跳到内容

PDF 表格

基类: BaseReader

PDF 表格阅读器。从 PDF 读取表格。

参数

名称

类型 描述 默认值 row_separator
str 用于连接 DataFrame 行的行分隔符。

'\n'

 col_separator
用于连接 DataFrame 列的列分隔符。 用于连接 DataFrame 行的行分隔符。

源码位于 llama-index-integrations/readers/llama-index-readers-pdf-table/llama_index/readers/pdf_table/base.py

 ', '
load_data # 
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
61
62
63
64
65
66
67
class PDFTableReader(BaseReader):
    """
    PDF Table Reader. Reads table from PDF.

    Args:
        row_separator (str): Row separator used to join rows of a DataFrame.
        col_separator (str): Col separator used to join columns of a DataFrame.

    """

    def __init__(
        self,
        *args: Any,
        row_separator: str = "\n",
        col_separator: str = ", ",
        **kwargs: Any
    ) -> None:
        super().__init__(*args, **kwargs)
        self._row_separator = row_separator
        self._col_separator = col_separator

    def load_data(
        self, file: Path, pages: str = "1", extra_info: Optional[Dict] = None
    ) -> List[Document]:
        """
        Load data and extract table from PDF file.

        Args:
            file (Path): Path for the PDF file.
            pages (str): Pages to read tables from.
            extra_info (Optional[Dict]): Extra information.

        Returns:
            List[Document]: List of documents.

        """
        import camelot

        results = []
        tables = camelot.read_pdf(filepath=str(file), pages=pages)

        for table in tables:
            document = self._dataframe_to_document(df=table.df, extra_info=extra_info)
            results.append(document)

        return results

    def _dataframe_to_document(
        self, df: pd.DataFrame, extra_info: Optional[Dict] = None
    ) -> Document:
        df_list = df.apply(
            lambda row: (self._col_separator).join(row.astype(str).tolist()), axis=1
        ).tolist()

        return Document(
            text=self._row_separator.join(df_list), extra_info=extra_info or {}
        )

加载数据并从 PDF 文件中提取表格。

load_data(file: Path, pages: str = '1', extra_info: Optional[Dict] = None) -> List[Document]

file

名称

类型 描述 默认值 row_separator
Path PDF 文件路径。

必需

 pages
从中读取表格的页码。 用于连接 DataFrame 行的行分隔符。

extra_info

 '1'
可选[Dict] 额外信息。

返回值

 工作流运行检查点

List[Document]

描述 默认值
List[Document]: 文档列表。

回到顶部
load_data # 
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
def load_data(
    self, file: Path, pages: str = "1", extra_info: Optional[Dict] = None
) -> List[Document]:
    """
    Load data and extract table from PDF file.

    Args:
        file (Path): Path for the PDF file.
        pages (str): Pages to read tables from.
        extra_info (Optional[Dict]): Extra information.

    Returns:
        List[Document]: List of documents.

    """
    import camelot

    results = []
    tables = camelot.read_pdf(filepath=str(file), pages=pages)

    for table in tables:
        document = self._dataframe_to_document(df=table.df, extra_info=extra_info)
        results.append(document)

    return results