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

fix: address the PR review: https://github.com/unclecode/crawl4ai/pull/899#discussion_r2024639193

Browse Source
This commit is contained in:
Aravind Karnam
2025-04-03 13:47:13 +05:30
parent 9e16a4bb26
commit 73fda8a6ec
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
crawl4ai/content_scraping_strategy.py
View File

@@ -905,7 +905,7 @@ class WebScrapingStrategy(ContentScrapingStrategy):
# Creating a fresh parse of HTML for each selector to prevent element extraction # Creating a fresh parse of HTML for each selector to prevent element extraction
# from modifying the original DOM tree; this keeps the original body # from modifying the original DOM tree; this keeps the original body
# intact for link processing. This is better performant than deepcopy. # intact for link processing. This is better performant than deepcopy.
fresh_body = BeautifulSoup(html, "html.parser") fresh_body = BeautifulSoup(html, "lxml")
for_content_targeted_element.extend(fresh_body.select(target_element)) for_content_targeted_element.extend(fresh_body.select(target_element))
content_element = soup.new_tag("div") content_element = soup.new_tag("div")
for el in for_content_targeted_element: for el in for_content_targeted_element: