langchain_community.document_loaders.open_city_data

from typing import Iterator

from langchain_core.documents import Document

from langchain_community.document_loaders.base import BaseLoader


[docs]class OpenCityDataLoader(BaseLoader):
    """从`开放城市`加载。"""

[docs]    def __init__(self, city_id: str, dataset_id: str, limit: int):
        """初始化数据集ID。
示例：https://dev.socrata.com/foundry/data.sfgov.org/vw6y-z8j6
例如，city_id = data.sfgov.org
例如，dataset_id = vw6y-z8j6

参数：
    city_id：开放城市的城市标识符。
    dataset_id：开放城市的数据集标识符。
    limit：要加载的文档的最大数量。
"""
        self.city_id = city_id
        self.dataset_id = dataset_id
        self.limit = limit

[docs]    def lazy_load(self) -> Iterator[Document]:
        """延迟加载记录。"""

        from sodapy import Socrata

        client = Socrata(self.city_id, None)
        results = client.get(self.dataset_id, limit=self.limit)
        for record in results:
            yield Document(
                page_content=str(record),
                metadata={
                    "source": self.city_id + "_" + self.dataset_id,
                },
            )
Source code for langchain_community.document_loaders.open_city_data
