langchain-scrapeless 0.1.3__tar.gz

langchain_scrapeless-0.1.3/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Scrapeless
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

langchain_scrapeless-0.1.3/PKG-INFO

@@ -0,0 +1,271 @@
+Metadata-Version: 2.3
+Name: langchain-scrapeless
+Version: 0.1.3
+Summary: An integration package connecting Scrapeless and LangChain
+License: MIT
+Keywords: scrapeless,langchain,integration,universal scraping api,scraping,crawl
+Author: Scrapeless Team
+Author-email: scrapelessteam@gmail.com
+Requires-Python: >=3.9,<4.0
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Dist: jupyter (>=1.1.1,<2.0.0)
+Requires-Dist: langchain-core (>=0.3.15,<0.4.0)
+Requires-Dist: python-dotenv (>=1.1.1,<2.0.0)
+Requires-Dist: scrapeless (==1.1.1)
+Project-URL: Issue Tracker, https://github.com/scrapeless-ai/langchain-scrapeless/issues
+Project-URL: Repository, https://github.com/scrapeless-ai/langchain-scrapeless
+Project-URL: Release Notes, https://github.com/scrapeless-ai/langchain-scrapeless/releases?expanded=true
+Project-URL: Scrapeless Homepage, https://scrapeless.com
+Project-URL: Source Code, https://github.com/scrapeless-ai/langchain-scrapeless/tree/main
+Description-Content-Type: text/markdown
+
+<div align="center">
+  <img width="180" src="https://app.scrapeless.com/assets/logo.svg" alt="Scrapeless logo">
+
+LangChain Scrapeless: an all-in-one, highly scalable web scraping toolkit for enterprises and developers that also integrates with LangChain’s AI tools. Maintained by [Scrapeless](https://app.scrapeless.com/passport/login?utm_source=github&utm_medium=langchain-scrapeless&utm_campaign=langchain-scrapeless).
+
+[Scrapeless](https://app.scrapeless.com/passport/login?utm_source=github&utm_medium=langchain-scrapeless&utm_campaign=langchain-scrapeless) | [Documentation](https://docs.scrapeless.com) | [LangChain](https://langchain.com)
+
+</div>
+
+---
+
+**langchain-scrapeless** is designed for seamless integration with LangChain, enabling you to:
+
+- Run custom scraping tasks using your own crawlers or scraping logic.
+- Automate data extraction and processing workflows in Python.
+- Manage and interact with datasets produced by your scraping jobs.
+- Access scraping and data handling capabilities as LangChain tools, making them easy to compose with LLM-powered chains and agents.
+
+## 📦 Installation
+
+```bash
+pip install langchain-scrapeless
+```
+
+## ✅ Prerequisites
+
+You should configure the credentials for the Scrapeless API in your environment variables.
+
+- `SCRAPELESS_API_KEY`: Your Scrapeless API key.
+
+If you don't have an API key, you can register at [here](https://app.scrapeless.com/passport/register?utm_source=github&utm_medium=langchain-scrapeless&utm_campaign=langchain-scrapeless) and learn how to get your API key in [Scrapeless documentation](https://docs.scrapeless.com/en/sdk/node-sdk/#quick-start).
+
+## 🛠️ Available Tools
+
+### 🔍 DeepSerp
+
+#### 🌐 ScrapelessDeepSerpGoogleSearchTool
+
+Perform Google search queries and get the results.
+
+```python
+from langchain_scrapeless import ScrapelessDeepSerpGoogleSearchTool
+
+tool = ScrapelessDeepSerpGoogleSearchTool()
+
+# Basic usage
+# result = tool.invoke("I want to know Scrapeless")
+# print(result)
+
+# Advanced usage
+result = tool.invoke({
+    "q": "Scrapeless",
+    "hl": "en",
+    "google_domain": "google.com"
+})
+print(result)
+
+# With LangChain
+from langchain_openai import ChatOpenAI
+from langchain_scrapeless import ScrapelessDeepSerpGoogleSearchTool
+from langgraph.prebuilt import create_react_agent
+
+llm = ChatOpenAI()
+
+tool = ScrapelessDeepSerpGoogleSearchTool()
+
+# Use the tool with an agent
+tools = [tool]
+agent = create_react_agent(llm, tools)
+
+for chunk in agent.stream(
+        {"messages": [("human", "I want to what is Scrapeless")]},
+        stream_mode="values"
+):
+    chunk["messages"][-1].pretty_print()
+```
+
+You can visit [here](https://apidocs.scrapeless.com/doc-800321) to learn more customizations options.
+
+#### 🌐 ScrapelessDeepSerpGoogleTrendsTool
+
+Perform Google trends queries and get the results.
+
+```python
+from langchain_scrapeless import ScrapelessDeepSerpGoogleTrendsTool
+
+tool = ScrapelessDeepSerpGoogleTrendsTool()
+
+# Basic usage
+# result = tool.invoke("Funny 2048,negamon monster trainer")
+# print(result)
+
+# Advanced usage
+result = tool.invoke({
+    "q": "Scrapeless",
+    "data_type": "related_topics",
+    "hl": "en"
+})
+print(result)
+
+# With LangChain
+from langchain_openai import ChatOpenAI
+from langchain_scrapeless import ScrapelessDeepSerpGoogleTrendsTool
+from langgraph.prebuilt import create_react_agent
+
+llm = ChatOpenAI()
+
+tool = ScrapelessDeepSerpGoogleTrendsTool()
+
+# Use the tool with an agent
+tools = [tool]
+agent = create_react_agent(llm, tools)
+
+for chunk in agent.stream(
+        {"messages": [("human", "I want to know the iphone keyword trends")]},
+        stream_mode="values"
+):
+    chunk["messages"][-1].pretty_print()
+
+```
+
+You can visit [here](https://apidocs.scrapeless.com/doc-796980) to learn more customizations options.
+
+### 🔓 ScrapelessUniversalScrapingTool
+
+Access any website at scale and say goodbye to blocks.
+
+```python
+from langchain_scrapeless import ScrapelessUniversalScrapingTool
+
+tool = ScrapelessUniversalScrapingTool()
+
+# Basic usage
+# result = tool.invoke("https://example.com")
+# print(result)
+
+# Advanced usage
+result = tool.invoke({
+    "url": "https://exmaple.com",
+    "response_type": "markdown"
+})
+print(result)
+
+# With LangChain
+from langchain_openai import ChatOpenAI
+from langchain_scrapeless import ScrapelessUniversalScrapingTool
+from langgraph.prebuilt import create_react_agent
+
+llm = ChatOpenAI()
+
+tool = ScrapelessUniversalScrapingTool()
+
+# Use the tool with an agent
+tools = [tool]
+agent = create_react_agent(llm, tools)
+
+for chunk in agent.stream(
+        {"messages": [("human", "Use the scrapeless scraping tool to fetch https://www.scrapeless.com/en and extract the h1 tag.")]},
+        stream_mode="values"
+):
+    chunk["messages"][-1].pretty_print()
+```
+
+You can visit [here](https://apidocs.scrapeless.com/api-12948840) to learn more customizations options.
+
+### 🕷️ Crawler
+
+#### 🌐 ScrapelessCrawlerCrawlTool
+
+Crawl a website and its linked pages to extract comprehensive data
+
+```python
+from langchain_scrapeless import ScrapelessCrawlerCrawlTool
+
+tool = ScrapelessCrawlerCrawlTool()
+
+# Basic
+# result = tool.invoke("https://example.com")
+# print(result)
+
+# Advanced usage
+result = tool.invoke({
+    "url": "https://exmaple.com",
+    "limit": 4
+})
+print(result)
+
+# With LangChain
+from langchain_openai import ChatOpenAI
+from langchain_scrapeless import ScrapelessCrawlerCrawlTool
+from langgraph.prebuilt import create_react_agent
+
+llm = ChatOpenAI()
+
+tool = ScrapelessCrawlerCrawlTool()
+
+# Use the tool with an agent
+tools = [tool]
+agent = create_react_agent(llm, tools)
+
+for chunk in agent.stream(
+        {"messages": [("human", "Use the scrapeless crawler crawl tool to crawl the website https://example.com and output the markdown content as a string.")]},
+        stream_mode="values"
+):
+    chunk["messages"][-1].pretty_print()
+```
+
+You can visit [here](https://apidocs.scrapeless.com/api-17509010) to learn more customizations options.
+
+#### 🌐 ScrapelessCrawlerScrapeTool
+
+Extract data from a single or multiple webpages.
+
+```python
+from langchain_scrapeless import ScrapelessCrawlerScrapeTool
+
+tool = ScrapelessCrawlerScrapeTool()
+
+result = tool.invoke({
+    "urls": ["https://exmaple.com", "https://www.scrapeless.com/en"],
+    "formats": ["markdown"]
+})
+print(result)
+
+# With LangChain
+from langchain_openai import ChatOpenAI
+from langchain_scrapeless import ScrapelessCrawlerScrapeTool
+from langgraph.prebuilt import create_react_agent
+
+llm = ChatOpenAI()
+
+tool = ScrapelessCrawlerScrapeTool()
+
+# Use the tool with an agent
+tools = [tool]
+agent = create_react_agent(llm, tools)
+
+for chunk in agent.stream(
+        {"messages": [("human", "Use the scrapeless crawler scrape tool to get the website content of https://example.com and output the html content as a string.")]},
+        stream_mode="values"
+):
+    chunk["messages"][-1].pretty_print()
+```
+

langchain_scrapeless-0.1.3/README.md

@@ -0,0 +1,243 @@
+<div align="center">
+  <img width="180" src="https://app.scrapeless.com/assets/logo.svg" alt="Scrapeless logo">
+
+LangChain Scrapeless: an all-in-one, highly scalable web scraping toolkit for enterprises and developers that also integrates with LangChain’s AI tools. Maintained by [Scrapeless](https://app.scrapeless.com/passport/login?utm_source=github&utm_medium=langchain-scrapeless&utm_campaign=langchain-scrapeless).
+
+[Scrapeless](https://app.scrapeless.com/passport/login?utm_source=github&utm_medium=langchain-scrapeless&utm_campaign=langchain-scrapeless) | [Documentation](https://docs.scrapeless.com) | [LangChain](https://langchain.com)
+
+</div>
+
+---
+
+**langchain-scrapeless** is designed for seamless integration with LangChain, enabling you to:
+
+- Run custom scraping tasks using your own crawlers or scraping logic.
+- Automate data extraction and processing workflows in Python.
+- Manage and interact with datasets produced by your scraping jobs.
+- Access scraping and data handling capabilities as LangChain tools, making them easy to compose with LLM-powered chains and agents.
+
+## 📦 Installation
+
+```bash
+pip install langchain-scrapeless
+```
+
+## ✅ Prerequisites
+
+You should configure the credentials for the Scrapeless API in your environment variables.
+
+- `SCRAPELESS_API_KEY`: Your Scrapeless API key.
+
+If you don't have an API key, you can register at [here](https://app.scrapeless.com/passport/register?utm_source=github&utm_medium=langchain-scrapeless&utm_campaign=langchain-scrapeless) and learn how to get your API key in [Scrapeless documentation](https://docs.scrapeless.com/en/sdk/node-sdk/#quick-start).
+
+## 🛠️ Available Tools
+
+### 🔍 DeepSerp
+
+#### 🌐 ScrapelessDeepSerpGoogleSearchTool
+
+Perform Google search queries and get the results.
+
+```python
+from langchain_scrapeless import ScrapelessDeepSerpGoogleSearchTool
+
+tool = ScrapelessDeepSerpGoogleSearchTool()
+
+# Basic usage
+# result = tool.invoke("I want to know Scrapeless")
+# print(result)
+
+# Advanced usage
+result = tool.invoke({
+    "q": "Scrapeless",
+    "hl": "en",
+    "google_domain": "google.com"
+})
+print(result)
+
+# With LangChain
+from langchain_openai import ChatOpenAI
+from langchain_scrapeless import ScrapelessDeepSerpGoogleSearchTool
+from langgraph.prebuilt import create_react_agent
+
+llm = ChatOpenAI()
+
+tool = ScrapelessDeepSerpGoogleSearchTool()
+
+# Use the tool with an agent
+tools = [tool]
+agent = create_react_agent(llm, tools)
+
+for chunk in agent.stream(
+        {"messages": [("human", "I want to what is Scrapeless")]},
+        stream_mode="values"
+):
+    chunk["messages"][-1].pretty_print()
+```
+
+You can visit [here](https://apidocs.scrapeless.com/doc-800321) to learn more customizations options.
+
+#### 🌐 ScrapelessDeepSerpGoogleTrendsTool
+
+Perform Google trends queries and get the results.
+
+```python
+from langchain_scrapeless import ScrapelessDeepSerpGoogleTrendsTool
+
+tool = ScrapelessDeepSerpGoogleTrendsTool()
+
+# Basic usage
+# result = tool.invoke("Funny 2048,negamon monster trainer")
+# print(result)
+
+# Advanced usage
+result = tool.invoke({
+    "q": "Scrapeless",
+    "data_type": "related_topics",
+    "hl": "en"
+})
+print(result)
+
+# With LangChain
+from langchain_openai import ChatOpenAI
+from langchain_scrapeless import ScrapelessDeepSerpGoogleTrendsTool
+from langgraph.prebuilt import create_react_agent
+
+llm = ChatOpenAI()
+
+tool = ScrapelessDeepSerpGoogleTrendsTool()
+
+# Use the tool with an agent
+tools = [tool]
+agent = create_react_agent(llm, tools)
+
+for chunk in agent.stream(
+        {"messages": [("human", "I want to know the iphone keyword trends")]},
+        stream_mode="values"
+):
+    chunk["messages"][-1].pretty_print()
+
+```
+
+You can visit [here](https://apidocs.scrapeless.com/doc-796980) to learn more customizations options.
+
+### 🔓 ScrapelessUniversalScrapingTool
+
+Access any website at scale and say goodbye to blocks.
+
+```python
+from langchain_scrapeless import ScrapelessUniversalScrapingTool
+
+tool = ScrapelessUniversalScrapingTool()
+
+# Basic usage
+# result = tool.invoke("https://example.com")
+# print(result)
+
+# Advanced usage
+result = tool.invoke({
+    "url": "https://exmaple.com",
+    "response_type": "markdown"
+})
+print(result)
+
+# With LangChain
+from langchain_openai import ChatOpenAI
+from langchain_scrapeless import ScrapelessUniversalScrapingTool
+from langgraph.prebuilt import create_react_agent
+
+llm = ChatOpenAI()
+
+tool = ScrapelessUniversalScrapingTool()
+
+# Use the tool with an agent
+tools = [tool]
+agent = create_react_agent(llm, tools)
+
+for chunk in agent.stream(
+        {"messages": [("human", "Use the scrapeless scraping tool to fetch https://www.scrapeless.com/en and extract the h1 tag.")]},
+        stream_mode="values"
+):
+    chunk["messages"][-1].pretty_print()
+```
+
+You can visit [here](https://apidocs.scrapeless.com/api-12948840) to learn more customizations options.
+
+### 🕷️ Crawler
+
+#### 🌐 ScrapelessCrawlerCrawlTool
+
+Crawl a website and its linked pages to extract comprehensive data
+
+```python
+from langchain_scrapeless import ScrapelessCrawlerCrawlTool
+
+tool = ScrapelessCrawlerCrawlTool()
+
+# Basic
+# result = tool.invoke("https://example.com")
+# print(result)
+
+# Advanced usage
+result = tool.invoke({
+    "url": "https://exmaple.com",
+    "limit": 4
+})
+print(result)
+
+# With LangChain
+from langchain_openai import ChatOpenAI
+from langchain_scrapeless import ScrapelessCrawlerCrawlTool
+from langgraph.prebuilt import create_react_agent
+
+llm = ChatOpenAI()
+
+tool = ScrapelessCrawlerCrawlTool()
+
+# Use the tool with an agent
+tools = [tool]
+agent = create_react_agent(llm, tools)
+
+for chunk in agent.stream(
+        {"messages": [("human", "Use the scrapeless crawler crawl tool to crawl the website https://example.com and output the markdown content as a string.")]},
+        stream_mode="values"
+):
+    chunk["messages"][-1].pretty_print()
+```
+
+You can visit [here](https://apidocs.scrapeless.com/api-17509010) to learn more customizations options.
+
+#### 🌐 ScrapelessCrawlerScrapeTool
+
+Extract data from a single or multiple webpages.
+
+```python
+from langchain_scrapeless import ScrapelessCrawlerScrapeTool
+
+tool = ScrapelessCrawlerScrapeTool()
+
+result = tool.invoke({
+    "urls": ["https://exmaple.com", "https://www.scrapeless.com/en"],
+    "formats": ["markdown"]
+})
+print(result)
+
+# With LangChain
+from langchain_openai import ChatOpenAI
+from langchain_scrapeless import ScrapelessCrawlerScrapeTool
+from langgraph.prebuilt import create_react_agent
+
+llm = ChatOpenAI()
+
+tool = ScrapelessCrawlerScrapeTool()
+
+# Use the tool with an agent
+tools = [tool]
+agent = create_react_agent(llm, tools)
+
+for chunk in agent.stream(
+        {"messages": [("human", "Use the scrapeless crawler scrape tool to get the website content of https://example.com and output the html content as a string.")]},
+        stream_mode="values"
+):
+    chunk["messages"][-1].pretty_print()
+```

langchain_scrapeless-0.1.3/langchain_scrapeless/__init__.py

@@ -0,0 +1,41 @@
+from importlib import metadata
+
+from langchain_scrapeless.tools.clawer import (
+    ScrapelessCrawlerCrawlTool,
+    ScrapelessCrawlerScrapeTool,
+)
+from langchain_scrapeless.tools.scrapeless_universal_scraping import (
+    ScrapelessUniversalScrapingTool,
+)
+from langchain_scrapeless.tools.scraping_api import (
+    ScrapelessDeepSerpGoogleSearchTool,
+    ScrapelessDeepSerpGoogleTrendsTool,
+)
+from langchain_scrapeless.wrappers import (
+    ScrapelessAPIWrapper,
+    ScrapelessCrawlerCrawlAPIWrapper,
+    ScrapelessCrawlerScrapeAPIWrapper,
+    ScrapelessDeepSerpAPIWrapper,
+    ScrapelessUniversalScrapingAPIWrapper,
+)
+
+try:
+    __version__ = metadata.version(__package__)
+except metadata.PackageNotFoundError:
+    # Case where package metadata is not available.
+    __version__ = ""
+del metadata  # optional, avoids polluting the results of dir(__package__)
+
+__all__ = [
+    "ScrapelessDeepSerpGoogleSearchTool",
+    "ScrapelessDeepSerpGoogleTrendsTool",
+    "ScrapelessUniversalScrapingTool",
+    "ScrapelessAPIWrapper",
+    "ScrapelessUniversalScrapingAPIWrapper",
+    "ScrapelessCrawlerScrapeAPIWrapper",
+    "ScrapelessCrawlerCrawlAPIWrapper",
+    "ScrapelessDeepSerpAPIWrapper",
+    "ScrapelessCrawlerScrapeTool",
+    "ScrapelessCrawlerCrawlTool",
+    "__version__",
+]

langchain_scrapeless-0.1.3/langchain_scrapeless/const.py

@@ -0,0 +1 @@
+REQUESTS_TIMEOUT_SECS: float = 30000 / 1000.0

langchain_scrapeless-0.1.3/langchain_scrapeless/error_messages.py

@@ -0,0 +1,8 @@
+ERROR_SCRAPELESS_TOKEN_ENV_VAR_NOT_SET = (
+    "SCRAPELESS_API_TOKEN environment variable is not set."
+    " Please set it to your Scrapeless API token "
+    "by using `os.environ['SCRAPELESS_API_TOKEN'] = 'YOUR_SCRAPELESS_API_TOKEN'"
+    " in your code or pass it as environment variable."
+    " To pass it as environment variable, you can use the following command:"
+    ' `SCRAPELESS_API_TOKEN="YOUR_SCRAPELESS_API_TOKEN" python your_script.py`'
+)

langchain_scrapeless-0.1.3/langchain_scrapeless/tools/__init__.py

@@ -0,0 +1,14 @@
+from .clawer import ScrapelessCrawlerCrawlTool, ScrapelessCrawlerScrapeTool
+from .scrapeless_universal_scraping import ScrapelessUniversalScrapingTool
+from .scraping_api import (
+    ScrapelessDeepSerpGoogleSearchTool,
+    ScrapelessDeepSerpGoogleTrendsTool,
+)
+
+__all__ = [
+    "ScrapelessUniversalScrapingTool",
+    "ScrapelessDeepSerpGoogleSearchTool",
+    "ScrapelessDeepSerpGoogleTrendsTool",
+    "ScrapelessCrawlerScrapeTool",
+    "ScrapelessCrawlerCrawlTool",
+]

langchain_scrapeless-0.1.3/langchain_scrapeless/tools/clawer/__init__.py

@@ -0,0 +1,4 @@
+from .crawl import ScrapelessCrawlerCrawlTool
+from .scrape import ScrapelessCrawlerScrapeTool
+
+__all__ = ["ScrapelessCrawlerScrapeTool", "ScrapelessCrawlerCrawlTool"]