init
commit
279c8fc54d
|
@ -0,0 +1,67 @@
|
||||||
|
|
||||||
|
# Editor
|
||||||
|
.idea/
|
||||||
|
.vscode/
|
||||||
|
|
||||||
|
# Byte-compiled / optimized / DLL files
|
||||||
|
__pycache__/
|
||||||
|
*.py[cod]
|
||||||
|
*$py.class
|
||||||
|
|
||||||
|
# C extensions
|
||||||
|
*.so
|
||||||
|
|
||||||
|
# Distribution / packaging
|
||||||
|
.Python
|
||||||
|
env/
|
||||||
|
build/
|
||||||
|
develop-eggs/
|
||||||
|
dist/
|
||||||
|
downloads/
|
||||||
|
eggs/
|
||||||
|
.eggs/
|
||||||
|
lib/
|
||||||
|
lib64/
|
||||||
|
parts/
|
||||||
|
sdist/
|
||||||
|
var/
|
||||||
|
*.egg-info/
|
||||||
|
.installed.cfg
|
||||||
|
*.egg
|
||||||
|
|
||||||
|
# PyInstaller
|
||||||
|
# Usually these files are written by a python script from a template
|
||||||
|
# before PyInstaller builds the exe, so as to inject date/other infos into it.
|
||||||
|
*.manifest
|
||||||
|
*.spec
|
||||||
|
|
||||||
|
# Installer logs
|
||||||
|
pip-log.txt
|
||||||
|
pip-delete-this-directory.txt
|
||||||
|
|
||||||
|
# Unit test / coverage reports
|
||||||
|
htmlcov/
|
||||||
|
.tox/
|
||||||
|
.coverage
|
||||||
|
.coverage.*
|
||||||
|
.cache
|
||||||
|
nosetests.xml
|
||||||
|
coverage.xml
|
||||||
|
*,cover
|
||||||
|
.hypothesis/
|
||||||
|
|
||||||
|
# Translations
|
||||||
|
*.mo
|
||||||
|
*.pot
|
||||||
|
|
||||||
|
# Django stuff:
|
||||||
|
*.log
|
||||||
|
|
||||||
|
# Sphinx documentation
|
||||||
|
docs/_build/
|
||||||
|
|
||||||
|
# PyBuilder
|
||||||
|
target/
|
||||||
|
|
||||||
|
#Ipython Notebook
|
||||||
|
.ipynb_checkpoints
|
|
@ -0,0 +1,21 @@
|
||||||
|
The MIT License (MIT)
|
||||||
|
|
||||||
|
Copyright (c) 2017 7sDream
|
||||||
|
|
||||||
|
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||||
|
of this software and associated documentation files (the "Software"), to deal
|
||||||
|
in the Software without restriction, including without limitation the rights
|
||||||
|
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||||
|
copies of the Software, and to permit persons to whom the Software is
|
||||||
|
furnished to do so, subject to the following conditions:
|
||||||
|
|
||||||
|
The above copyright notice and this permission notice shall be included in all
|
||||||
|
copies or substantial portions of the Software.
|
||||||
|
|
||||||
|
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||||
|
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||||
|
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||||
|
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||||
|
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||||
|
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||||
|
SOFTWARE.
|
|
@ -0,0 +1,3 @@
|
||||||
|
include README.md LICENSE changelog.md
|
||||||
|
include test.py
|
||||||
|
include test.torrent
|
|
@ -0,0 +1,50 @@
|
||||||
|
# Torrent file parser for Python
|
||||||
|
|
||||||
|
## Install
|
||||||
|
|
||||||
|
```
|
||||||
|
pip install torret_parser
|
||||||
|
```
|
||||||
|
|
||||||
|
## Usage:
|
||||||
|
|
||||||
|
### CLI
|
||||||
|
|
||||||
|
```
|
||||||
|
$ pytp test.torrent
|
||||||
|
```
|
||||||
|
|
||||||
|
```
|
||||||
|
$ cat test.torrent | pytp
|
||||||
|
```
|
||||||
|
|
||||||
|
![][screenshots-help]
|
||||||
|
|
||||||
|
![][screenshots-normal]
|
||||||
|
|
||||||
|
![][screenshots-indent]
|
||||||
|
|
||||||
|
|
||||||
|
### As a module
|
||||||
|
|
||||||
|
```pycon
|
||||||
|
>>> import torrent_parser as tp
|
||||||
|
>>> data = tp.parse_torrent_file('test.torrent')
|
||||||
|
>>> print(data['announce'])
|
||||||
|
http://tracker.trackerfix.com:80/announce
|
||||||
|
```
|
||||||
|
|
||||||
|
## Test
|
||||||
|
|
||||||
|
```bash
|
||||||
|
python -m unittest test
|
||||||
|
```
|
||||||
|
|
||||||
|
## LICENSE
|
||||||
|
|
||||||
|
See [License][LICENSE].
|
||||||
|
|
||||||
|
[screenshots-help]: http://rikka-10066868.image.myqcloud.com/7c23f6d0-b23f-4c57-be93-d37fafe3292a.png
|
||||||
|
[screenshots-normal]: http://rikka-10066868.image.myqcloud.com/1492616d-9f14-4fe2-9146-9a3ac06c6868.png
|
||||||
|
[screenshots-indent]: http://rikka-10066868.image.myqcloud.com/eadc4184-6deb-42eb-bfd4-239da8f50c08.png
|
||||||
|
[LICENSE]: https://github.com/7sDream/torrent_parser/blob/master/LICENSE
|
|
@ -0,0 +1,6 @@
|
||||||
|
[metadata]
|
||||||
|
description-file = README.md
|
||||||
|
license-file = LICENSE
|
||||||
|
|
||||||
|
[bdist_wheel]
|
||||||
|
universal = 1
|
|
@ -0,0 +1,41 @@
|
||||||
|
#!/usr/bin/env python
|
||||||
|
# coding=utf-8
|
||||||
|
|
||||||
|
try:
|
||||||
|
from setuptools import setup
|
||||||
|
except ImportError:
|
||||||
|
from distutils.core import setup
|
||||||
|
|
||||||
|
import torrent_parser
|
||||||
|
|
||||||
|
setup(
|
||||||
|
name='torrent_parser',
|
||||||
|
keywords=['file', 'torrent', 'JSON', 'parser'],
|
||||||
|
version=torrent_parser.__version__,
|
||||||
|
py_modules=['torrent_parser'],
|
||||||
|
url='https://github.com/7sDream/torrent_parser',
|
||||||
|
license='MIT',
|
||||||
|
author='7sDream',
|
||||||
|
author_email='7seconddream@gmail.com',
|
||||||
|
description='A .torrent file parser for both Python 2 and 3',
|
||||||
|
install_requires=[],
|
||||||
|
entry_points={
|
||||||
|
'console_scripts': ['pytp=torrent_parser:__main']
|
||||||
|
},
|
||||||
|
classifiers=[
|
||||||
|
'Development Status :: 3 - Alpha',
|
||||||
|
'Environment :: Console',
|
||||||
|
'Intended Audience :: Developers',
|
||||||
|
'Intended Audience :: End Users/Desktop',
|
||||||
|
'License :: OSI Approved :: MIT License',
|
||||||
|
'Natural Language :: English',
|
||||||
|
'Operating System :: OS Independent',
|
||||||
|
'Programming Language :: Python',
|
||||||
|
'Programming Language :: Python :: 2.7',
|
||||||
|
'Programming Language :: Python :: 3.5',
|
||||||
|
'Programming Language :: Python :: 3.6',
|
||||||
|
'Topic :: Multimedia',
|
||||||
|
'Topic :: Software Development :: Libraries :: Python Modules',
|
||||||
|
'Topic :: Utilities',
|
||||||
|
]
|
||||||
|
)
|
|
@ -0,0 +1,49 @@
|
||||||
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
|
import unittest
|
||||||
|
import collections
|
||||||
|
|
||||||
|
from torrent_parser import TorrentFileParser, parse_torrent_file
|
||||||
|
|
||||||
|
|
||||||
|
class Test(unittest.TestCase):
|
||||||
|
TEST_FILENAME = 'test.torrent'
|
||||||
|
|
||||||
|
def test_parse_torrent_file_use_shortcut(self):
|
||||||
|
parse_torrent_file(self.TEST_FILENAME)
|
||||||
|
|
||||||
|
def test_parse_torrent_file_use_class(self):
|
||||||
|
with open(self.TEST_FILENAME, 'rb') as fp:
|
||||||
|
TorrentFileParser(fp).parse()
|
||||||
|
|
||||||
|
def test_parse_torrent_file_to_ordered_dict(self):
|
||||||
|
data = parse_torrent_file(self.TEST_FILENAME, True)
|
||||||
|
self.assertIsInstance(data, collections.OrderedDict)
|
||||||
|
|
||||||
|
with open(self.TEST_FILENAME, 'rb') as fp:
|
||||||
|
data = TorrentFileParser(fp, True).parse()
|
||||||
|
self.assertIsInstance(data, collections.OrderedDict)
|
||||||
|
|
||||||
|
def test_parse_correctness(self):
|
||||||
|
data = parse_torrent_file(self.TEST_FILENAME)
|
||||||
|
self.assertIn(['udp://p4p.arenabg.ch:1337/announce'],
|
||||||
|
data['announce-list'])
|
||||||
|
self.assertEqual(data['comment'],
|
||||||
|
'Torrent downloaded from https://rarbg.to')
|
||||||
|
self.assertEqual(data['creation date'], 1472762993)
|
||||||
|
|
||||||
|
def test_parse_two_times(self):
|
||||||
|
with open(self.TEST_FILENAME, 'rb') as fp:
|
||||||
|
parser = TorrentFileParser(fp)
|
||||||
|
data = parser.parse()
|
||||||
|
self.assertIn(['udp://p4p.arenabg.ch:1337/announce'],
|
||||||
|
data['announce-list'])
|
||||||
|
self.assertEqual(data['comment'],
|
||||||
|
'Torrent downloaded from https://rarbg.to')
|
||||||
|
self.assertEqual(data['creation date'], 1472762993)
|
||||||
|
data = parser.parse()
|
||||||
|
self.assertIn(['udp://p4p.arenabg.ch:1337/announce'],
|
||||||
|
data['announce-list'])
|
||||||
|
self.assertEqual(data['comment'],
|
||||||
|
'Torrent downloaded from https://rarbg.to')
|
||||||
|
self.assertEqual(data['creation date'], 1472762993)
|
|
@ -0,0 +1,2 @@
|
||||||
|
d8:announce41:http://tracker.trackerfix.com:80/announce13:announce-listll41:http://tracker.trackerfix.com:80/announceel30:udp://9.rarbg.me:2710/announceel30:udp://9.rarbg.to:2710/announceel43:udp://tracker.coppersurfer.tk:6969/announceel34:udp://glotorrents.pw:6969/announceel40:udp://tracker.trackerfix.com:80/announceel40:udp://inferno.demonoid.ooo:3392/announceel34:udp://p4p.arenabg.ch:1337/announceel30:udp://9.rarbg.me:2710/announceel30:udp://9.rarbg.to:2710/announceel38:udp://torrent.gresille.org:80/announceel35:http://retracker.krs-ix.ru/announceel34:http://mgtracker.org:2710/announceel30:http://thetracker.org/announceel33:http://explodie.org:6969/announceee7:comment40:Torrent downloaded from https://rarbg.to10:created by13:uTorrent/221013:creation datei1472762993e8:encoding5:UTF-84:infod5:filesld6:lengthi505957e4:pathl83:Streaming, Sharing, Stealing - Big Data and the Future of Entertainment (2016).epubeed6:lengthi36e4:pathl16:Come Join Us.txteee4:name92:Streaming, Sharing, Stealing - Big Data and the Future of Entertainment (2016) (Epub) Gooner12:piece lengthi65536e6:pieces160:™d\6Z)¡þ<1E>Š¸l0 aÛèPZ™6HÿV'†",fÄ{9ô3™üG2õ0½íOoj¹/v%YG†•VÞƒW&‘®YoÏ=-5ö<35>À¬-¡rCÆÉbñÂ,ìB,¹’<C2B9>Äw¸Ç—f{PJ|—‰C/ä<>+
|
||||||
|
+ B¾+¹žÓ ò±!ЧæTåO0pSDšlüÇ92º¸3Ý8ÅAee
|
|
@ -0,0 +1,262 @@
|
||||||
|
#!/usr/bin/env python
|
||||||
|
# coding: utf-8
|
||||||
|
|
||||||
|
"""
|
||||||
|
A .torrent file parser for both Python 2 and 3
|
||||||
|
|
||||||
|
Usage:
|
||||||
|
|
||||||
|
data = parse_torrent_file(filename)
|
||||||
|
|
||||||
|
# or
|
||||||
|
|
||||||
|
with open(filename, 'rb') as f: # the binary mode 'b' is necessary
|
||||||
|
data = TorrentFileParser(f).parse()
|
||||||
|
"""
|
||||||
|
|
||||||
|
from __future__ import print_function, unicode_literals
|
||||||
|
|
||||||
|
import argparse
|
||||||
|
import collections
|
||||||
|
import io
|
||||||
|
import json
|
||||||
|
import sys
|
||||||
|
|
||||||
|
|
||||||
|
__all__ = [
|
||||||
|
'InvalidTorrentFileException',
|
||||||
|
'parse_torrent_file',
|
||||||
|
'TorrentFileParser',
|
||||||
|
]
|
||||||
|
|
||||||
|
__version__ = '0.1.0'
|
||||||
|
|
||||||
|
|
||||||
|
class InvalidTorrentFileException(Exception):
|
||||||
|
def __init__(self, pos, msg=None):
|
||||||
|
msg = msg or "Invalid torrent format when reading at pos " + str(pos)
|
||||||
|
super(InvalidTorrentFileException, self).__init__(msg)
|
||||||
|
|
||||||
|
|
||||||
|
class TorrentFileParser(object):
|
||||||
|
|
||||||
|
TYPE_LIST = 'list'
|
||||||
|
TYPE_DICT = 'dict'
|
||||||
|
TYPE_INT = 'int'
|
||||||
|
TYPE_STRING = 'string'
|
||||||
|
TYPE_END = 'end'
|
||||||
|
|
||||||
|
LIST_INDICATOR = b'l'
|
||||||
|
DICT_INDICATOR = b'd'
|
||||||
|
INT_INDICATOR = b'i'
|
||||||
|
END_INDICATOR = b'e'
|
||||||
|
STRING_INDICATOR = b''
|
||||||
|
|
||||||
|
TYPES = [
|
||||||
|
(TYPE_LIST, LIST_INDICATOR),
|
||||||
|
(TYPE_DICT, DICT_INDICATOR),
|
||||||
|
(TYPE_INT, INT_INDICATOR),
|
||||||
|
(TYPE_END, END_INDICATOR),
|
||||||
|
(TYPE_STRING, STRING_INDICATOR),
|
||||||
|
]
|
||||||
|
|
||||||
|
def __init__(self, fp, use_ordered_dict=False, encoding='utf-8'):
|
||||||
|
"""
|
||||||
|
:param fp: a **binary** file-like object to parse,
|
||||||
|
which means need 'b' mode when use built-in open function
|
||||||
|
:param encoding: file content encoding, default utf-8
|
||||||
|
:param use_ordered_dict: Use collections.OrderedDict as dict container
|
||||||
|
default False, which mean use built-in dict
|
||||||
|
"""
|
||||||
|
if getattr(fp, 'read', ) is None \
|
||||||
|
or getattr(fp, 'seek') is None:
|
||||||
|
raise ValueError('Argument fp needs a file like object')
|
||||||
|
|
||||||
|
self._pos = 0
|
||||||
|
self._encoding = encoding
|
||||||
|
self._content = fp
|
||||||
|
self._use_ordered_dict = use_ordered_dict
|
||||||
|
|
||||||
|
def parse(self):
|
||||||
|
"""
|
||||||
|
:return: the parse result
|
||||||
|
:type: depends on ``use_ordered_dict`` option when init the parser
|
||||||
|
see :any:`TorrentFileParser.__init__`
|
||||||
|
"""
|
||||||
|
self._restart()
|
||||||
|
data = self._next_element()
|
||||||
|
|
||||||
|
try:
|
||||||
|
c = self._read_byte(1, True)
|
||||||
|
raise InvalidTorrentFileException(
|
||||||
|
0, 'Expect EOF, but get [{}] at pos {}'.format(c, self._pos)
|
||||||
|
)
|
||||||
|
except EOFError: # expect EOF
|
||||||
|
pass
|
||||||
|
|
||||||
|
if isinstance(data, dict):
|
||||||
|
return data
|
||||||
|
|
||||||
|
raise InvalidTorrentFileException('Outermost element is not a dict')
|
||||||
|
|
||||||
|
def _read_byte(self, count=1, raise_eof=False):
|
||||||
|
assert count >= 0
|
||||||
|
gotten = self._content.read(count)
|
||||||
|
if count != 0 and len(gotten) == 0:
|
||||||
|
if raise_eof:
|
||||||
|
raise EOFError()
|
||||||
|
raise InvalidTorrentFileException(
|
||||||
|
self._pos,
|
||||||
|
'Unexpected EOF when reading torrent file'
|
||||||
|
)
|
||||||
|
self._pos += count
|
||||||
|
return gotten
|
||||||
|
|
||||||
|
def _seek_back(self, count):
|
||||||
|
self._content.seek(-count, 1)
|
||||||
|
|
||||||
|
def _restart(self):
|
||||||
|
self._content.seek(0, 0)
|
||||||
|
self._pos = 0
|
||||||
|
|
||||||
|
def _dict_items_generator(self):
|
||||||
|
while True:
|
||||||
|
try:
|
||||||
|
k = self._next_element()
|
||||||
|
except InvalidTorrentFileException:
|
||||||
|
return
|
||||||
|
if k == 'pieces':
|
||||||
|
v = self._pieces()
|
||||||
|
else:
|
||||||
|
v = self._next_element()
|
||||||
|
if k == 'encoding':
|
||||||
|
self._encoding = v
|
||||||
|
yield k, v
|
||||||
|
|
||||||
|
def _next_dict(self):
|
||||||
|
data = collections.OrderedDict() if self._use_ordered_dict else dict()
|
||||||
|
for key, element in self._dict_items_generator():
|
||||||
|
data[key] = element
|
||||||
|
return data
|
||||||
|
|
||||||
|
def _list_items_generator(self):
|
||||||
|
while True:
|
||||||
|
try:
|
||||||
|
element = self._next_element()
|
||||||
|
except InvalidTorrentFileException:
|
||||||
|
return
|
||||||
|
yield element
|
||||||
|
|
||||||
|
def _next_list(self):
|
||||||
|
return [element for element in self._list_items_generator()]
|
||||||
|
|
||||||
|
def _next_int(self, end=END_INDICATOR):
|
||||||
|
value = 0
|
||||||
|
char = self._read_byte(1)
|
||||||
|
while char != end:
|
||||||
|
# noinspection PyTypeChecker
|
||||||
|
if not b'0' <= char <= b'9':
|
||||||
|
raise InvalidTorrentFileException(self._pos)
|
||||||
|
value = value * 10 + int(char) - int(b'0')
|
||||||
|
char = self._read_byte(1)
|
||||||
|
return value
|
||||||
|
|
||||||
|
def _next_string(self, decode=True):
|
||||||
|
length = self._next_int(b':')
|
||||||
|
raw = self._read_byte(length)
|
||||||
|
if decode:
|
||||||
|
string = raw.decode(self._encoding)
|
||||||
|
return string
|
||||||
|
return raw
|
||||||
|
|
||||||
|
@staticmethod
|
||||||
|
def __to_hex(v):
|
||||||
|
return hex(ord(v) if isinstance(v, str) else v)[2:].rjust(2, str(0))
|
||||||
|
|
||||||
|
def _pieces(self):
|
||||||
|
raw = self._next_string(decode=False)
|
||||||
|
if len(raw) % 20 != 0:
|
||||||
|
raise InvalidTorrentFileException(self._pos)
|
||||||
|
return [
|
||||||
|
''.join([self.__to_hex(c) for c in h])
|
||||||
|
for h in (raw[x:x+20] for x in range(0, len(raw), 20))
|
||||||
|
]
|
||||||
|
|
||||||
|
def _next_end(self):
|
||||||
|
raise InvalidTorrentFileException(self._pos)
|
||||||
|
|
||||||
|
def _next_type(self):
|
||||||
|
for (element_type, indicator) in self.TYPES:
|
||||||
|
indicator_length = len(indicator)
|
||||||
|
char = self._read_byte(indicator_length)
|
||||||
|
if indicator == char:
|
||||||
|
return element_type
|
||||||
|
self._seek_back(indicator_length)
|
||||||
|
raise InvalidTorrentFileException(self._pos)
|
||||||
|
|
||||||
|
def _type_to_func(self, t):
|
||||||
|
return getattr(self, '_next_' + t)
|
||||||
|
|
||||||
|
def _next_element(self):
|
||||||
|
element_type = self._next_type()
|
||||||
|
element = self._type_to_func(element_type)()
|
||||||
|
return element
|
||||||
|
|
||||||
|
|
||||||
|
def parse_torrent_file(filename, use_ordered_dict=False):
|
||||||
|
"""
|
||||||
|
Shortcut function for parse torrent object use TorrentFileParser
|
||||||
|
|
||||||
|
:param string filename: torrent filename
|
||||||
|
:param bool use_ordered_dict: see :any:`TorrentFileParser.__init__`
|
||||||
|
:rtype: dict if ``use_ordered_dict`` is false,
|
||||||
|
collections.OrderedDict otherwise
|
||||||
|
"""
|
||||||
|
with open(filename, 'rb') as f:
|
||||||
|
return TorrentFileParser(f, use_ordered_dict).parse()
|
||||||
|
|
||||||
|
|
||||||
|
def __main():
|
||||||
|
parser = argparse.ArgumentParser()
|
||||||
|
parser.add_argument('file', nargs='?', default='',
|
||||||
|
help='input file, will read form stdin if empty')
|
||||||
|
parser.add_argument('--dict', '-d', action='store_true', default=False,
|
||||||
|
help='use built-in dict, default will be OrderedDict')
|
||||||
|
parser.add_argument('--sort', '-s', action='store_true', default=False,
|
||||||
|
help='sort output json item by key')
|
||||||
|
parser.add_argument('--indent', '-i', type=int, default=None,
|
||||||
|
help='json output indent for every inner level')
|
||||||
|
parser.add_argument('--ascii', '-a', action='store_true', default=False,
|
||||||
|
help='ensure output json use ascii char, '
|
||||||
|
'escape other char use \\u')
|
||||||
|
parser.add_argument('--version', '-v', action='store_true', default=False,
|
||||||
|
help='print version and exit')
|
||||||
|
args = parser.parse_args()
|
||||||
|
|
||||||
|
if args.version:
|
||||||
|
print(__version__)
|
||||||
|
exit(0)
|
||||||
|
|
||||||
|
try:
|
||||||
|
if args.file == '':
|
||||||
|
target_file = io.BytesIO(
|
||||||
|
getattr(sys.stdin, 'buffer', sys.stdin).read()
|
||||||
|
)
|
||||||
|
else:
|
||||||
|
target_file = open(args.file, 'rb')
|
||||||
|
except FileNotFoundError:
|
||||||
|
sys.stderr.write('Unable to find file {}\n'.format(args.file))
|
||||||
|
exit(1)
|
||||||
|
|
||||||
|
# noinspection PyUnboundLocalVariable
|
||||||
|
data = TorrentFileParser(target_file, not args.dict).parse()
|
||||||
|
|
||||||
|
data = json.dumps(
|
||||||
|
data, ensure_ascii=args.ascii,
|
||||||
|
sort_keys=args.sort, indent=args.indent
|
||||||
|
)
|
||||||
|
|
||||||
|
print(data)
|
||||||
|
|
||||||
|
if __name__ == '__main__':
|
||||||
|
__main()
|
Loading…
Reference in New Issue