Chrome tabs to JSON structure

estabs.py

# -*- coding: utf-8 -*-
#!/usr/bin/env python

import hashlib
import json
import re
import subprocess
import sys
from time import gmtime, strftime

import lxml
from lxml.html.clean import Cleaner

TAB_ID_REGEX = re.compile('\[[0-9]+:([0-9]+)\]')

def run_command(command):
    return subprocess.check_output(command).strip('\n')

try:
    CHROME_CLI = run_command(['which', 'chrome-cli'])
except:
    print "No exec for chrome-cli was found. Please install."
    sys.exit(1)

class Chrome(object):
    def __init__(self, bin):
        self.bin = bin

    def list(self, element='tabs'):
        return self._run(['list', element])

    def tab_ids(self):
        tabs = self.tabs_list()
        tab_ids = []
        for tab in tabs:
            tab_id_match = TAB_ID_REGEX.match(tab)
            if tab_id_match == None:
                continue

            tab_id = tab_id_match.group(1)
            tab_ids.append(tab_id)

        return tab_ids

    def tab_info(self, tab_id):
        return self._run(['info', '-t', tab_id])

    def tabs_list(self):
        tabs_list = self.list('tabs')
        return tabs_list.split('\n')

    def _run(self, command):
        full_command = [self.bin] + command
        return subprocess.check_output(full_command).strip('\n')

class TabInfo(object):
    def __init__(self, tab_id, chrome):
        self.chrome = chrome
        self.tab_id = tab_id

    def data(self):
        return chrome.tab_info(self.tab_id)

    def id(self):
        pass

    def loading(self):
        pass

    def title(self):
        return self._parsed_row(self.data().split('\n')[1].replace('Title: ', '').decode('utf-8'))

    def url(self):
        pass

    def _parsed_row(self, row_index, replace):
        return self.data().split('\n')[row_index].replace(replace, '').decode('utf-8')


class Tab(object):
    def __init__(self, id, chrome):
        self.chrome = chrome
        self.id = id

    def info(self):
        return TabInfo(id, chrome)

chrome = Chrome(CHROME_CLI)

tabs = chrome.tabs_list()

for tab in tabs:
    tab_id_match = TAB_ID_REGEX.match(tab)
    if tab_id_match == None:
        continue
    else:
        tab_id   = tab_id_match.group(1)
        tab_info = run_command([CHROME_CLI, 'info', '-t', tab_id])

        tab_record = {}
        tab_record['title'] = tab_info.split('\n')[1].replace('Title: ', '').decode('utf-8')
        tab_record['url'] = tab_info.split('\n')[2].replace('Url: ', '')
        tab_record['id']  = hashlib.md5(tab_record['url']).hexdigest()
        tab_record['updated_at'] = strftime("%Y-%m-%d %H:%M:%S", gmtime())

        tab_source = run_command([CHROME_CLI, 'source', '-t', tab_id])

        cleaner = Cleaner()
        cleaner.page_structure = False
        cleaner.javascript = True # This is True because we want to activate the javascript filter
        cleaner.style = True      # This is True because we want to activate the styles & stylesheet filter
        cleaner.remove_tags = ['div', 'h3', 'span', 'table', 'th', 'tr', 'td', 'ul', 'li', 'section', 'footer', 'hr', 'br', 'p', 'img', 'dd', 'dl', 'dt']

        tab_record['source'] = lxml.html.tostring(cleaner.clean_html(lxml.html.fromstri
                                                                     ng(tab_source)))

This code may or may not work, I can't remember how I left it.