Skip to content

Commit dc91719

Browse files
committed
Update cleanup_html.py
1 parent b752499 commit dc91719

File tree

1 file changed

+2
-4
lines changed

1 file changed

+2
-4
lines changed

scrapegraphai/utils/cleanup_html.py

Lines changed: 2 additions & 4 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.
@@ -45,9 +46,6 @@ def cleanup_html(html_content: str, base_url: str) -> str:
4546
if body_content:
4647
# Minify the HTML within the body tag
4748
minimized_body = minify(str(body_content))
48-
print("Came here")
4949
return "Title: " + title + ", Body: " + minimized_body + ", Links: " + str(link_urls)
5050

51-
52-
print("No Came here")
53-
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)