Fetch MangaDex Data for LlamaIndex
MangaDex Loader fetches manga metadata from the MangaDex API by title, returning canonical titles, author/artist info, descriptions, tags, and chapter counts
Why it matters
Integrate MangaDex content into your LlamaIndex applications. This asset fetches manga details, descriptions, and metadata directly from the MangaDex API.
Outcomes
What it gets done
Retrieve manga by title from MangaDex.
Extract canonical titles, authors, and artists.
Gather manga descriptions and tags.
Load manga data into LlamaIndex for further processing.
Install
Add it to your toolbox
Run in your project directory:
curl -fsSL https://spark.entire.vc/get/li-reader-readers-mangadex | bash Overview
MangaDex Loader
MangaDex Loader fetches manga information from the MangaDex API using manga titles as search queries. It returns canonical titles along with metadata including author and artist names, descriptions, original language, genre tags, chapter counts in the requested language, and timestamps for the latest chapter publications. Use MangaDex Loader when you need to fetch manga metadata from the MangaDex API by title for use with LlamaIndex.
What it does
MangaDex Loader is a data reader that fetches manga information from the MangaDex API using manga titles as queries. It retrieves manga metadata including canonical titles, author and artist names, descriptions, original language, genre tags, chapter counts, and publication timestamps.
When to use - and when NOT to
Use MangaDex Loader when you need to retrieve manga metadata from the MangaDex API by title. Do NOT use this loader if you need the actual manga chapter content or images - it only fetches metadata.
Inputs and outputs
You provide a list of manga titles and a language code (e.g., "en" for English). The loader queries the MangaDex API and returns documents where the text field contains the canonical manga title. Metadata fields available include: MangaDex manga ID, author's full name, artist's full name, manga description, original language of the source material, genre tags, chapter count in the requested language, and a timestamp for the latest chapter publication.
Integrations
MangaDex Loader is designed to load data into LlamaIndex, the data framework for building LLM applications.
Who it's for
This loader is for users of LlamaIndex who need to fetch manga metadata from the MangaDex API.
Installation and usage
pip install llama-index-readers-mangadex
from llama_index.readers.mangadex import MangaDexReader
loader = MangaDexReader()
documents = loader.load_data(
titles=["manga title 1", "manga title 2"], lang="en"
)
Source README
MangaDex Loader
pip install llama-index-readers-mangadex
This loader fetches information from the MangaDex API, by manga title.
Usage
from llama_index.readers.mangadex import MangaDexReader
loader = MangaDexReader()
documents = loader.load_data(
titles=["manga title 1", "manga title 2"], lang="en"
)
Output
Text
Document text is the manga title. There are alternate titles for many manga, so the canonical title will be returned, even if it is not the title that the user queried with.
Extra Info
| Data | Description |
|---|---|
| id (str) | MangaDex manga id |
| author (str) | Author's full name |
| artist (str) | Artist's full name |
| description (str) | Manga description |
| original_language (str) | The language of the source material (before translation) |
| tags (List[str]) | Describes the manga's genre, e.g. "slice of life" |
| chapter_count (int) | How many chapters exist in the requested language |
| latest_chapter_published_at (str) | Timestamp (YYYY-MM-DDTHH:MM:SS in timezone UTC+0) for the latest chapter in the requested language |
Examples
This loader is designed to be used as a way to load data into LlamaIndex.
FAQ
Common questions
Discussion
Questions & comments · 0
Sign In Sign in to leave a comment.