Das deutsche Python-Forum

Code: Alles auswählen

grep -E "png|jpg|gif" skype_links.txt > image_list.txt

Code: Alles auswählen

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

from __future__ import print_function
import codecs, sqlite3, re

# replace with the path to main.db, the database containing your skype history
HISTORY_FILE = "/Users/username/Library/Application Support/Skype/username/main.db"
OUTPUT_FILE = "skype_links.txt"
SQL_STATEMENT = "SELECT body_xml FROM Messages"
PATTERN = re.compile("<a href=\"(?P<url>.*?)\">(?P<text>.*?)</a>")

def main():
    links = set() # if you use a set instead of a list you don't need to remove duplicates
    connection = sqlite3.connect(HISTORY_FILE)
    c = connection.cursor()
    
    for message in c.execute(SQL_STATEMENT):
        # for some reason simply selecting the message body doesn't suffice
        # so I check whether the first element of it exists at all
        if message[0]:
            # I need to use a loop because I don't know how many URLs the message contains
            for match in re.finditer(PATTERN, message[0]):
                links.add(match.group("url"))

    # this is needed to make sure it works with python 2.x and 3.x
    with codecs.open(OUTPUT_FILE, "w", "utf-8") as output_file:
        output_file.write("\n".join(sorted(links)))
    print("{} links were written".format(len(links)))

if __name__ == "__main__":
    main()

Code: Alles auswählen

#! /usr/bin/env python
# -*- coding: utf-8 -*-
from __future__ import print_function

import codecs
import sqlite3

from lxml import etree

# 
# Replace with the path to main.db, the database containing your skype history.
# 
HISTORY_FILENAME = (
    '/Users/username/Library/Application Support/Skype/username/main.db'
)
OUTPUT_FILENAME = 'skype_links.txt'
SQL_STATEMENT = 'SELECT body_xml FROM Messages WHERE body_xml IS NOT NULL'


def main():
    links = set()
    connection = sqlite3.connect(HISTORY_FILE)
    cursor = connection.cursor()
    for message, in cursor.execute(SQL_STATEMENT):
        links.update(etree.fromstring(message).xpath('//a/@href'))
    connection.close()
    
    with codecs.open(OUTPUT_FILE, 'w', 'utf-8') as output_file:
        output_file.write('\n'.join(sorted(links)))
    print('{0} links were written'.format(len(links)))


if __name__ == "__main__":
    main()

Code: Alles auswählen

>>> from xml.etree.ElementTree import ElementTree
>>> tree = ElementTree()
>>> tree.parse("index.xhtml")
<Element 'html' at 0xb77e6fac>
>>> p = tree.find("body/p")     # Finds first occurrence of tag p in body
>>> p
<Element 'p' at 0xb77ec26c>
>>> links = list(p.iter("a"))   # Returns list of all links
>>> links
[<Element 'a' at 0xb77ec2ac>, <Element 'a' at 0xb77ec1cc>]
>>> for i in links:             # Iterates through all found links
...     i.attrib["target"] = "blank"
>>> tree.write("output.xhtml")

Code: Alles auswählen

with sqlite3.connect(…) as connection:
    …

Code: Alles auswählen

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

from __future__ import print_function, unicode_literals

import os
import sqlite3
from argparse import ArgumentParser

import lxml.html


DEFAULT_HISTORY = '~/Library/Application Support/Skype/{username}/main.db'
SQL_STATEMENT = 'SELECT body_xml FROM Messages WHERE body_xml IS NOT NULL'


def extract_links_from_message(message):
    fragments = lxml.html.fragments_fromstring(message)
    nodes = (f for f in fragments if not isinstance(f, basestring))
    for node in nodes:
        for link in node.xpath('//a/@href'):
            yield link


def extract_links_from_history(filename):
    with sqlite3.connect(filename) as connection:
        cursor = connection.cursor()
        for message, in cursor.execute(SQL_STATEMENT):
            for link in extract_links_from_message(message):
                yield link


def find_history_file(skype_username):
    return os.path.expanduser(DEFAULT_HISTORY.format(username=skype_username))


def main(argv=None):
    parser = ArgumentParser(description='Extract links from Skype history')
    parser.add_argument('-s', '--sort', help='Sort links alphabetically',
                        action='store_true')
    parser.add_argument('-u', '--unique', help='Print each link only once',
                        action='store_true')
    parser.add_argument('username', help='The Skype username')
    args = parser.parse_args(argv)

    links = extract_links_from_history(find_history_file(args.username))
    if args.unique:
        links = set(links)
    if args.sort:
        links = sorted(links)

    for link in links:
        print(link)


if __name__ == "__main__":
    main()