mirror of https://github.com/hwchase17/langchain
Compare commits
4 Commits
9fa9f05e5d
...
804390ba4b
| Author | SHA1 | Date |
|---|---|---|
WilliamEspegren
|
804390ba4b | 2 weeks ago |
Jamie Lemon
|
6342217b93 | 2 weeks ago |
Chouaieb Nemri
|
8097bec472 | 2 weeks ago |
ccurme
|
9ec7151317 | 2 weeks ago |
@ -0,0 +1,95 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Spider\n",
|
||||
"[Spider](https://spider.cloud/) is the [fastest](https://github.com/spider-rs/spider/blob/main/benches/BENCHMARKS.md) and most affordable crawler and scraper that returns LLM-ready data.\n",
|
||||
"\n",
|
||||
"## Setup"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"pip install spider-client"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Usage\n",
|
||||
"To use spider you need to have an API key from [spider.cloud](https://spider.cloud/)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[Document(page_content='Spider - Fastest Web Crawler built for AI Agents and Large Language Models[Spider v1 Logo Spider ](/)The World\\'s Fastest and Cheapest Crawler API==========View Demo* Basic* StreamingExample requestPythonCopy```import requests, osheaders = { \\'Authorization\\': os.environ[\"SPIDER_API_KEY\"], \\'Content-Type\\': \\'application/json\\',}json_data = {\"limit\":50,\"url\":\"http://www.example.com\"}response = requests.post(\\'https://api.spider.cloud/crawl\\', headers=headers, json=json_data)print(response.json())```Example ResponseScrape with no headaches----------* Proxy rotations* Agent headers* Avoid anti-bot detections* Headless chrome* Markdown LLM ResponsesThe Fastest Web Crawler----------* Powered by [spider-rs](https://github.com/spider-rs/spider)* Do 20,000 pages in seconds* Full concurrency* Powerful and simple API* Cost effectiveScrape Anything with AI----------* Custom scripting browser* Custom data extraction* Data pipelines* Detailed insights* Advanced labeling[API](/docs/api) [Price](/credits/new) [Guides](/guides) [About](/about) [Docs](https://docs.rs/spider/latest/spider/) [Privacy](/privacy) [Terms](/eula)© 2024 Spider from A11yWatchTheme Light Dark Toggle Theme [GitHubGithub](https://github.com/spider-rs/spider)', metadata={'description': 'Collect data rapidly from any website. Seamlessly scrape websites and get data tailored for LLM workloads.', 'domain': 'spider.cloud', 'extracted_data': None, 'file_size': 33743, 'keywords': None, 'pathname': '/', 'resource_type': 'html', 'title': 'Spider - Fastest Web Crawler built for AI Agents and Large Language Models', 'url': '48f1bc3c-3fbb-408a-865b-c191a1bb1f48/spider.cloud/index.html', 'user_id': '48f1bc3c-3fbb-408a-865b-c191a1bb1f48'})]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain_community.document_loaders import SpiderLoader\n",
|
||||
"\n",
|
||||
"loader = SpiderLoader(\n",
|
||||
" api_key=\"YOUR_API_KEY\",\n",
|
||||
" url=\"https://spider.cloud\",\n",
|
||||
" mode=\"scrape\", # if no API key is provided it looks for SPIDER_API_KEY in env\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"data = loader.load()\n",
|
||||
"print(data)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Modes\n",
|
||||
"- `scrape`: Default mode that scrapes a single URL\n",
|
||||
"- `crawl`: Crawl all subpages of the domain url provided"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Crawler options\n",
|
||||
"The `params` parameter is a dictionary that can be passed to the loader. See the [Spider documentation](https://spider.cloud/docs/api) to see all available parameters"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "venv",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.12.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@ -0,0 +1,94 @@
|
||||
from typing import Iterator, Literal, Optional
|
||||
|
||||
from langchain_core.document_loaders import BaseLoader
|
||||
from langchain_core.documents import Document
|
||||
from langchain_core.utils import get_from_env
|
||||
|
||||
|
||||
class SpiderLoader(BaseLoader):
|
||||
"""Load web pages as Documents using Spider AI.
|
||||
|
||||
Must have the Python package `spider-client` installed and a Spider API key.
|
||||
See https://spider.cloud for more.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
url: str,
|
||||
*,
|
||||
api_key: Optional[str] = None,
|
||||
mode: Literal["scrape", "crawl"] = "scrape",
|
||||
params: Optional[dict] = {"return_format": "markdown"},
|
||||
):
|
||||
"""Initialize with API key and URL.
|
||||
|
||||
Args:
|
||||
url: The URL to be processed.
|
||||
api_key: The Spider API key. If not specified, will be read from env
|
||||
var `SPIDER_API_KEY`.
|
||||
mode: The mode to run the loader in. Default is "scrape".
|
||||
Options include "scrape" (single page) and "crawl" (with deeper
|
||||
crawling following subpages).
|
||||
params: Additional parameters for the Spider API.
|
||||
"""
|
||||
try:
|
||||
from spider import Spider # noqa: F401
|
||||
except ImportError:
|
||||
raise ImportError(
|
||||
"`spider` package not found, please run `pip install spider-client`"
|
||||
)
|
||||
if mode not in ("scrape", "crawl"):
|
||||
raise ValueError(
|
||||
f"Unrecognized mode '{mode}'. Expected one of 'scrape', 'crawl'."
|
||||
)
|
||||
# If `params` is `None`, initialize it as an empty dictionary
|
||||
if params is None:
|
||||
params = {}
|
||||
|
||||
# Add a default value for 'metadata' if it's not already present
|
||||
if "metadata" not in params:
|
||||
params["metadata"] = True
|
||||
|
||||
# Use the environment variable if the API key isn't provided
|
||||
api_key = api_key or get_from_env("api_key", "SPIDER_API_KEY")
|
||||
self.spider = Spider(api_key=api_key)
|
||||
self.url = url
|
||||
self.mode = mode
|
||||
self.params = params
|
||||
|
||||
def lazy_load(self) -> Iterator[Document]:
|
||||
"""Load documents based on the specified mode."""
|
||||
spider_docs = []
|
||||
|
||||
if self.mode == "scrape":
|
||||
# Scrape a single page
|
||||
response = self.spider.scrape_url(self.url, params=self.params)
|
||||
if response:
|
||||
spider_docs.append(response)
|
||||
elif self.mode == "crawl":
|
||||
# Crawl multiple pages
|
||||
response = self.spider.crawl_url(self.url, params=self.params)
|
||||
if response:
|
||||
spider_docs.extend(response)
|
||||
|
||||
for doc in spider_docs:
|
||||
if self.mode == "scrape":
|
||||
# Ensure page_content is also not None
|
||||
page_content = doc[0].get("content", "")
|
||||
|
||||
# Ensure metadata is also not None
|
||||
metadata = doc[0].get("metadata", {})
|
||||
|
||||
yield Document(page_content=page_content, metadata=metadata)
|
||||
if self.mode == "crawl":
|
||||
# Ensure page_content is also not None
|
||||
page_content = doc.get("content", "")
|
||||
|
||||
# Ensure metadata is also not None
|
||||
metadata = doc.get("metadata", {})
|
||||
|
||||
if page_content is not None:
|
||||
yield Document(
|
||||
page_content=page_content,
|
||||
metadata=metadata,
|
||||
)
|
||||
Loading…
Reference in New Issue