datasinking 0.2.2__tar.gz → 0.2.3__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.
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: datasinking
3
- Version: 0.2.2
3
+ Version: 0.2.3
4
4
  Summary: Python client for DataSinking — full-text Asian financial reports (China, Korea, Japan) as Markdown.
5
5
  Author: DataSinking
6
6
  License: MIT
@@ -52,6 +52,8 @@ datasinking-mcp # requires DATASINK_API_KEY (free at https://datasink.i
52
52
  Or add to your client with `command: datasinking-mcp`. A remote streamable-HTTP endpoint
53
53
  is also live at `https://api.datasink.ing/mcp`. See [`mcp-server.md`](mcp-server.md).
54
54
 
55
+ ![DataSinking MCP in Claude](docs/images/mcp-demo.png)
56
+
55
57
  ## What this repo is
56
58
 
57
59
  Examples, research and tutorials showing how to work with financial report data, including reproducing the presentation styles found in financial-report research papers.
@@ -109,7 +111,7 @@ coverage, list a company's reports, and extract a figure with correct units.
109
111
 
110
112
  Every example pulls from the live API and runs as-is.
111
113
 
112
- > `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.
114
+ > `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 (3 req/s, 8,191 requests/day per key, drawn from a 131,071/day pool shared by all free users); a **paid (yearly)** key is strongly recommended for full-exchange downloads.
113
115
 
114
116
  ## Research (`research/`)
115
117
 
@@ -125,7 +127,7 @@ Start from [`research/TEMPLATE.md`](research/TEMPLATE.md).
125
127
 
126
128
  | | |
127
129
  |---|---|
128
- | Coverage | China (SSE / SZSE / BSE) · Korea (KOSPI / KOSDAQ / KONEX) · Japan (TSE) |
130
+ | Coverage | China (SSE / SZSE / BSE) · Korea (KOSPI / KOSDAQ / KONEX) · Japan (TSE) · Taiwan (TWSE / TPEx) |
129
131
  | Document types | annual / semiannual / q1 / q3 / amendment |
130
132
  | Update frequency | Daily — Korea/Japan via official DART/EDINET APIs (new filings within ~24h of publication) |
131
133
  | Format | Full-text Markdown (with YAML frontmatter) |
@@ -135,7 +137,16 @@ Start from [`research/TEMPLATE.md`](research/TEMPLATE.md).
135
137
 
136
138
  ## Data source
137
139
 
138
- Reports are sourced from official regulatory disclosure platforms in each market and converted in-house to clean Markdown.
140
+ Reports are sourced from the official regulatory disclosure platform of each market and converted in-house to clean Markdown:
141
+
142
+ | Market | Source | Platform |
143
+ |---|---|---|
144
+ | China A-shares (`.SS` `.SZ` `.BJ`) | 巨潮资讯网 cninfo | CSRC-designated disclosure platform |
145
+ | Korea (`.KS` `.KQ` `.KN`) | DART | Financial Supervisory Service — opendart.fss.or.kr |
146
+ | Japan (`.T`) | EDINET | Financial Services Agency — disclosure2.edinet-fsa.go.jp |
147
+ | Taiwan (`.TW` `.TWO`) | 公開資訊觀測站 MOPS | Taiwan Stock Exchange — mops.twse.com.tw |
148
+
149
+ Every document also carries a `source` field in the API response, so the attribution travels with the data. **Please keep it when you redistribute.**
139
150
 
140
151
  ## License
141
152
 
@@ -30,6 +30,8 @@ datasinking-mcp # requires DATASINK_API_KEY (free at https://datasink.i
30
30
  Or add to your client with `command: datasinking-mcp`. A remote streamable-HTTP endpoint
31
31
  is also live at `https://api.datasink.ing/mcp`. See [`mcp-server.md`](mcp-server.md).
32
32
 
33
+ ![DataSinking MCP in Claude](docs/images/mcp-demo.png)
34
+
33
35
  ## What this repo is
34
36
 
35
37
  Examples, research and tutorials showing how to work with financial report data, including reproducing the presentation styles found in financial-report research papers.
@@ -87,7 +89,7 @@ coverage, list a company's reports, and extract a figure with correct units.
87
89
 
88
90
  Every example pulls from the live API and runs as-is.
89
91
 
90
- > `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.
92
+ > `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 (3 req/s, 8,191 requests/day per key, drawn from a 131,071/day pool shared by all free users); a **paid (yearly)** key is strongly recommended for full-exchange downloads.
91
93
 
92
94
  ## Research (`research/`)
93
95
 
@@ -103,7 +105,7 @@ Start from [`research/TEMPLATE.md`](research/TEMPLATE.md).
103
105
 
104
106
  | | |
105
107
  |---|---|
106
- | Coverage | China (SSE / SZSE / BSE) · Korea (KOSPI / KOSDAQ / KONEX) · Japan (TSE) |
108
+ | Coverage | China (SSE / SZSE / BSE) · Korea (KOSPI / KOSDAQ / KONEX) · Japan (TSE) · Taiwan (TWSE / TPEx) |
107
109
  | Document types | annual / semiannual / q1 / q3 / amendment |
108
110
  | Update frequency | Daily — Korea/Japan via official DART/EDINET APIs (new filings within ~24h of publication) |
109
111
  | Format | Full-text Markdown (with YAML frontmatter) |
@@ -113,7 +115,16 @@ Start from [`research/TEMPLATE.md`](research/TEMPLATE.md).
113
115
 
114
116
  ## Data source
115
117
 
116
- Reports are sourced from official regulatory disclosure platforms in each market and converted in-house to clean Markdown.
118
+ Reports are sourced from the official regulatory disclosure platform of each market and converted in-house to clean Markdown:
119
+
120
+ | Market | Source | Platform |
121
+ |---|---|---|
122
+ | China A-shares (`.SS` `.SZ` `.BJ`) | 巨潮资讯网 cninfo | CSRC-designated disclosure platform |
123
+ | Korea (`.KS` `.KQ` `.KN`) | DART | Financial Supervisory Service — opendart.fss.or.kr |
124
+ | Japan (`.T`) | EDINET | Financial Services Agency — disclosure2.edinet-fsa.go.jp |
125
+ | Taiwan (`.TW` `.TWO`) | 公開資訊觀測站 MOPS | Taiwan Stock Exchange — mops.twse.com.tw |
126
+
127
+ Every document also carries a `source` field in the API response, so the attribution travels with the data. **Please keep it when you redistribute.**
117
128
 
118
129
  ## License
119
130
 
@@ -36,7 +36,7 @@ mcp = FastMCP(
36
36
  "DataSinking",
37
37
  title="DataSinking — Full-text Asian Financial Reports",
38
38
  description="Full-text Asian financial reports (China, Korea, Japan) as clean Markdown via API, with chapter-level access for RAG and AI agents.",
39
- version="0.2.2",
39
+ version="0.2.3",
40
40
  instructions=(
41
41
  "DataSinking serves full-text financial reports (annual / semi-annual / quarterly) "
42
42
  "from China, Korea and Japan as clean Markdown, ready for LLM reading and RAG. "
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: datasinking
3
- Version: 0.2.2
3
+ Version: 0.2.3
4
4
  Summary: Python client for DataSinking — full-text Asian financial reports (China, Korea, Japan) as Markdown.
5
5
  Author: DataSinking
6
6
  License: MIT
@@ -52,6 +52,8 @@ datasinking-mcp # requires DATASINK_API_KEY (free at https://datasink.i
52
52
  Or add to your client with `command: datasinking-mcp`. A remote streamable-HTTP endpoint
53
53
  is also live at `https://api.datasink.ing/mcp`. See [`mcp-server.md`](mcp-server.md).
54
54
 
55
+ ![DataSinking MCP in Claude](docs/images/mcp-demo.png)
56
+
55
57
  ## What this repo is
56
58
 
57
59
  Examples, research and tutorials showing how to work with financial report data, including reproducing the presentation styles found in financial-report research papers.
@@ -109,7 +111,7 @@ coverage, list a company's reports, and extract a figure with correct units.
109
111
 
110
112
  Every example pulls from the live API and runs as-is.
111
113
 
112
- > `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.
114
+ > `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 (3 req/s, 8,191 requests/day per key, drawn from a 131,071/day pool shared by all free users); a **paid (yearly)** key is strongly recommended for full-exchange downloads.
113
115
 
114
116
  ## Research (`research/`)
115
117
 
@@ -125,7 +127,7 @@ Start from [`research/TEMPLATE.md`](research/TEMPLATE.md).
125
127
 
126
128
  | | |
127
129
  |---|---|
128
- | Coverage | China (SSE / SZSE / BSE) · Korea (KOSPI / KOSDAQ / KONEX) · Japan (TSE) |
130
+ | Coverage | China (SSE / SZSE / BSE) · Korea (KOSPI / KOSDAQ / KONEX) · Japan (TSE) · Taiwan (TWSE / TPEx) |
129
131
  | Document types | annual / semiannual / q1 / q3 / amendment |
130
132
  | Update frequency | Daily — Korea/Japan via official DART/EDINET APIs (new filings within ~24h of publication) |
131
133
  | Format | Full-text Markdown (with YAML frontmatter) |
@@ -135,7 +137,16 @@ Start from [`research/TEMPLATE.md`](research/TEMPLATE.md).
135
137
 
136
138
  ## Data source
137
139
 
138
- Reports are sourced from official regulatory disclosure platforms in each market and converted in-house to clean Markdown.
140
+ Reports are sourced from the official regulatory disclosure platform of each market and converted in-house to clean Markdown:
141
+
142
+ | Market | Source | Platform |
143
+ |---|---|---|
144
+ | China A-shares (`.SS` `.SZ` `.BJ`) | 巨潮资讯网 cninfo | CSRC-designated disclosure platform |
145
+ | Korea (`.KS` `.KQ` `.KN`) | DART | Financial Supervisory Service — opendart.fss.or.kr |
146
+ | Japan (`.T`) | EDINET | Financial Services Agency — disclosure2.edinet-fsa.go.jp |
147
+ | Taiwan (`.TW` `.TWO`) | 公開資訊觀測站 MOPS | Taiwan Stock Exchange — mops.twse.com.tw |
148
+
149
+ Every document also carries a `source` field in the API response, so the attribution travels with the data. **Please keep it when you redistribute.**
139
150
 
140
151
  ## License
141
152
 
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
4
4
 
5
5
  [project]
6
6
  name = "datasinking"
7
- version = "0.2.2"
7
+ version = "0.2.3"
8
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"
File without changes
File without changes