Refactor loader classes to accept inputs directly

This commit is contained in:
Alex
2024-02-14 15:17:56 +00:00
parent 030c2a740f
commit 0cb3d12d94
4 changed files with 9 additions and 11 deletions

View File

@@ -10,7 +10,7 @@ class CrawlerLoader(BaseRemote):
self.limit = limit # Set the limit for the number of pages to scrape
def load_data(self, inputs):
url = inputs['data']
url = inputs
# Check if the input is a list and if it is, use the first element
if isinstance(url, list) and url:
url = url[0]

View File

@@ -10,7 +10,7 @@ class SitemapLoader(BaseRemote):
self.limit = limit # Adding limit to control the number of URLs to process
def load_data(self, inputs):
sitemap_url= inputs['data']
sitemap_url= inputs
# Check if the input is a list and if it is, use the first element
if isinstance(sitemap_url, list) and sitemap_url:
url = sitemap_url[0]

View File

@@ -6,7 +6,7 @@ class WebLoader(BaseRemote):
self.loader = WebBaseLoader
def load_data(self, inputs):
urls = inputs['data']
urls = inputs
if isinstance(urls, str):
urls = [urls] # Convert string to list if a single URL is passed