SitemapLoader 集成

os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")
os.environ["LANGSMITH_TRACING"] = "true"

pip install -qU langchain-community

import nest_asyncio

nest_asyncio.apply()

from langchain_community.document_loaders.sitemap import SitemapLoader

sitemap_loader = SitemapLoader(web_path="https://api.python.langchain.com/sitemap.xml")

docs = sitemap_loader.load()
docs[0]

Fetching pages: 100%|##########| 28/28 [00:04<00:00,  6.83it/s]

Document(metadata={'source': 'https://api.python.langchain.com/en/stable/', 'loc': 'https://api.python.langchain.com/en/stable/', 'lastmod': '2024-05-15T00:29:42.163001+00:00', 'changefreq': 'weekly', 'priority': '1'}, page_content='\n\n\n\n\n\n\n\n\n\nLangChain Python API Reference Documentation.\n\n\nYou will be automatically redirected to the new location of this page.\n\n')

print(docs[0].metadata)

{'source': 'https://api.python.langchain.com/en/stable/', 'loc': 'https://api.python.langchain.com/en/stable/', 'lastmod': '2024-05-15T00:29:42.163001+00:00', 'changefreq': 'weekly', 'priority': '1'}

sitemap_loader.requests_per_second = 2
# 可选：避免 `[SSL: CERTIFICATE_VERIFY_FAILED]` 问题
sitemap_loader.requests_kwargs = {"verify": False}

page = []
for doc in sitemap_loader.lazy_load():
    page.append(doc)
    if len(page) >= 10:
        # 执行一些分页操作，例如
        # index.upsert(page)

        page = []

Fetching pages: 100%|##########| 28/28 [00:01<00:00, 19.06it/s]

loader = SitemapLoader(
    web_path="https://api.python.langchain.com/sitemap.xml",
    filter_urls=["https://api.python.langchain.com/en/latest"],
)
documents = loader.load()

documents[0]

Document(page_content='\n\n\n\n\n\n\n\n\n\nLangChain Python API Reference Documentation.\n\n\nYou will be automatically redirected to the new location of this page.\n\n', metadata={'source': 'https://api.python.langchain.com/en/latest/', 'loc': 'https://api.python.langchain.com/en/latest/', 'lastmod': '2024-02-12T05:26:10.971077+00:00', 'changefreq': 'daily', 'priority': '0.9'})

pip install beautifulsoup4

from bs4 import BeautifulSoup


def remove_nav_and_header_elements(content: BeautifulSoup) -> str:
    # 在 BeautifulSoup 对象中查找所有 'nav' 和 'header' 元素
    nav_elements = content.find_all("nav")
    header_elements = content.find_all("header")

    # 从 BeautifulSoup 对象中移除每个 'nav' 和 'header' 元素
    for element in nav_elements + header_elements:
        element.decompose()

    return str(content.get_text())

loader = SitemapLoader(
    "https://api.python.langchain.com/sitemap.xml",
    filter_urls=["https://api.python.langchain.com/en/latest/"],
    parsing_function=remove_nav_and_header_elements,
)

sitemap_loader = SitemapLoader(web_path="example_data/sitemap.xml", is_local=True)

docs = sitemap_loader.load()