跳到内容

维基百科

WikipediaReader #

基础类: BasePydanticReader

维基百科读取器。

读取一个页面。

源代码位于 llama-index-integrations/readers/llama-index-readers-wikipedia/llama_index/readers/wikipedia/base.py 
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
class WikipediaReader(BasePydanticReader):
    """
    Wikipedia reader.

    Reads a page.

    """

    is_remote: bool = True

    def __init__(self) -> None:
        """Initialize with parameters."""
        try:
            import wikipedia  # noqa
        except ImportError:
            raise ImportError(
                "`wikipedia` package not found, please run `pip install wikipedia`"
            )

    @classmethod
    def class_name(cls) -> str:
        return "WikipediaReader"

    def load_data(
        self, pages: List[str], lang_prefix: str = "en", **load_kwargs: Any
    ) -> List[Document]:
        """
        Load data from the input directory.

        Args:
            pages (List[str]): List of pages to read.
            lang_prefix (str): Language prefix for Wikipedia. Defaults to English. Valid Wikipedia language codes
            can be found at https://en.wikipedia.org/wiki/List_of_Wikipedias.

        """
        import wikipedia

        if lang_prefix.lower() != "en":
            if lang_prefix.lower() in wikipedia.languages():
                wikipedia.set_lang(lang_prefix.lower())
            else:
                raise ValueError(
                    f"Language prefix '{lang_prefix}' for Wikipedia is not supported. Check supported languages at https://en.wikipedia.org/wiki/List_of_Wikipedias."
                )

        results = []
        for page in pages:
            wiki_page = wikipedia.page(page, **load_kwargs)
            page_content = wiki_page.content
            page_id = wiki_page.pageid
            results.append(Document(id_=page_id, text=page_content))
        return results

load_data #

load_data(pages: List[str], lang_prefix: str = 'en', **load_kwargs: Any) -> List[Document]

从输入目录加载数据。

参数

名称 类型 描述 默认值
pages List[str]

要读取的页面列表。

 必需
lang_prefix str

维基百科的语言前缀。默认为英语。有效的维基百科语言代码

 'en'
可以 在 https

//en.wikipedia.org/wiki/List_of_Wikipedias 找到。

 必需
源代码位于 llama-index-integrations/readers/llama-index-readers-wikipedia/llama_index/readers/wikipedia/base.py 
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
def load_data(
    self, pages: List[str], lang_prefix: str = "en", **load_kwargs: Any
) -> List[Document]:
    """
    Load data from the input directory.

    Args:
        pages (List[str]): List of pages to read.
        lang_prefix (str): Language prefix for Wikipedia. Defaults to English. Valid Wikipedia language codes
        can be found at https://en.wikipedia.org/wiki/List_of_Wikipedias.

    """
    import wikipedia

    if lang_prefix.lower() != "en":
        if lang_prefix.lower() in wikipedia.languages():
            wikipedia.set_lang(lang_prefix.lower())
        else:
            raise ValueError(
                f"Language prefix '{lang_prefix}' for Wikipedia is not supported. Check supported languages at https://en.wikipedia.org/wiki/List_of_Wikipedias."
            )

    results = []
    for page in pages:
        wiki_page = wikipedia.page(page, **load_kwargs)
        page_content = wiki_page.content
        page_id = wiki_page.pageid
        results.append(Document(id_=page_id, text=page_content))
    return results