CodeCow/Scrapegraph-ai
1
0
Fork 0
mirror of https://github.com/VinciGit00/Scrapegraph-ai.git synced 2026-07-04 21:00:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

fix: fixed bug on fetch_node

Browse Source 
Co-Authored-By: Federico Minutoli <40361744+DiTo97@users.noreply.github.com>
This commit is contained in:
Marco Vinciguerra 2024-08-01 13:23:54 +02:00
parent e21d461710
commit 968c69e217
2 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
scrapegraphai/docloaders/browser_base.py
View File

@ -43,6 +43,6 @@ def browser_base_fetch(api_key: str, project_id: str, link: List[str]) -> List[s
browserbase = Browserbase(api_key=api_key, project_id=project_id)
result = browserbase.load([link])
result = browserbase.load(link)
return result

7
scrapegraphai/nodes/fetch_node.py
View File

@ -202,10 +202,11 @@ class FetchNode(BaseNode):
loader_kwargs = self.node_config.get("loader_kwargs", {})
if self.browser_base is not None:
data = browser_base_fetch(self.browser_base.get("api_key"),
self.browser_base.get("project_id"), source)
if self.browser_base is not None:
data = browser_base_fetch(self.browser_base.get("api_key"),
self.browser_base.get("project_id"), [source])
document = [Document(page_content= data, metadata={"source": "html file"})]
document = [Document(page_content=content, metadata={"source": source}) for content in data]
else:
loader = ChromiumLoader([source], headless=self.headless, **loader_kwargs)
document = loader.load()