Last active
September 9, 2023 02:27
-
-
Save maxdemaio/7c3bbeea75df9eed01ba74768c8676e2 to your computer and use it in GitHub Desktop.
bookmark links extract
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment