CodeCow/Scrapegraph-ai
1
0
Fork 0
mirror of https://github.com/VinciGit00/Scrapegraph-ai.git synced 2026-07-18 21:00:31 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

feat: update parse node

Browse Source
This commit is contained in:
Marco Vinciguerra 2025-02-25 12:09:58 +01:00
parent 2c0b4591ae
commit 8cf96857a0
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
scrapegraphai/nodes/parse_node.py
View File

@ -78,7 +78,6 @@ class ParseNode(BaseNode):
self.logger.info(f"--- Executing {self.node_name} Node ---") self.logger.info(f"--- Executing {self.node_name} Node ---")
input_keys = self.get_input_keys(state) input_keys = self.get_input_keys(state)
input_data = [state[key] for key in input_keys] input_data = [state[key] for key in input_keys]
docs_transformed = input_data[0] docs_transformed = input_data[0]
source = input_data[1] if self.parse_urls else None source = input_data[1] if self.parse_urls else None
@ -121,6 +120,9 @@ class ParseNode(BaseNode):
) )
state.update({self.output[0]: chunks}) state.update({self.output[0]: chunks})
state.update({"parsed_doc": chunks})
state.update({"content": chunks})
if self.parse_urls: if self.parse_urls:
state.update({self.output[1]: link_urls}) state.update({self.output[1]: link_urls})
state.update({self.output[2]: img_urls}) state.update({self.output[2]: img_urls})