Fix example notebook if playwright is not installed yet

Author: leopiney

examples/01_basics_notebook.ipynb

@@ -34,7 +34,8 @@
    },
    "outputs": [],
    "source": [
-    "!pip install --upgrade neuralnoise"
+    "!pip install --upgrade neuralnoise\n",
+    "!playwright install --with-deps"
    ]
   },
   {

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "neuralnoise"
-version = "1.3.0"
+version = "1.3.1"
 description = "An AI-powered podcast studio that uses multiple AI agents working together."
 authors = [
     { name = "Leonardo Piñeyro", email = "[email protected]" }

src/neuralnoise/extract.py

@@ -4,10 +4,9 @@
 from pathlib import Path
 from tempfile import NamedTemporaryFile
 from textwrap import dedent
-from typing import AsyncIterator, Iterator
+from typing import AsyncIterator
 
 import requests  # type: ignore
-from crawl4ai import AsyncWebCrawler, CrawlResult
 from langchain_community.document_loaders import (
     BSHTMLLoader,
     PyMuPDFLoader,
@@ -30,6 +29,8 @@ def __init__(
         self.css_selector = css_selector
 
     async def crawl(self, url: str, css_selector: str | None = None):
+        from crawl4ai import AsyncWebCrawler
+
         async with AsyncWebCrawler(verbose=True) as crawler:
             result = await crawler.arun(
                 url,
@@ -38,11 +39,11 @@ async def crawl(self, url: str, css_selector: str | None = None):
 
         return result
 
-    def _process_result(self, result: CrawlResult):
+    def _process_result(self, result):
         if result.markdown is None:
             raise ValueError(f"No valid content found at {self.url}")
 
-        metadata: dict[str, str | None] = {
+        metadata: dict[str, str | None] = {  # type: ignore
             **(result.metadata or {}),
             "source": self.url,
         }