Created
January 27, 2012 19:11
-
-
Save jayrambhia/1690395 to your computer and use it in GitHub Desktop.
Extract bookmarks (from html file) from the browser
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
""" | |
@author: jay | |
""" | |
from BeautifulSoup import BeautifulSoup | |
import gdbm | |
import pickle | |
import time | |
def main(): | |
f = open('bookmarks.html','r') | |
soup = BeautifulSoup(f.read()) | |
f.close() | |
dt=[] | |
for d in soup.findAll('dt'): | |
dt.append(d) | |
f = gdbm.open('bookmark','c') | |
for i in range(len(dt)): | |
if dt[i].contents[0].has_key('href') and dt[i].contents[0].has_key('add_date'): | |
uri = dt[i].contents[0]['href'] | |
title = dt[i].contents[0].contents[0] | |
add_date = time.ctime(int(dt[i].contents[0]['add_date'])) | |
last_modified = time.ctime(int(dt[i].contents[0]['last_modified'])) | |
f[uri] = pickle.dumps((str(title), add_date, last_modified)) | |
f.close() | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Go to Bookmarks in your browser. Open Show All Bookmarks. Import and Backup > Export Bookmark to HTML > Save the file and feed it to the script.