ayrisdev/crawl4ai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs(extraction): add clarifying comments for CSS selector behavior

Browse Source 
Add explanatory comments to JsonCssExtractionStrategy._get_elements() method to clarify that it returns all matching elements using select() instead of select_one(). This helps developers understand the method's behavior and its difference from single element selection.

Removed trailing whitespace at end of file.
This commit is contained in:
UncleCode
2025-01-05 19:39:15 +08:00
parent 72fbdac467
commit ae376f15fb
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
crawl4ai/extraction_strategy.py
View File

@@ -974,6 +974,8 @@ class JsonCssExtractionStrategy(JsonElementExtractionStrategy):
return parsed_html.select(selector) return parsed_html.select(selector)
def _get_elements(self, element, selector: str): def _get_elements(self, element, selector: str):
# Return all matching elements using select() instead of select_one()
# This ensures that we get all elements that match the selector, not just the first one
return element.select(selector) return element.select(selector)
def _get_element_text(self, element) -> str: def _get_element_text(self, element) -> str:
@@ -1048,5 +1050,3 @@ class JsonXPathExtractionStrategy(JsonElementExtractionStrategy):
def _get_element_attribute(self, element, attribute: str): def _get_element_attribute(self, element, attribute: str):
return element.get(attribute) return element.get(attribute)