LlamaIndex Readers Web

0.6.0 verified Fri May 01 auth: no python

A collection of web-based data readers for LlamaIndex, enabling ingestion from URLs, web pages, and online documents. Currently at version 0.6.0, released under the LlamaIndex ecosystem. Release cadence is irregular, tied to LlamaIndex updates.

pip install llama-index-readers-web

Common errors

error ModuleNotFoundError: No module named 'llama_index.readers.web' ↓

cause Older version of llama-index-readers-web or incorrect import path.

fix

Upgrade to latest version (>=0.10.0) and use correct import: from llama_index.readers.web import ...

error ImportError: cannot import name 'SimpleWebPageReader' from 'llama_index' ↓

cause Using old top-level import path from before v0.10.

fix

Change import to: from llama_index.readers.web import SimpleWebPageReader

error ValueError: You must provide at least one URL. ↓

cause Called load_data() with an empty list or no urls parameter.

fix

Pass a non-empty list of URL strings: reader.load_data(urls=['https://example.com'])

Warnings

breaking Import paths changed in v0.10+. Readers are now under llama_index.readers.web, not top-level llama_index.web. ↓

fix Use 'from llama_index.readers.web import ...' instead of 'from llama_index import ...'.

deprecated SimpleWebPageReader requires requests and beautifulsoup4 as dependencies; they are not installed by default. ↓

fix Install extra dependencies: pip install llama-index-readers-web[beautifulsoup4] or pip install beautifulsoup4 requests.

gotcha Some readers (e.g., BeautifulSoupWebReader) require additional dependencies like lxml for certain parsers. ↓

fix Install lxml if you encounter parser errors: pip install lxml.

Imports

BeautifulSoupWebReader

wrong

from llama_index.readers.web.BeautifulSoupWebReader import BeautifulSoupWebReader

correct

from llama_index.readers.web import BeautifulSoupWebReader

Wrong nesting; correct is direct import from web module.

SimpleWebPageReader

wrong

from llama_index.web import SimpleWebPageReader

correct

from llama_index.readers.web import SimpleWebPageReader

Old top-level import path removed in recent versions.

TrafilaturaWebReader

from llama_index.readers.web import TrafilaturaWebReader

Correct import path.

Quickstart

Load a web page into a Document object using SimpleWebPageReader.

from llama_index.readers.web import SimpleWebPageReader

reader = SimpleWebPageReader()
docs = reader.load_data(urls=["https://example.com"])
print(docs[0].text[:100])