decode("utf-8"))
|
|
42
|
+
except urllib.error.HTTPError as e:
|
|
43
|
+
if e.code == 429: # 限流, 稍等重试
|
|
30
44
|
time.sleep(2)
|
|
31
45
|
continue
|
|
32
|
-
|
|
33
|
-
|
|
34
|
-
except (requests.exceptions.SSLError, requests.exceptions.ConnectionError):
|
|
46
|
+
raise # 其他 HTTP 错误(401/403/404...)直接抛给上层
|
|
47
|
+
except (urllib.error.URLError, TimeoutError, OSError) as e:
|
|
35
48
|
time.sleep(1 + i)
|
|
36
|
-
|
|
49
|
+
last = e
|
|
50
|
+
raise RuntimeError(f"Request failed after retries: {last}")
|
|
37
51
|
|
|
38
|
-
def
|
|
39
|
-
|
|
40
|
-
|
|
41
|
-
|
|
42
|
-
|
|
43
|
-
if r.status_code == 429:
|
|
44
|
-
time.sleep(2)
|
|
45
|
-
continue
|
|
46
|
-
r.raise_for_status()
|
|
47
|
-
return r.json()
|
|
48
|
-
except (requests.exceptions.SSLError, requests.exceptions.ConnectionError):
|
|
49
|
-
time.sleep(1 + i)
|
|
50
|
-
raise RuntimeError("Request failed after multiple retries")
|
|
52
|
+
def _get(self, path, params=None):
|
|
53
|
+
return self._request("GET", path, params)
|
|
54
|
+
|
|
55
|
+
def _post(self, path, body=None):
|
|
56
|
+
return self._request("POST", path, body=body)
|
|
51
57
|
|
|
52
58
|
def _fetch_all_meta(self, params):
|
|
53
59
|
"""分页拉全 metadata(无 content), 200/页"""
|
|
@@ -72,8 +78,8 @@ class DataSinking:
|
|
|
72
78
|
b = self._post("/documents/batch", {"doc_ids": chunk})
|
|
73
79
|
items.extend(b["items"])
|
|
74
80
|
continue
|
|
75
|
-
except
|
|
76
|
-
if e.
|
|
81
|
+
except urllib.error.HTTPError as e:
|
|
82
|
+
if e.code == 403:
|
|
77
83
|
batch_ok = False
|
|
78
84
|
else:
|
|
79
85
|
raise
|
|
@@ -0,0 +1,119 @@
|
|
|
1
|
+
# -*- coding: utf-8 -*-
|
|
2
|
+
"""DataSinking MCP server (Model Context Protocol).
|
|
3
|
+
|
|
4
|
+
Expose the DataSinking API — full-text financial reports across Asia
|
|
5
|
+
(China, Korea, Japan) as clean Markdown — to AI agents (Claude, Cursor,
|
|
6
|
+
Codex, DeepSeek, Windsurf, …).
|
|
7
|
+
|
|
8
|
+
Install the MCP extra::
|
|
9
|
+
|
|
10
|
+
pip install "datasinking[mcp]"
|
|
11
|
+
|
|
12
|
+
Then run::
|
|
13
|
+
|
|
14
|
+
datasinking-mcp
|
|
15
|
+
|
|
16
|
+
or add to any MCP client with ``command: datasinking-mcp`` (stdio). Requires
|
|
17
|
+
the environment variable ``DATASINK_API_KEY`` (get a free key at
|
|
18
|
+
https://datasink.ing).
|
|
19
|
+
"""
|
|
20
|
+
|
|
21
|
+
import os
|
|
22
|
+
from typing import Optional
|
|
23
|
+
|
|
24
|
+
import requests
|
|
25
|
+
|
|
26
|
+
# mcp v1 uses FastMCP; v2 renamed it to MCPServer. Support both.
|
|
27
|
+
try:
|
|
28
|
+
from mcp.server.fastmcp import FastMCP # mcp v1
|
|
29
|
+
except ImportError: # pragma: no cover
|
|
30
|
+
from mcp.server.mcpserver import MCPServer as FastMCP # mcp v2
|
|
31
|
+
|
|
32
|
+
BASE_URL = "https://api.datasink.ing"
|
|
33
|
+
API_KEY = os.environ.get("DATASINK_API_KEY", "")
|
|
34
|
+
|
|
35
|
+
mcp = FastMCP(
|
|
36
|
+
"DataSinking",
|
|
37
|
+
instructions=(
|
|
38
|
+
"DataSinking 提供亚洲(中国/韩国/日本)上市公司财报的全文 Markdown。"
|
|
39
|
+
"symbol 用 FMP 风格:600519.SS(茅台)、005930.KS(三星)、7203.T(丰田)。"
|
|
40
|
+
"要省 token 时用 get_section 只取某一章(如 MD&A),而不是 get_report 拿整篇。"
|
|
41
|
+
),
|
|
42
|
+
)
|
|
43
|
+
|
|
44
|
+
|
|
45
|
+
def _get(path: str, params: Optional[dict] = None) -> dict:
|
|
46
|
+
"""Call the DataSinking API, carrying the API key automatically."""
|
|
47
|
+
if not API_KEY:
|
|
48
|
+
raise RuntimeError("缺少 DATASINK_API_KEY 环境变量(去 datasink.ing 免费拿一个)")
|
|
49
|
+
p = dict(params or {})
|
|
50
|
+
p["apikey"] = API_KEY
|
|
51
|
+
r = requests.get(f"{BASE_URL}{path}", params=p, timeout=90)
|
|
52
|
+
r.raise_for_status()
|
|
53
|
+
return r.json()
|
|
54
|
+
|
|
55
|
+
|
|
56
|
+
@mcp.tool()
|
|
57
|
+
def list_exchanges() -> list:
|
|
58
|
+
"""列出 DataSinking 覆盖的交易所代码(sse/szse/bj/ksc/koe/knx/jpx)。"""
|
|
59
|
+
return _get("/exchanges").get("exchanges", [])
|
|
60
|
+
|
|
61
|
+
|
|
62
|
+
@mcp.tool()
|
|
63
|
+
def list_stocks(exchange: str, limit: int = 20) -> dict:
|
|
64
|
+
"""列出某交易所的股票(含每家公司的报告数)。
|
|
65
|
+
|
|
66
|
+
Args:
|
|
67
|
+
exchange: 交易所代码,如 sse / szse / ksc / koe / jpx
|
|
68
|
+
limit: 返回前 N 家(默认 20,防止列表过长)
|
|
69
|
+
"""
|
|
70
|
+
data = _get("/stocks", {"exchange": exchange})
|
|
71
|
+
return {"exchange": exchange, "total": data.get("total", 0), "items": data.get("items", [])[:limit]}
|
|
72
|
+
|
|
73
|
+
|
|
74
|
+
@mcp.tool()
|
|
75
|
+
def list_reports(symbol: str, doc_type: str = "annual", size: int = 10) -> dict:
|
|
76
|
+
"""列出某公司的报告(元数据,不含正文)。
|
|
77
|
+
|
|
78
|
+
Args:
|
|
79
|
+
symbol: FMP 风格代码,如 600519.SS / 005930.KS / 7203.T
|
|
80
|
+
doc_type: annual / semiannual / q1 / q3
|
|
81
|
+
size: 返回条数(默认 10)
|
|
82
|
+
"""
|
|
83
|
+
return _get("/documents", {"symbol": symbol, "doc_type": doc_type, "size": size})
|
|
84
|
+
|
|
85
|
+
|
|
86
|
+
@mcp.tool()
|
|
87
|
+
def get_report(document_id: int) -> dict:
|
|
88
|
+
"""获取单篇报告的全文(元数据 + Markdown 正文)。
|
|
89
|
+
|
|
90
|
+
Args:
|
|
91
|
+
document_id: 报告 ID,从 list_reports 的 items[].id 拿
|
|
92
|
+
"""
|
|
93
|
+
return _get(f"/documents/{document_id}")
|
|
94
|
+
|
|
95
|
+
|
|
96
|
+
@mcp.tool()
|
|
97
|
+
def list_sections(document_id: int) -> dict:
|
|
98
|
+
"""列出某报告的所有章节标题(供 get_section 用)。"""
|
|
99
|
+
return _get(f"/documents/{document_id}/sections")
|
|
100
|
+
|
|
101
|
+
|
|
102
|
+
@mcp.tool()
|
|
103
|
+
def get_section(document_id: int, section: str) -> dict:
|
|
104
|
+
"""只取报告的某一章(省 token,适合 RAG)。
|
|
105
|
+
|
|
106
|
+
Args:
|
|
107
|
+
document_id: 报告 ID
|
|
108
|
+
section: 章节标题的关键词,如 "管理层讨论与分析" / "MD&A" / "财务报告"
|
|
109
|
+
"""
|
|
110
|
+
return _get(f"/documents/{document_id}", {"section": section})
|
|
111
|
+
|
|
112
|
+
|
|
113
|
+
def main() -> None:
|
|
114
|
+
"""Entry point for the ``datasinking-mcp`` console script."""
|
|
115
|
+
mcp.run()
|
|
116
|
+
|
|
117
|
+
|
|
118
|
+
if __name__ == "__main__":
|
|
119
|
+
main()
|
|
@@ -1,13 +1,13 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: datasinking
|
|
3
|
-
Version: 0.
|
|
4
|
-
Summary: Python client for DataSinking — full-text
|
|
3
|
+
Version: 0.2.0
|
|
4
|
+
Summary: Python client for DataSinking — full-text Asian financial reports (China, Korea, Japan) as Markdown.
|
|
5
5
|
Author: DataSinking
|
|
6
6
|
License: MIT
|
|
7
7
|
Project-URL: Homepage, https://datasink.ing
|
|
8
8
|
Project-URL: Documentation, https://datasink.ing/docs
|
|
9
9
|
Project-URL: Repository, https://github.com/heubme2020/datasinking
|
|
10
|
-
Keywords: a-share,china,financial reports,markdown,api,
|
|
10
|
+
Keywords: a-share,china,korea,japan,financial reports,markdown,api,mcp,model-context-protocol,rag,llm
|
|
11
11
|
Classifier: Programming Language :: Python :: 3
|
|
12
12
|
Classifier: License :: OSI Approved :: MIT License
|
|
13
13
|
Classifier: Operating System :: OS Independent
|
|
@@ -15,20 +15,23 @@ Classifier: Topic :: Office/Business :: Financial
|
|
|
15
15
|
Requires-Python: >=3.8
|
|
16
16
|
Description-Content-Type: text/markdown
|
|
17
17
|
License-File: LICENSE
|
|
18
|
-
|
|
18
|
+
Provides-Extra: mcp
|
|
19
|
+
Requires-Dist: mcp>=1.0.0; extra == "mcp"
|
|
20
|
+
Requires-Dist: requests>=2.28; extra == "mcp"
|
|
19
21
|
Dynamic: license-file
|
|
20
22
|
|
|
21
23
|
# DataSinking
|
|
22
24
|
|
|
23
|
-
|
|
25
|
+
[](https://pypi.org/project/datasinking/)
|
|
24
26
|
|
|
25
|
-
|
|
26
|
-
|
|
27
|
-
|
|
28
|
-
|
|
29
|
-
|
|
30
|
-
|
|
31
|
-
|
|
27
|
+
**Full-text financial reports across Asia, as clean Markdown.**
|
|
28
|
+
|
|
29
|
+
[DataSinking](https://datasink.ing) serves **full-text financial reports** — annual, semi-annual
|
|
30
|
+
and quarterly — from **China, Korea and Japan** as clean **Markdown**, ready for LLM reading
|
|
31
|
+
and RAG. Query by FMP-style symbol (`600519.SS`, `005930.KS`, `7203.T`) or filter by exchange,
|
|
32
|
+
report period, or **section** — pull just the MD&A / risk section instead of the whole report.
|
|
33
|
+
Reports are sourced from official disclosure platforms and parsed into structured Markdown with
|
|
34
|
+
YAML frontmatter, preserved headings, paragraphs and tables.
|
|
32
35
|
|
|
33
36
|
---
|
|
34
37
|
|
|
@@ -40,25 +43,23 @@ Examples, research and tutorials showing how to work with financial report data,
|
|
|
40
43
|
datasinking/
|
|
41
44
|
├── examples/ # Example scripts: pull data from the API and analyze it
|
|
42
45
|
├── research/ # Research notes / blog posts (reproducing paper-style presentation)
|
|
43
|
-
├── datasinking/ # Python client — pip install datasinking
|
|
44
|
-
├──
|
|
46
|
+
├── datasinking/ # Python client + MCP server — pip install "datasinking[mcp]"
|
|
47
|
+
├── mcp-server.md # How to configure the MCP server (for AI agents: Claude / Cursor / Codex / DeepSeek)
|
|
48
|
+
├── llm-examples.md # Ask an LLM — no code needed (8 end-to-end examples)
|
|
49
|
+
├── api-examples.md # 7 examples × 3 interfaces (curl / Python / LLM)
|
|
45
50
|
└── README.md
|
|
46
51
|
```
|
|
47
52
|
|
|
48
53
|
## Quick start
|
|
49
54
|
|
|
50
55
|
1. Get an API key at [datasink.ing](https://datasink.ing)
|
|
51
|
-
2.
|
|
56
|
+
2. One line (FMP-style `?apikey=`):
|
|
52
57
|
|
|
53
58
|
```bash
|
|
54
|
-
|
|
55
|
-
curl "https://api.datasink.ing/exchanges?apikey=YOUR_KEY"
|
|
56
|
-
|
|
57
|
-
# List all of Kweichow Moutai's reports
|
|
58
|
-
curl "https://api.datasink.ing/documents?symbol=600519.SS&apikey=YOUR_KEY"
|
|
59
|
+
curl "https://api.datasink.ing/documents?symbol=600519.SS&with_content=1&apikey=YOUR_KEY"
|
|
59
60
|
```
|
|
60
61
|
|
|
61
|
-
|
|
62
|
+
Or in Python:
|
|
62
63
|
|
|
63
64
|
```bash
|
|
64
65
|
pip install datasinking
|
|
@@ -68,17 +69,17 @@ pip install datasinking
|
|
|
68
69
|
from datasinking import DataSinking
|
|
69
70
|
|
|
70
71
|
ds = DataSinking("YOUR_KEY")
|
|
71
|
-
|
|
72
|
-
# Latest 3 reports of Kweichow Moutai (full markdown content included)
|
|
73
72
|
for r in ds.get_stock_reports("600519.SS", limit=3):
|
|
74
73
|
print(r["report_period"], r["title"], len(r["content"]), "chars")
|
|
75
74
|
```
|
|
76
75
|
|
|
76
|
+
All five functions (curl / Python / LLM): [`api-examples.md`](api-examples.md).
|
|
77
|
+
|
|
77
78
|
## Ask an LLM (no code)
|
|
78
79
|
|
|
79
80
|
Don't want to write code? Point any LLM at [datasink.ing](https://datasink.ing),
|
|
80
81
|
give it your API key, and ask in plain language. See
|
|
81
|
-
[`llm-examples.md`](llm-examples.md) for
|
|
82
|
+
[`llm-examples.md`](llm-examples.md) for eight end-to-end examples — explore
|
|
82
83
|
coverage, list a company's reports, and extract a figure with correct units.
|
|
83
84
|
|
|
84
85
|
## Examples (`examples/`)
|
|
@@ -91,7 +92,7 @@ coverage, list a company's reports, and extract a figure with correct units.
|
|
|
91
92
|
|
|
92
93
|
Every example pulls from the live API and runs as-is.
|
|
93
94
|
|
|
94
|
-
> `03_download_exchange.py` fetches every report on an exchange (e.g. all of Shenzhen —
|
|
95
|
+
> `03_download_exchange.py` fetches every report on an exchange (e.g. all of Shenzhen — 150k+ documents). Free keys work too, but fall back to slow per-document fetching (1 req/s + shared daily quota); a **paid (yearly)** key is strongly recommended for full-exchange downloads.
|
|
95
96
|
|
|
96
97
|
## Research (`research/`)
|
|
97
98
|
|
|
@@ -107,16 +108,17 @@ Start from [`research/TEMPLATE.md`](research/TEMPLATE.md).
|
|
|
107
108
|
|
|
108
109
|
| | |
|
|
109
110
|
|---|---|
|
|
110
|
-
| Coverage | SSE / SZSE / BSE
|
|
111
|
+
| Coverage | China (SSE / SZSE / BSE) · Korea (KOSPI / KOSDAQ / KONEX) · Japan (TSE) |
|
|
111
112
|
| Document types | annual / semiannual / q1 / q3 / amendment |
|
|
113
|
+
| Update frequency | Daily — Korea/Japan via official DART/EDINET APIs (new filings within ~24h of publication) |
|
|
112
114
|
| Format | Full-text Markdown (with YAML frontmatter) |
|
|
113
|
-
| API | REST — `GET /documents`, batch download, `with_content=1` for full text |
|
|
114
|
-
| Symbols | FMP style: `600519.SS` / `
|
|
115
|
+
| API | REST — `GET /documents`, batch download, `with_content=1` for full text, `?section=` + `/sections` for chapter-level access |
|
|
116
|
+
| Symbols | FMP style: `600519.SS` / `005930.KS` / `7203.T` |
|
|
115
117
|
| Auth | `?apikey=` query parameter (FMP style) |
|
|
116
118
|
|
|
117
119
|
## Data source
|
|
118
120
|
|
|
119
|
-
|
|
121
|
+
Reports are sourced from official regulatory disclosure platforms in each market and converted in-house to clean Markdown.
|
|
120
122
|
|
|
121
123
|
## License
|
|
122
124
|
|
|
@@ -3,8 +3,10 @@ README.md
|
|
|
3
3
|
pyproject.toml
|
|
4
4
|
datasinking/__init__.py
|
|
5
5
|
datasinking/client.py
|
|
6
|
+
datasinking/mcp_server.py
|
|
6
7
|
datasinking.egg-info/PKG-INFO
|
|
7
8
|
datasinking.egg-info/SOURCES.txt
|
|
8
9
|
datasinking.egg-info/dependency_links.txt
|
|
10
|
+
datasinking.egg-info/entry_points.txt
|
|
9
11
|
datasinking.egg-info/requires.txt
|
|
10
12
|
datasinking.egg-info/top_level.txt
|
|
@@ -4,20 +4,26 @@ build-backend = "setuptools.build_meta"
|
|
|
4
4
|
|
|
5
5
|
[project]
|
|
6
6
|
name = "datasinking"
|
|
7
|
-
version = "0.
|
|
8
|
-
description = "Python client for DataSinking — full-text
|
|
7
|
+
version = "0.2.0"
|
|
8
|
+
description = "Python client for DataSinking — full-text Asian financial reports (China, Korea, Japan) as Markdown."
|
|
9
9
|
readme = "README.md"
|
|
10
10
|
requires-python = ">=3.8"
|
|
11
11
|
license = { text = "MIT" }
|
|
12
12
|
authors = [{ name = "DataSinking" }]
|
|
13
|
-
keywords = ["a-share", "china", "financial reports", "markdown", "api", "
|
|
13
|
+
keywords = ["a-share", "china", "korea", "japan", "financial reports", "markdown", "api", "mcp", "model-context-protocol", "rag", "llm"]
|
|
14
14
|
classifiers = [
|
|
15
15
|
"Programming Language :: Python :: 3",
|
|
16
16
|
"License :: OSI Approved :: MIT License",
|
|
17
17
|
"Operating System :: OS Independent",
|
|
18
18
|
"Topic :: Office/Business :: Financial",
|
|
19
19
|
]
|
|
20
|
-
dependencies = [
|
|
20
|
+
dependencies = []
|
|
21
|
+
|
|
22
|
+
[project.optional-dependencies]
|
|
23
|
+
mcp = ["mcp>=1.0.0", "requests>=2.28"]
|
|
24
|
+
|
|
25
|
+
[project.scripts]
|
|
26
|
+
datasinking-mcp = "datasinking.mcp_server:main"
|
|
21
27
|
|
|
22
28
|
[project.urls]
|
|
23
29
|
Homepage = "https://datasink.ing"
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
requests
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|