HyperbrowserLoader 集成

pip install -qU langchain-hyperbrowser

from langchain_hyperbrowser import HyperbrowserLoader

loader = HyperbrowserLoader(
    urls="https://example.com",
    api_key="YOUR_API_KEY",
)

docs = loader.load()
docs[0]

Document(metadata={'title': 'Example Domain', 'viewport': 'width=device-width, initial-scale=1', 'sourceURL': 'https://example.com'}, page_content='Example Domain\n\n# Example Domain\n\nThis domain is for use in illustrative examples in documents. You may use this\ndomain in literature without prior coordination or asking for permission.\n\n[More information...](https://www.iana.org/domains/example)')

print(docs[0].metadata)

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

        page = []

loader = HyperbrowserLoader(
    urls="https://hyperbrowser.ai", api_key="YOUR_API_KEY", operation="crawl"
)

loader = HyperbrowserLoader(
    urls="https://example.com",
    api_key="YOUR_API_KEY",
    operation="scrape",
    params={"scrape_options": {"include_tags": ["h1", "h2", "p"]}},
)