vodorod/Dorod-Sky
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

⚡️ Speed up function clean_element_before_hashing by 827% (#1890)

Browse Source 
Co-authored-by: codeflash-ai[bot] <148906541+codeflash-ai[bot]@users.noreply.github.com>
This commit is contained in:
Saurabh Misra
2025-03-08 02:14:48 -08:00
committed by GitHub
parent 7abbb4ff03
commit fcc87243c1
1 changed files with 11 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
skyvern/webeye/scraper/scraper.py
View File

@@ -160,16 +160,17 @@ def json_to_html(element: dict, need_skyvern_attrs: bool = True) -> str:
def clean_element_before_hashing(element: dict) -> dict:
element_copy = copy.deepcopy(element)
element_copy.pop("id", None)
element_copy.pop("rect", None)
element_copy.pop("frame_index", None)
if "attributes" in element_copy:
element_copy["attributes"].pop(SKYVERN_ID_ATTR, None)
if "children" in element_copy:
for idx, child in enumerate(element_copy["children"]):
element_copy["children"][idx] = clean_element_before_hashing(child)
return element_copy
def clean_nested(element: dict) -> dict:
element_cleaned = {key: value for key, value in element.items() if key not in {"id", "rect", "frame_index"}}
if "attributes" in element:
attributes_cleaned = {key: value for key, value in element["attributes"].items() if key != SKYVERN_ID_ATTR}
element_cleaned["attributes"] = attributes_cleaned
if "children" in element:
children_cleaned = [clean_nested(child) for child in element["children"]]
element_cleaned["children"] = children_cleaned
return element_cleaned
return clean_nested(element)
def hash_element(element: dict) -> str: