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

update scraped_page references when it's refreshed (#1151)

Browse Source
This commit is contained in:
Shuchang Zheng
2024-11-06 16:48:58 -08:00
committed by GitHub
parent 5583dee658
commit c531f9bc5d
1 changed files with 13 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
skyvern/webeye/scraper/scraper.py
View File

@@ -242,13 +242,25 @@ class ScrapedPage(BaseModel):
raise UnknownElementTreeFormat(fmt=fmt) raise UnknownElementTreeFormat(fmt=fmt)
async def refresh(self, with_screenshot: bool = True) -> Self: async def refresh(self, with_screenshot: bool = True) -> Self:
return await scrape_website( refreshed_page = await scrape_website(
browser_state=self._browser_state, browser_state=self._browser_state,
url=self.url, url=self.url,
cleanup_element_tree=self._clean_up_func, cleanup_element_tree=self._clean_up_func,
scrape_exclude=self._scrape_exclude, scrape_exclude=self._scrape_exclude,
with_screenshot=with_screenshot, with_screenshot=with_screenshot,
) )
self.elements = refreshed_page.elements
self.id_to_css_dict = refreshed_page.id_to_css_dict
self.id_to_element_dict = refreshed_page.id_to_element_dict
self.id_to_frame_dict = refreshed_page.id_to_frame_dict
self.id_to_element_hash = refreshed_page.id_to_element_hash
self.hash_to_element_ids = refreshed_page.hash_to_element_ids
self.element_tree = refreshed_page.element_tree
self.element_tree_trimmed = refreshed_page.element_tree_trimmed
self.screenshots = refreshed_page.screenshots or self.screenshots
self.html = refreshed_page.html
self.extracted_text = refreshed_page.extracted_text
return self
async def scrape_website( async def scrape_website(