dataify-sdk 1.1.0__tar.gz → 1.2.0__tar.gz

{dataify_sdk-1.1.0 → dataify_sdk-1.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: dataify-sdk
-Version: 1.1.0
+Version: 1.2.0
 Summary: Python SDK that calls the Dataify upstream REST API directly (no MCP layer) — web scrapers and search engines.
 Project-URL: Homepage, https://dashboard.dataify.com
 Project-URL: Repository, https://github.com/dataify/dataify-sdk

{dataify_sdk-1.1.0 → dataify_sdk-1.2.0}/PYPI_RELEASE.md

@@ -87,6 +87,22 @@ username: __token__
 password: TestPyPI token
 ```
 
+如果看到 `WARNING This environment is not supported for trusted publishing`，本机发布时可以忽略，继续用上面的 token 登录即可。
+
+如果返回 `403 Forbidden`，先执行：
+
+```powershell
+python -m twine upload --repository testpypi --verbose dist/*
+```
+
+常见原因：
+
+- 用了正式 PyPI token；TestPyPI 必须用 TestPyPI 单独创建的 token。
+- token 对应账号不是 `dataify-sdk` 在 TestPyPI 上的 owner/maintainer。
+- 项目级 token 只能上传已有项目；首次创建项目建议用 TestPyPI 账号级 token。
+- TestPyPI 账号邮箱未验证。
+- 版本号或文件已上传过，换一个新版本号后重新构建。
+
 ## 10. 从 TestPyPI 安装验证
 
 ```powershell
@@ -111,6 +127,8 @@ username: __token__
 password: PyPI token
 ```
 
+如果看到 `WARNING This environment is not supported for trusted publishing`，本机发布时可以忽略，继续用上面的 token 登录即可。
+
 ## 12. 从正式 PyPI 安装验证
 
 ```powershell

{dataify_sdk-1.1.0 → dataify_sdk-1.2.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "dataify-sdk"
-version = "1.1.0"
+version = "1.2.0"
 description = "Python SDK that calls the Dataify upstream REST API directly (no MCP layer) — web scrapers and search engines."
 readme = "README.md"
 license = {text = "MIT"}

{dataify_sdk-1.1.0 → dataify_sdk-1.2.0}/src/dataify_sdk/__init__.py

@@ -31,7 +31,7 @@ from dataify_sdk.errors import (
     DataifyTimeoutError,
 )
 
-__version__ = "1.1.0"
+__version__ = "1.2.0"
 
 
 

{dataify_sdk-1.1.0 → dataify_sdk-1.2.0}/src/dataify_sdk/tools/__init__.py

@@ -15,6 +15,7 @@ from dataify_sdk.tools.bingsearch import bing_search
 from dataify_sdk.tools.bingshopping import bing_shopping
 from dataify_sdk.tools.bingvideos import bing_videos
 from dataify_sdk.tools.bookinghotellist import booking_hotellist_by_url
+from dataify_sdk.tools.chatgptanswer import chatgpt_answer_by_keywords, chatgpt_answer_by_url
 from dataify_sdk.tools.crunchbasecompany import crunchbase_company_by_url, crunchbase_company_by_keywords
 from dataify_sdk.tools.duckduckgosearch import duckduckgo_search
 from dataify_sdk.tools.ebayinfo import ebay_ebay_by_url, ebay_ebay_by_category_url, ebay_ebay_by_keywords, ebay_ebay_by_listurl
@@ -94,6 +95,8 @@ __all__ = [
     'bing_shopping',
     'bing_videos',
     'booking_hotellist_by_url',
+    'chatgpt_answer_by_keywords',
+    'chatgpt_answer_by_url',
     'crunchbase_company_by_url',
     'crunchbase_company_by_keywords',
     'duckduckgo_search',

dataify_sdk-1.2.0/src/dataify_sdk/tools/chatgptanswer.py

@@ -0,0 +1,66 @@
+"""Auto-generated Dataify tool functions.  Do not edit by hand.
+
+Generated from the Go reference project by ``dataify_sdk._codegen.generate``.
+Each function calls the Dataify upstream REST API directly (no MCP layer).
+"""
+
+from __future__ import annotations
+
+import json
+from typing import Any
+
+from dataify_sdk.client import DataifyClient, get_default_client
+
+
+def _client(client: DataifyClient | None) -> DataifyClient:
+    return client if client is not None else get_default_client()
+
+def chatgpt_answer_by_keywords(file_name: str = '{{TasksID}}', search_terms: str = 'pizza', client: DataifyClient | None = None) -> dict[str, Any]:
+    """当用户需要 ChatGPT 答案、ChatGPT 回答内容、ChatGPT 提问结果、AI 回答文本、引用来源链接、相关推荐问题、答案生成时间、模型版本，与采集、抓取、爬取、获取、提取等动词组合时触发。复用一个工具提交 ChatGPT 答案采集 Builder 任务，支持 chatgpt_answer_by-keywords（通过搜索关键词采集）和 chatgpt_answer_by-url（通过 URL 采集）。
+
+    上游接口: Scraper Builder (POST /builder?platform=1)
+    spider_name: chatgpt.com
+    spider_id: chatgpt_answer_by-keywords
+
+    Parameters
+    ----------
+    search_terms: 搜索关键词，该参数用于指定向 ChatGPT 提问并采集答案的关键词。用于 chatgpt_answer_by-keywords。  [默认: pizza]
+    file_name: Builder file_name 字段。不传默认为 {{TasksID}}。  [默认: {{TasksID}}]
+    client: 可选 DataifyClient 实例;不传则使用默认 client(优先读取 DATAIFY_API_TOKEN, 兼容 DATAIFY_TOKEN)。
+    """
+    params_obj = {
+        "search_terms": search_terms,
+    }
+    spider_parameters = json.dumps([params_obj], ensure_ascii=False)
+    return _client(client).request_scraper(
+        spider_name='chatgpt.com',
+        spider_id='chatgpt_answer_by-keywords',
+        spider_parameters=spider_parameters,
+        file_name=file_name,
+    )
+
+
+def chatgpt_answer_by_url(chatgpt_url: str = '', file_name: str = '{{TasksID}}', client: DataifyClient | None = None) -> dict[str, Any]:
+    """当用户需要 ChatGPT 答案、ChatGPT 回答内容、ChatGPT 提问结果、AI 回答文本、引用来源链接、相关推荐问题、答案生成时间、模型版本，与采集、抓取、爬取、获取、提取等动词组合时触发。复用一个工具提交 ChatGPT 答案采集 Builder 任务，支持 chatgpt_answer_by-keywords（通过搜索关键词采集）和 chatgpt_answer_by-url（通过 URL 采集）。
+
+    上游接口: Scraper Builder (POST /builder?platform=1)
+    spider_name: chatgpt.com
+    spider_id: chatgpt_answer_by-url
+
+    Parameters
+    ----------
+    chatgpt_url: ChatGPT 页面 URL，该参数用于指定待采集答案的 ChatGPT 访问 URL。用于 chatgpt_answer_by-url。  [默认: (空)]
+    file_name: Builder file_name 字段。不传默认为 {{TasksID}}。  [默认: {{TasksID}}]
+    client: 可选 DataifyClient 实例;不传则使用默认 client(优先读取 DATAIFY_API_TOKEN, 兼容 DATAIFY_TOKEN)。
+    """
+    params_obj = {
+        "chatgpt_url": chatgpt_url,
+    }
+    spider_parameters = json.dumps([params_obj], ensure_ascii=False)
+    return _client(client).request_scraper(
+        spider_name='chatgpt.com',
+        spider_id='chatgpt_answer_by-url',
+        spider_parameters=spider_parameters,
+        file_name=file_name,
+    )
+

{dataify_sdk-1.1.0 → dataify_sdk-1.2.0}/tests/test_tools/test_tool_modules.py

@@ -27,10 +27,10 @@ def test_module_imports(module):
 
 def test_function_count():
     mods = _all_modules()
-    assert len(mods) == 70
+    assert len(mods) == 71
     import dataify_sdk.tools as pkg
 
-    assert len(pkg.__all__) == 113
+    assert len(pkg.__all__) == 115
 
 
 def test_amazon_product_by_asin_request(captured_request):
@@ -45,6 +45,34 @@ def test_amazon_product_by_asin_request(captured_request):
     assert json.loads(form["spider_parameters"]) == [{"asin": "B0X"}]
 
 
+def test_chatgpt_answer_by_url_request(captured_request):
+    from dataify_sdk.tools.chatgptanswer import chatgpt_answer_by_url
+
+    chatgpt_answer_by_url(
+        chatgpt_url="https://chatgpt.com/?q=pizza", client=DataifyClient(token="t")
+    )
+    req = captured_request["req"]
+    assert req.full_url.endswith("/builder?platform=1")
+    form = decode_form(req)
+    assert form["spider_id"] == "chatgpt_answer_by-url"
+    assert form["spider_name"] == "chatgpt.com"
+    assert json.loads(form["spider_parameters"]) == [
+        {"chatgpt_url": "https://chatgpt.com/?q=pizza"}
+    ]
+
+
+def test_chatgpt_answer_by_keywords_request(captured_request):
+    from dataify_sdk.tools.chatgptanswer import chatgpt_answer_by_keywords
+
+    chatgpt_answer_by_keywords(search_terms="pizza", client=DataifyClient(token="t"))
+    req = captured_request["req"]
+    assert req.full_url.endswith("/builder?platform=1")
+    form = decode_form(req)
+    assert form["spider_id"] == "chatgpt_answer_by-keywords"
+    assert form["spider_name"] == "chatgpt.com"
+    assert json.loads(form["spider_parameters"]) == [{"search_terms": "pizza"}]
+
+
 def test_google_search_request(captured_request):
     from dataify_sdk.tools.googlesearch import google_search
 
@@ -57,14 +85,14 @@ def test_google_search_request(captured_request):
     assert "gl" not in form  # empty dropped
 
 
-def test_default_client_uses_env(monkeypatch, captured_request):
-    monkeypatch.setenv("DATAIFY_API_TOKEN", "env-token")
-    from dataify_sdk.tools.twitterpost import twitter_post_by_profileurl
-
-    # no client passed -> default client reads DATAIFY_API_TOKEN
-    twitter_post_by_profileurl(url="https://x.com/foo")
-    req = captured_request["req"]
-    assert req.full_url.endswith("/builder?platform=1")
-    form = decode_form(req)
-    assert json.loads(form["spider_parameters"]) == [{"url": "https://x.com/foo"}]
-    assert req.get_header("Authorization") == "Bearer env-token"
+def test_default_client_uses_env(monkeypatch, captured_request):
+    monkeypatch.setenv("DATAIFY_API_TOKEN", "env-token")
+    from dataify_sdk.tools.twitterpost import twitter_post_by_profileurl
+
+    # no client passed -> default client reads DATAIFY_API_TOKEN
+    twitter_post_by_profileurl(url="https://x.com/foo")
+    req = captured_request["req"]
+    assert req.full_url.endswith("/builder?platform=1")
+    form = decode_form(req)
+    assert json.loads(form["spider_parameters"]) == [{"url": "https://x.com/foo"}]
+    assert req.get_header("Authorization") == "Bearer env-token"