langchain/libs/community/tests/integration_tests/document_loaders/test_rss.py

from pathlib import Path

from langchain_community.document_loaders.rss import RSSFeedLoader


def test_rss_loader() -> None:
    loader = RSSFeedLoader(urls=["https://www.engadget.com/rss.xml"])
    docs = loader.load()

    assert docs[0] is not None
    assert hasattr(docs[0], "page_content")
    assert hasattr(docs[0], "metadata")

    metadata = docs[0].metadata
    assert "feed" in metadata
    assert "title" in metadata
    assert "link" in metadata
    assert "authors" in metadata
    assert "language" in metadata
    assert "description" in metadata
    assert "publish_date" in metadata


def test_rss_loader_with_opml() -> None:
    file_path = Path(__file__).parent.parent / "examples"
    with open(file_path.joinpath("sample_rss_feeds.opml"), "r") as f:
        loader = RSSFeedLoader(opml=f.read())

    docs = loader.load()

    assert docs[0] is not None
    assert hasattr(docs[0], "page_content")
    assert hasattr(docs[0], "metadata")

    metadata = docs[0].metadata
    assert "feed" in metadata
    assert "title" in metadata
    assert "link" in metadata
    assert "authors" in metadata
    assert "language" in metadata
    assert "description" in metadata
    assert "publish_date" in metadata
RSS Feed / OPML loader (#8694) Replace this comment with: - Description: added a document loader for a list of RSS feeds or OPML. It iterates through the list and uses NewsURLLoader to load each article. - Issue: N/A - Dependencies: feedparser, listparser - Tag maintainer: @rlancemartin, @eyurtsev - Twitter handle: @ruze --------- Co-authored-by: Bagatur <baskaryan@gmail.com> 1 year ago			`from pathlib import Path`

community[major], core[patch], langchain[patch], experimental[patch]: Create langchain-community (#14463) Moved the following modules to new package langchain-community in a backwards compatible fashion: ``` mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community ``` Moved the following to core ``` mv langchain/langchain/utils/json_schema.py core/langchain_core/utils mv langchain/langchain/utils/html.py core/langchain_core/utils mv langchain/langchain/utils/strings.py core/langchain_core/utils cat langchain/langchain/utils/env.py >> core/langchain_core/utils/env.py rm langchain/langchain/utils/env.py ``` See .scripts/community_split/script_integrations.sh for all changes 10 months ago			`from langchain_community.document_loaders.rss import RSSFeedLoader`
RSS Feed / OPML loader (#8694) Replace this comment with: - Description: added a document loader for a list of RSS feeds or OPML. It iterates through the list and uses NewsURLLoader to load each article. - Issue: N/A - Dependencies: feedparser, listparser - Tag maintainer: @rlancemartin, @eyurtsev - Twitter handle: @ruze --------- Co-authored-by: Bagatur <baskaryan@gmail.com> 1 year ago

			`def test_rss_loader() -> None:`
			`loader = RSSFeedLoader(urls=["https://www.engadget.com/rss.xml"])`
			`docs = loader.load()`

			`assert docs[0] is not None`
			`assert hasattr(docs[0], "page_content")`
			`assert hasattr(docs[0], "metadata")`

			`metadata = docs[0].metadata`
			`assert "feed" in metadata`
			`assert "title" in metadata`
			`assert "link" in metadata`
			`assert "authors" in metadata`
			`assert "language" in metadata`
			`assert "description" in metadata`
			`assert "publish_date" in metadata`


			`def test_rss_loader_with_opml() -> None:`
			`file_path = Path(__file__).parent.parent / "examples"`
			`with open(file_path.joinpath("sample_rss_feeds.opml"), "r") as f:`
			`loader = RSSFeedLoader(opml=f.read())`

			`docs = loader.load()`

			`assert docs[0] is not None`
			`assert hasattr(docs[0], "page_content")`
			`assert hasattr(docs[0], "metadata")`

			`metadata = docs[0].metadata`
			`assert "feed" in metadata`
			`assert "title" in metadata`
			`assert "link" in metadata`
			`assert "authors" in metadata`
			`assert "language" in metadata`
			`assert "description" in metadata`
			`assert "publish_date" in metadata`