podcast_llm.extractors.pdf

PDF file extraction module.

This module provides functionality for extracting text content from PDF files using LangChain’s PyPDFLoader. It handles loading PDFs, extracting text from each page, and combining the content into a single document.

The module includes: - PDFSourceDocument class for handling PDF file extraction - Page-by-page text extraction - Combining pages with appropriate spacing - Conversion to LangChain Document format

Example

>>> from podcast_llm.extractors.pdf import PDFSourceDocument
>>> extractor = PDFSourceDocument('document.pdf')
>>> extractor.extract()
>>> print(extractor.content)
'Text content from PDF pages...'

The extraction process: 1. Loads the PDF using PyPDFLoader 2. Extracts text from each page 3. Combines pages with double newlines between them 4. Returns the complete text content

The module integrates with the BaseSourceDocument interface to provide consistent handling of PDF files alongside other source types like audio and web content.

class podcast_llm.extractors.pdf.PDFSourceDocument(source: str)[source]

Bases: BaseSourceDocument

A document extractor for PDF files.

This class handles extracting text content from PDF files using the PyPDFLoader from LangChain. It loads the PDF, extracts text from each page, and combines them into a single document with page breaks.

src

Path to the source PDF file

Type:: str

src_type

Type of source document (‘PDF File’)

Type:: str

title

Title combining source type and filename

Type:: str

content

Extracted text content after processing

Type:: Optional[str]

Example

>>> extractor = PDFSourceDocument('document.pdf')
>>> extractor.extract()
>>> print(extractor.content)
'Text content from PDF pages...'

extract() → str[source]

Extract text content from the PDF file.

Returns:: The extracted text content as a string