Skip to main content
Open In ColabOpen on GitHub

递归URL

RecursiveUrlLoader 可让您从根 URL 递归抓取所有子链接，并将其解析为文档。

概览​

集成详情​

类包本地可序列化的JS 支持
RecursiveUrlLoaderlangchain_community✅❌✅

加载器功能​

源文档延迟加载原生异步支持
RecursiveUrlLoader✅❌

设置​

凭据​

使用 RecursiveUrlLoader 无需任何凭据。

安装​

RecursiveUrlLoader 位于 langchain-community 包中。没有其他必需的包，不过如果您也安装了 ``beautifulsoup4`，将获得更丰富的默认文档元数据。

%pip install -qU langchain-community beautifulsoup4 lxml

实例化​

现在我们可以实例化文档加载器对象并加载文档：

from langchain_community.document_loaders import RecursiveUrlLoader

loader = RecursiveUrlLoader(
    "https://docs.python.org/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,
    # ...
)
API 参考：RecursiveUrlLoader

加载​

使用 .load() 将所有文档同步加载到内存中，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，直到达到指定的 max_depth。

让我们通过一个基本示例来了解如何在 Python 3.9 文档 上使用 RecursiveUrlLoader。

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.python.org/3.9/',
 'content_type': 'text/html',
 'title': '3.9.19 Documentation',
 'language': None}

太好了！第一份文档看起来像是我们开始时的根页面。让我们看看下一份文档的元数据

docs[1].metadata
{'source': 'https://docs.python.org/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子页面，这很好！接下来，让我们从元数据转向检查其中一份文档的内容。

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网址 https://docs.python.org/3.9/ 的 HTML，这正是我们所预期的。现在，让我们看看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。

惰性加载​

如果我们正在加载大量文档，且下游操作可以针对已加载文档的子集进行，那么我们可以逐个延迟加载文档，以最小化内存占用：

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")

在此示例中，内存中同时加载的文档数量永远不会超过 10 个。

添加提取器​

默认情况下，加载器会将每个链接的原始 HTML 设置为文档页面内容。若要将此 HTML 解析为更适合人类/大语言模型的格式，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.python.org/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

这样看起来好多了！

您同样可以传入 metadata_extractor 来自定义如何从 HTTP 响应中提取文档元数据。有关更多详情，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的几种方式，但还有许多其他修改可以更好地适应您的用例。使用参数link_regex和exclude_dirs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。

有关配置和调用 RecursiveUrlLoader 的详细信息，请参阅 API 参考：https://python.langchain.com/api_reference/community/document_loaders/langchain_community.document_loaders.recursive_url_loader.RecursiveUrlLoader.html。