BookmarkStats – Calculate bookmark stats with Python

Well, once I hit over 4300 bookmarks, I decided it was time to write a script that would get me some bookmark stats (such as folders, number per folder, duplicates, etc.).

When I initially set out, I wanted to figure out what information I could get from a browser HTML export that would be useful (as well as how to display it).

import collections
import cProfile
import re
import requests

from bs4 import BeautifulSoup

# http://www.quesucede.com/page/show/id/python-3-tree-implementation
class Node:
    def __init__(self, identifier, parent=None):
        self.__identifier = identifier
        self.__children = []
        self.__parent = parent

    @property
    def identifier(self):
        return self.__identifier

    @property
    def children(self):
        return self.__children
        
    @property
    def parent(self):
        return self.__parent

    def add_child(self, identifier):
        self.__children.append(identifier)
        
class Tree:
    def __init__(self):
        self.__nodes = {}

    @property
    def nodes(self):
        return self.__nodes

    def add_node(self, identifier, parent=None):
        if parent is not None:
            node = Node(identifier, self.__nodes[parent])
        else:
            node = Node(identifier)
        self[identifier] = node

        if parent is not None:
            self[parent].add_child(identifier)

        return node

    def display(self, identifier, depth=0):
        children = self[identifier].children
        if depth == 0:
            print identifier
        else:
            print "\t" * depth + str(identifier)

        depth += 1
        for child in children:
            self.display(child, depth)  # recursive call

    def traverse(self, identifier, mode="depth"):
        # Python generator. Loosly[sic] based on an algorithm from 
        # 'Essential LISP' by John R. Anderson, Albert T. Corbett, 
        # and Brian J. Reiser, page 239-241
        yield self.__nodes[identifier]
        queue = self[identifier].children
        while queue:
            yield self.__nodes[queue[0]]
            expansion = self[queue[0]].children
            if mode == "depth":
                queue = expansion + queue[1:]  # dfs
            elif mode == "breadth":
                queue = queue[1:] + expansion  # bfs

    def __getitem__(self, key):
        return self.__nodes[key]

    def __setitem__(self, key, item):
        self.__nodes[key] = item


def createSoup(browser):
    with open ("./bookmarks_" + browser + ".html", "r") as myfile:
        html = myfile.read()
    soup = BeautifulSoup(html, 'html.parser')
    return soup

def getChildren(theNode, level):
    children = []
    
    theChildren = theNode.findAll('dl')
    for child in theChildren:
        parents = len(child.findParents('dl'))
        header = child.findPrevious('h3')
        if parents == level + 1:
            children.append(str(''.join(header.findAll(text=True))))
    return children
    
def genHeaderTree(browser, theSoup):
    iterSoup = theSoup.findAll('dl')
    
    if browser == "chrome" or browser == "firefox": 
        headerList = theSoup.findAll('h3')
        iterSoup = iterSoup[1:]
    else:
        headerList = theSoup.findAll(re.compile("h?"))
    
    firstHeader = str(headerList[0].text)
    
    headerTree = Tree()
    headerTree.add_node(firstHeader)
    
    for item in iterSoup:
        parents = len(item.findParents('dl'))
        children = getChildren(item, parents)
        if children:
            for child in children:
                if browser == "chrome" or browser == "firefox":
                    parent = str(item.findPrevious('h3').text)
                else:
                    parent = str(item.findPrevious(re.compile("h?")).text)
                headerTree.add_node(child, parent)
    return headerTree

def printHeaderList(browser, theTree, theSoup, linkList):
    if browser == "chrome" or browser == "firefox": 
        headerList = theSoup.findAll('h3')
    else:
        headerList = theSoup.findAll(re.compile("h?"))    
    
    firstHeader = ''.join(headerList[0].findAll(text=True))
    
    iterTree = theTree.traverse(firstHeader, "depth")
    
    removed = 0    
    if browser == "chrome" or browser == "firefox" or browser == "ie":
        next(iterTree) # Remove "Bookmarks Toolbar" or "Bookmarks"
        removed += 1
        
    for node in iterTree:
        temp = node
        parents = 0
        while temp.parent:
            parents += 1
            temp = temp.parent
        prepend = "\t" * (parents - removed)
        links = getLinks(browser, theSoup, node.identifier)
        count = len(links)
        percentage = "{0:.2f}%".format(((count + 0.0)/len(linkList)) * 100)
        print (prepend + str(node.identifier) + " - " + 
            str(count) + " = " +percentage)

def getLinks(browser, theSoup, header):
    s = None
    # Total time: 2.00404 s - slowest part of the code
    headerNodes = theSoup.findAll('h3')
    for node in headerNodes:
        if node.text == header:
            s = node
            break
    
    while getattr(s, 'name', None) != 'dl':
        if browser == "chrome" or browser == "ie":
            s = s.nextSibling
        elif browser == "firefox":
            s = s.findNext('dl')
    return s.findAll('a')

def populateList(linkList, urlType):
    urlList = []
    
    for link in linkList:
        if urlType == "normal":
            urlList.append(str(link['href']))
        elif urlType == "noProtocol":
            noProtocol = link['href'].split('://', 1)[-1]
            urlList.append(str(noProtocol))
    return urlList

def getDupes(inList):        
    return [item for item, c in collections.Counter(inList).items() if c > 1]
    
def checkStatus(link):
    resp = requests.head(link)
    return resp

def main():
    supportedBrowsers = ["chrome", "firefox", "ie"]
    browser = "chrome"
    
    getCount = True
    checkDupes = True
    checkErrors = False
    
    mySoup = createSoup(browser)
    linkList = mySoup.find_all('a')
    
    # Firefox only fix
    for link in linkList[:]:
        if link['href'].startswith('place'):
            linkList.remove(link)
            
    myTree = genHeaderTree(browser, mySoup)
    
    if getCount:
        total = len(linkList)
        print "Total number of bookmarks: " + str(total) + "\n"

    if checkDupes:    
        if any(browser in s for s in supportedBrowsers):
            printHeaderList(browser, myTree, mySoup, linkList)

            urlList = populateList(linkList, "normal")    
            dupes = getDupes(urlList)
            print "\n\nDUPLICATE LINKS = " + str(len(dupes))
            print "----------------"
            for dupe in dupes:
                print dupe
        
            urlList = populateList(linkList, "noProtocol")    
            dupes = getDupes(urlList)    
            print "\nDUPLICATE LINKS (IGNORING PROTOCOL) = " + str(len(dupes))
            print "------------------------------------"
            for dupe in dupes:
                print dupe
    
    if checkErrors:
        print "\nERROR CONNECTS"
        print "---------------"    
        for link in linkList:
            try:
                response = checkStatus(link['href'])
            except:
                print "ERROR?!"
            if response.status_code != 200:
                print str(response.status_code) + " - " + link['href']
        
if __name__=="__main__":
	main()

The script had to not only my total number of bookmarks, but also how many bookmarks I had in each folder (and sub-folders). This was not in any of the applications or plugins that I could find, but BookmarkStats does just that.

Bookmark Stats - Folders

Additionally, I wanted duplicate checking in the same application, with some wiggle room. For now I have implemented ignoring the protocol (as I had some "dupes" that were normally ignored because they were HTTP vs HTTPS). In the future, I also plan on adding almost duplicates (maybe the URL slightly changed, or it is a similar URL to the same page).

Bookmark Stats - Duplicates

I plan on adding support for more browsers, as well as some visualizations and even timeout checking in the future. That said, even for now this script has helped me drop down to 3508 bookmarks and counting!

As usual, the code and updates can always be found in my GitHub repository as well.

doyler on Githubdoyler on Twitter
doyler
Ray Doyle is an avid pentester/security enthusiast/beer connoisseur who has worked in IT for almost 16 years now. From building machines and the software on them, to breaking into them and tearing it all down; he's done it all. To show for it, he has obtained an OSCE, OSCP, eCPPT, GXPN, eWPT, eWPTX, SLAE, eMAPT, Security+, ICAgile CP, ITIL v3 Foundation, and even a sabermetrics certification!

He currently serves as a Senior Penetration tester for Avalara, and his previous position was a Principal Penetration Testing Consultant for Secureworks.

When he's not figuring out what cert to get next or side project to work on, he enjoys playing video games, traveling, and watching sports.

Leave a Comment

Filed under Security Not Included

Leave a Reply

Your email address will not be published. Required fields are marked *

*

This site uses Akismet to reduce spam. Learn how your comment data is processed.