langchain_community.document_loaders.async_html
.AsyncHtmlLoader¶
- class langchain_community.document_loaders.async_html.AsyncHtmlLoader(web_path: Union[str, List[str]], header_template: Optional[dict] = None, verify_ssl: Optional[bool] = True, proxies: Optional[dict] = None, autoset_encoding: bool = True, encoding: Optional[str] = None, default_parser: str = 'html.parser', requests_per_second: int = 2, requests_kwargs: Optional[Dict[str, Any]] = None, raise_for_status: bool = False, ignore_load_errors: bool = False, *, preserve_order: bool = True)[source]¶
异步加载`HTML`。
使用网页路径进行初始化。
Methods
__init__
(web_path[, header_template, ...])使用网页路径进行初始化。
从web_path中的url(s)中延迟加载文本。
aload
()将数据加载到文档对象中。
fetch_all
(urls)以限制速率并发获取所有URL。
从web_path中的url(s)中延迟加载文本。
load
()将数据加载到文档对象中。
load_and_split
([text_splitter])加载文档并分割成块。块作为文档返回。
- Parameters
web_path (Union[str, List[str]]) –
header_template (Optional[dict]) –
verify_ssl (Optional[bool]) –
proxies (Optional[dict]) –
autoset_encoding (bool) –
encoding (Optional[str]) –
default_parser (str) –
requests_per_second (int) –
requests_kwargs (Optional[Dict[str, Any]]) –
raise_for_status (bool) –
ignore_load_errors (bool) –
preserve_order (bool) –
- __init__(web_path: Union[str, List[str]], header_template: Optional[dict] = None, verify_ssl: Optional[bool] = True, proxies: Optional[dict] = None, autoset_encoding: bool = True, encoding: Optional[str] = None, default_parser: str = 'html.parser', requests_per_second: int = 2, requests_kwargs: Optional[Dict[str, Any]] = None, raise_for_status: bool = False, ignore_load_errors: bool = False, *, preserve_order: bool = True)[source]¶
使用网页路径进行初始化。
- Parameters
web_path (Union[str, List[str]]) –
header_template (Optional[dict]) –
verify_ssl (Optional[bool]) –
proxies (Optional[dict]) –
autoset_encoding (bool) –
encoding (Optional[str]) –
default_parser (str) –
requests_per_second (int) –
requests_kwargs (Optional[Dict[str, Any]]) –
raise_for_status (bool) –
ignore_load_errors (bool) –
preserve_order (bool) –
- async alazy_load() AsyncIterator[Document] [source]¶
从web_path中的url(s)中延迟加载文本。
- Return type
AsyncIterator[Document]
- async fetch_all(urls: List[str]) List[str] [source]¶
以限制速率并发获取所有URL。
- Parameters
urls (List[str]) –
- Return type
List[str]
- load_and_split(text_splitter: Optional[TextSplitter] = None) List[Document] ¶
加载文档并分割成块。块作为文档返回。
不要覆盖此方法。应该被视为已弃用!
- 参数:
- text_splitter: 用于分割文档的TextSplitter实例。
默认为RecursiveCharacterTextSplitter。
- 返回:
文档列表。
- Parameters
text_splitter (Optional[TextSplitter]) –
- Return type
List[Document]