Skip to content

Commit dd29c16

Browse files
committed
Merge branch 'deepScrape' of github.com:mayurdb/Scrapegraph-ai into deepScrape
2 parents 9a67a26 + ea3b545 commit dd29c16

File tree

1 file changed

+2
-2
lines changed

1 file changed

+2
-2
lines changed

scrapegraphai/utils/cleanup_html.py

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -5,6 +5,7 @@
55
from minify_html import minify
66
from urllib.parse import urljoin
77

8+
89
def cleanup_html(html_content: str, base_url: str) -> str:
910
"""
1011
Processes HTML content by removing unnecessary tags, minifying the HTML, and extracting the title and body content.
@@ -47,5 +48,4 @@ def cleanup_html(html_content: str, base_url: str) -> str:
4748
minimized_body = minify(str(body_content))
4849
return "Title: " + title + ", Body: " + minimized_body + ", Links: " + str(link_urls)
4950

50-
51-
return "Title: " + title + ", Body: No body content found" + ", Links: " + str(link_urls)
51+
return "Title: " + title + ", Body: No body content found" + ", Links: " + str(link_urls)

0 commit comments

Comments
 (0)