1
0
mirror of https://github.com/gryf/slack-backup.git synced 2025-12-17 19:40:21 +01:00

5 Commits
v0.1 ... v0.3

Author SHA1 Message Date
b5e9c150ed Merge to head 2016-11-26 19:23:03 +01:00
af7f24e9a9 Dropping Python 2 support 2016-11-26 19:13:12 +01:00
11241e9d8b Readme update 2016-11-26 18:40:54 +01:00
c8c1dd4bfe Small fixes, version bump, alpha stage, added emoji map. 2016-11-26 18:03:29 +01:00
c79d8ae0e1 Small fixes, version bump, alpha stage, added emoji map. 2016-11-26 17:57:58 +01:00
10 changed files with 1921 additions and 67 deletions

View File

@@ -1,8 +1,6 @@
language: python
env:
- TOXENV=py27
- TOXENV=py34
- TOXENV=py27-flake8
- TOXENV=py34-flake8
install: pip install tox
script: tox

View File

@@ -4,15 +4,18 @@ Slack backup
.. image:: https://travis-ci.org/gryf/slack-backup.svg?branch=master
:target: https://travis-ci.org/gryf/slack-backup
This simple project which aim is to collect conversations from Slack using its
API and optionally user account information, and provides convenient way to
represent as a log.
.. image:: https://img.shields.io/pypi/v/slack-backup.svg
:target: https://pypi.python.org/pypi/slack-backup
The project aim is to collect conversations from Slack using its API and
optionally user account information, and provides convenient way to represent
as a log.
Requirements
------------
This project is written in Python 2.7, and 3.4+, although version 2.7, which
should work, wasn't tested as extensively as it should be.
This project is written in Python 3, 3.4 to be precise, although it may work on
earlier version of Python3. Sorry no support for Python2.
Other than that, required packages are as follows:
@@ -111,6 +114,33 @@ where:
The rest of the options (``-d`` and ``-v``) have same meaning as in ``fetch``
command.
See help for the ``slack-backup`` command for complete list of options.
Details
-------
During first run, database with provided name is generated. For ease of use
sqlite database is used, although it is easy to switch the engine, since there
is an ORM (SQLAlchemy) used.
Slack users, channels and messages are mapped to SQLAlchemy models, as well as
other information, like:
- user profiles
- channel topic
- channel purpose
- message reactions
- message attachments
- and files
Channels and users are always synchronized in every run, so every modification
to the user or channels are overwriting old data. During first run, all messages
are retrieved for all/selected channels. Every other run will only fetch those
messages, which are older then newest message in the database - so that we don't
loose any old messages, which might be automatically removed from Slack servers.
The drawback of this behaviour is that all past messages which was altered in
the meantime will not be updated.
License
-------

View File

@@ -2,12 +2,15 @@
"""
Setup for the slack-backup project
"""
from distutils.core import setup
try:
from setuptools import setup
except ImportError:
from distutils.core import setup
setup(name="slack-backup",
packages=["slack_backup"],
version="0.1",
version="0.3",
description="Make copy of slack converstaions",
author="Roman Dobosz",
author_email="gryf73@gmail.com",
@@ -18,7 +21,7 @@ setup(name="slack-backup",
scripts=["scripts/slack-backup"],
classifiers=["Programming Language :: Python :: 3",
"Programming Language :: Python :: 3.4",
"Development Status :: 2 - Pre-Alpha",
"Development Status :: 3 - Alpha",
"Environment :: Console",
"Intended Audience :: End Users/Desktop",
"License :: OSI Approved :: BSD License",

View File

@@ -146,10 +146,17 @@ class Client(object):
Create message with corresponding possible metadata, like reactions,
files etc.
"""
message = o.Message(data)
message.user = self.q(o.User).\
user = self.q(o.User).\
filter(o.User.slackid == data['user']).one()
if data['type'] == 'message' and not data['text'].strip():
logging.info("Skipping message from `%s' since it's empty",
user.name)
return
message = o.Message(data)
message.channel = channel
message.user = user
if data.get('is_starred'):
message.is_starred = True

View File

@@ -78,7 +78,7 @@ class Download(object):
path = os.path.join(path, fname)
count = 1
while os.path.exists(path):
while filetype != 'avatar' and os.path.exists(path):
base, ext = os.path.splitext(path)
path = base + "%0.3d" % count + ext

1821
slack_backup/emoji.py Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -1,18 +1,18 @@
# -*- coding: utf-8 -*-
"""
Reporters module.
There are several classes for specific format reporting, and also some of the
slack conversation/convention parsers.
"""
from __future__ import absolute_import, division, print_function
import os
import errno
import html.parser
import logging
import re
from slack_backup import objects as o
from slack_backup import utils
from slack_backup import emoji
class Reporter(object):
@@ -40,16 +40,18 @@ class Reporter(object):
'file': 'đź“‚',
'topic': 'đźź…',
'separator': '│'}}
self.emoji = emoji.EMOJI.get(args.theme, {})
self.channels = self._get_channels(args.channels)
self.users = self.q(o.User).all()
self._re_first_idnick = re.compile(r'^(?P<replace>'
r'<@(?P<slackid>U[A-Z,0-9]+)\|.+>)')
self._re_first_id = re.compile('^(?P<replace>'
'<@(?P<slackid>U[A-Z,0-9]+)>)')
self._re_idnick = re.compile(r'.*(?P<replace>'
r'<@(?P<slackid>U[A-Z,0-9]+)\|.+>)')
self._re_id = re.compile('.*(?P<replace><@(?P<slackid>U[A-Z,0-9]+)>)')
self._slackid_pat = [re.compile(r'^(?P<replace>'
r'<@(?P<slackid>U[A-Z,0-9]+)\|.+>)'),
re.compile('^(?P<replace>'
'<@(?P<slackid>U[A-Z,0-9]+)>)'),
re.compile(r'.*(?P<replace>'
r'<@(?P<slackid>U[A-Z,0-9]+)\|.+>)'),
re.compile('.*(?P<replace><@(?P<slackid>'
'U[A-Z,0-9]+)>)')]
def generate(self):
"""Generate raport it's a dummmy one - for use with none reporter"""
@@ -154,11 +156,9 @@ class TextReporter(Reporter):
"""
msg_txt = self._filter_slackid(msg.text)
msg_txt = self._fix_newlines(msg_txt)
for emoticon in self.emoji:
msg_txt = msg_txt.replace(emoticon, self.emoji[emoticon])
formatter = self.types.get(msg.type, self._msg)
if not msg_txt.strip():
logging.info("Skipping message from `%s' since it's empty",
msg.user.name)
return ''
return formatter(msg, msg_txt)
@@ -202,7 +202,7 @@ class TextReporter(Reporter):
def _msg_file(self, msg, text):
"""return formatter for file"""
groups = self._re_first_idnick.match(msg.text).groupdict()
groups = self._slackid_pat[0].match(msg.text).groupdict()
text = msg.text.replace(groups['replace'], '')
filename = msg.file.filepath
if filename:
@@ -211,14 +211,17 @@ class TextReporter(Reporter):
filename = msg.file.url
if not filename:
logging.warning("Dude, we have a file object, but nothing has "
"found. Name of the file object is `i%s'",
msg.file.name)
logging.warning("There is a file object, but without filename."
"Name of the file object is `%s'", msg.file.name)
filename = msg.file.name
text = self._filter_slackid(text)
text = self._remove_entities(text)
text = self._fix_newlines(text)
for emoticon in self.emoji:
text = text.replace(emoticon, self.emoji[emoticon])
data = {'date': msg.datetime().strftime("%Y-%m-%d %H:%M:%S"),
'msg': text,
'max_len': self._max_len,
@@ -230,24 +233,40 @@ class TextReporter(Reporter):
'shared file "{filename}"{msg}\n'.format(**data))
def _msg(self, msg, text):
"""return formatter for /me"""
"""return formatter for all other message types"""
data = {'date': msg.datetime().strftime("%Y-%m-%d %H:%M:%S"),
'msg': text,
'max_len': self._max_len,
'separator': self._get_symbol('separator'),
'nick': msg.user.name}
return '{date} {nick:>{max_len}} {separator} {msg}\n'.format(**data)
result = '{date} {nick:>{max_len}} {separator} {msg}\n'.format(**data)
if msg.attachments:
for att in msg.attachments:
if att.title:
att_text = "\n" + att.title + '\n'
else:
att_text = "\n" + self._fix_newlines(att.fallback) + '\n'
if att.text:
att_text += att.text
att_text = self._fix_newlines(att_text)
# remove first newline
att_text = att_text[1:]
result += att_text + '\n'
return result
def _remove_entities(self, text):
"""replace html entites into appropriate chars"""
return html.parser.HTMLParser().unescape(text)
def _filter_slackid(self, text):
"""filter out all of the id from slack"""
for pat in (self._re_first_idnick, self._re_first_id):
while pat.search(text):
groups = pat.search(text).groupdict('slackid')
user = [u for u in self.users
if u.slackid == groups['slackid']][0]
text = text.replace(groups['replace'], user.name + ":")
for pat in (self._re_idnick, self._re_id):
for pat in self._slackid_pat:
while pat.search(text):
groups = pat.search(text).groupdict('slackid')
user = [u for u in self.users

View File

@@ -1,8 +1,5 @@
from unittest import TestCase
try:
from unittest.mock import MagicMock
except ImportError:
from mock import MagicMock
from unittest.mock import MagicMock
from slack_backup import client
from slack_backup import objects as o

View File

@@ -1,10 +1,5 @@
# -*- coding: utf-8 -*-
from unittest import TestCase
try:
from unittest.mock import MagicMock
except ImportError:
from mock import MagicMock
from unittest.mock import MagicMock
from slack_backup import reporters as r
@@ -45,7 +40,3 @@ class TestReporter(TestCase):
text = ('<@U111BBBBB|user2>Praesent vel enim sed eros luctus '
'imperdiet.\nMauris neque ante, <@U111DDDDD> placerat at, '
'mollis vitae, faucibus quis, <@U111CCCCC>leo. Ut feugiat.')
# Praesent vel enim sed eros luctus imperdiet. Vivamus urna quam, congue
# vulputate, convallis non, cursus cursus, risus. Quisque aliquet. Donec
# vulputate egestas elit. Morbi dictum, sem sit amet aliquam.

14
tox.ini
View File

@@ -1,5 +1,5 @@
[tox]
envlist = py27,py34,{py27,py34}-flake8
envlist = py34,py34-flake8
usedevelop = True
@@ -10,18 +10,6 @@ commands = py.test --cov=slack_backup --cov-report=term-missing
deps = -r{toxinidir}/requirements.txt
-r{toxinidir}/test-requirements.txt
[testenv:py27]
usedevelop={[testenv]usedevelop}
setenv = {[testenv]setenv}
commands = {[testenv]commands}
deps = {[testenv]deps}
mock
[testenv:py27-flake8]
basepython = python2.7
deps = flake8
commands = flake8 {posargs}
[testenv:py34-flake8]
basepython = python3.4
deps = flake8