bookmark links extract

bookmarks.py

import re

# Replace html_content with your HTML content
# This is the HTML format of the exported bookmarks
html_content = """
<DT><H3 ADD_DATE="1664237946" LAST_MODIFIED="1693619091">Portfolio Inspo</H3>
<DL><p>
    <DT><A HREF="https://ddiu.io/" ADD_DATE="1664237973">Diu</A>
    <DT><A HREF="https://www.cnblogs.com/okup" ADD_DATE="1664238125">Gonfei - 博客园</A>
</DL></p>
"""

# Define a regular expression pattern to match "href" attributes
pattern = r'HREF="(.*?)"'

# Find all matches of the pattern in the HTML content
matches = re.findall(pattern, html_content)

# Print the matched text within double quotes
for match in matches:
    print(match)