递归 URL
RecursiveUrlLoader
允许您递归地抓取根 URL 的所有子链接,并将它们解析为文档。
概述
集成细节
类 | 包 | 本地 | 可序列化 | JS 支持 |
---|---|---|---|---|
RecursiveUrlLoader | langchain_community | ✅ | ❌ | ✅ |
加载器功能
来源 | 文档延迟加载 | 原生异步支持 |
---|---|---|
RecursiveUrlLoader | ✅ | ❌ |
设置
凭据
使用 RecursiveUrlLoader
不需要任何凭据。
安装
RecursiveUrlLoader
位于 langchain-community
包中。没有其他必需的包,但如果您也安装了
,您将获得更丰富的默认文档元数据。beautifulsoup4
%pip install -qU langchain-community beautifulsoup4
实例化
现在我们可以实例化我们的文档加载器对象并加载文档
from langchain_community.document_loaders import RecursiveUrlLoader
loader = RecursiveUrlLoader(
"https://docs.pythonlang.cn/3.9/",
# max_depth=2,
# use_async=False,
# extractor=None,
# metadata_extractor=None,
# exclude_dirs=(),
# timeout=10,
# check_response_status=True,
# continue_on_failure=True,
# prevent_outside=True,
# base_url=None,
# ...
)
加载
使用 .load()
同步加载所有文档到内存中,每个访问的 URL 对应一个文档。从初始 URL 开始,我们递归遍历所有链接的 URL,直到指定的最大深度。
让我们通过一个基本示例来演示如何使用 RecursiveUrlLoader
在 Python 3.9 文档 上。
docs = loader.load()
docs[0].metadata
/Users/bagatur/.pyenv/versions/3.9.1/lib/python3.9/html/parser.py:170: XMLParsedAsHTMLWarning: It looks like you're parsing an XML document using an HTML parser. If this really is an HTML document (maybe it's XHTML?), you can ignore or filter this warning. If it's XML, you should know that using an XML parser will be more reliable. To parse this document as XML, make sure you have the lxml package installed, and pass the keyword argument `features="xml"` into the BeautifulSoup constructor.
k = self.parse_starttag(i)
{'source': 'https://docs.pythonlang.cn/3.9/',
'content_type': 'text/html',
'title': '3.9.19 Documentation',
'language': None}
太好了!第一个文档看起来像我们开始时的根页面。让我们看看下一个文档的元数据
docs[1].metadata
{'source': 'https://docs.pythonlang.cn/3.9/using/index.html',
'content_type': 'text/html',
'title': 'Python Setup and Usage — Python 3.9.19 documentation',
'language': None}
该 URL 看起来是我们根页面的一个子页面,这很好!让我们从元数据转向检查我们其中一个文档的内容
print(docs[0].page_content[:300])
<!DOCTYPE html>
<html xmlns="http://www.w3.org/1999/xhtml">
<head>
<meta charset="utf-8" /><title>3.9.19 Documentation</title><meta name="viewport" content="width=device-width, initial-scale=1.0">
<link rel="stylesheet" href="_static/pydoctheme.css" type="text/css" />
<link rel=
这看起来确实像是来自 URL https://docs.pythonlang.cn/3.9/ 的 HTML,这是我们预期的。现在让我们看看我们可以对基本示例进行的一些变体,这些变体在不同情况下可能会有所帮助。
延迟加载
如果我们正在加载大量文档,并且我们的下游操作可以在所有加载的文档的子集上完成,我们可以延迟加载我们的文档,一次加载一个文档,以最小化我们的内存占用
pages = []
for doc in loader.lazy_load():
pages.append(doc)
if len(pages) >= 10:
# do some paged operation, e.g.
# index.upsert(page)
pages = []
/var/folders/4j/2rz3865x6qg07tx43146py8h0000gn/T/ipykernel_73962/2110507528.py:6: XMLParsedAsHTMLWarning: It looks like you're parsing an XML document using an HTML parser. If this really is an HTML document (maybe it's XHTML?), you can ignore or filter this warning. If it's XML, you should know that using an XML parser will be more reliable. To parse this document as XML, make sure you have the lxml package installed, and pass the keyword argument `features="xml"` into the BeautifulSoup constructor.
soup = BeautifulSoup(html, "lxml")
在这个示例中,我们一次最多只加载 10 个文档到内存中。
添加提取器
默认情况下,加载器将每个链接的原始 HTML 作为文档页面内容。要将此 HTML 解析为更人性化/更适合 LLM 的格式,您可以传入一个自定义的 extractor
方法
import re
from bs4 import BeautifulSoup
def bs4_extractor(html: str) -> str:
soup = BeautifulSoup(html, "lxml")
return re.sub(r"\n\n+", "\n\n", soup.text).strip()
loader = RecursiveUrlLoader("https://docs.pythonlang.cn/3.9/", extractor=bs4_extractor)
docs = loader.load()
print(docs[0].page_content[:200])
/var/folders/td/vzm913rx77x21csd90g63_7c0000gn/T/ipykernel_10935/1083427287.py:6: XMLParsedAsHTMLWarning: It looks like you're parsing an XML document using an HTML parser. If this really is an HTML document (maybe it's XHTML?), you can ignore or filter this warning. If it's XML, you should know that using an XML parser will be more reliable. To parse this document as XML, make sure you have the lxml package installed, and pass the keyword argument `features="xml"` into the BeautifulSoup constructor.
soup = BeautifulSoup(html, "lxml")
/Users/isaachershenson/.pyenv/versions/3.11.9/lib/python3.11/html/parser.py:170: XMLParsedAsHTMLWarning: It looks like you're parsing an XML document using an HTML parser. If this really is an HTML document (maybe it's XHTML?), you can ignore or filter this warning. If it's XML, you should know that using an XML parser will be more reliable. To parse this document as XML, make sure you have the lxml package installed, and pass the keyword argument `features="xml"` into the BeautifulSoup constructor.
k = self.parse_starttag(i)
``````output
3.9.19 Documentation
Download
Download these documents
Docs by version
Python 3.13 (in development)
Python 3.12 (stable)
Python 3.11 (security-fixes)
Python 3.10 (security-fixes)
Python 3.9 (securit
看起来好多了!
您可以类似地传入一个 metadata_extractor
来定制如何从 HTTP 响应中提取文档元数据。有关详细信息,请参阅 API 参考。
API 参考
这些示例仅展示了您可以修改默认 RecursiveUrlLoader
的几种方法,但还有更多修改可以更好地适应您的用例。使用 link_regex
和 exclude_dirs
参数可以帮助您过滤掉不需要的 URL,aload()
和 alazy_load()
可用于异步加载,等等。
有关配置和调用 RecursiveUrlLoader
的详细信息,请参阅 API 参考:https://python.langchain.ac.cn/v0.2/api_reference/community/document_loaders/langchain_community.document_loaders.recursive_url_loader.RecursiveUrlLoader.html。