diff options
| -rw-r--r-- | README.md | 82 | ||||
| -rw-r--r-- | setup.py | 32 | ||||
| -rw-r--r-- | tpblite/__init__.py | 2 | ||||
| -rw-r--r-- | tpblite/models/torrents.py | 20 |
4 files changed, 109 insertions, 27 deletions
@@ -0,0 +1,82 @@ +Unofficial Lightweight Python API for ThePirateBay + +Installation +============= +```sh +$ pip install tpblite +``` + +Dependencies: + - BeautifulSoup + - purl + +Usage +========== + +```python +from tpblite import TPB + +# Create a TPB object with a domain name +t = TPB('https://thepiratebay.org') + +# Or create a TPB object with default domain +t = TPB() +``` +## Search +```python +# Quick search for torrents, returns a Torrents object +torrents = t.search('public domain') + +# See how many torrents were found +print('There were {0} torrents found.'.format(len(torrents)) + +# Iterate through list of torrents and print info for Torrent object +for torrent in torrents: + print(torrent) + +# Customize your search +from tpb import CATEGORIES, ORDERS +torrents = t.search('public domain', page=2, order=ORDERS.NAME.DEC, category=CATEGORIES.VIDEO.MOVIES) + +# Get the most seeded torrent based on a filter +torrent = torrents.getBestTorrent(min_seeds=30, min_filesize='500 MiB', max_filesize='4 GiB') + +# Or select a particular torrent by indexing +torrent = torrents[3] + +# Get the magnet link for a torrent +print(torrent.magnetlink) +``` +## Torrents object +The search function returns a `Torrents` object, which is a *list-like* collection of the torrents found. + +You can also iterate over the `Torrents` object just by calling it in a for loop (see example above). + +You can see how many `Torrent` objects your query has returned, by using the `len()` function + +## Torrent object +`Torrent` objects represent each torrent found in the `Torrents` class, they have the following attributes +### Attributes +- `Torrent.title` - The name of the torrent (str) +- `Torrent.seeds` - The number of seeders (int) +- `Torrent.leeches` - The number of leechers (int) +- `Torrent.upload_date` - Date the torrent was uploaded (str) +- `Torrent.uploader` - Name of user who uploaded torrent (str) +- `Torrent.filesize` - The filesize in *iB format, eg. 5 GiB (str) +- `Torrent.byte_size` - The filesize in bytes of the torrent (int) +- `Torrent.magnetlink` - magnetlink of the torrent (str) + + +Example Workflow +========== + +With a commandline torrent client such as [aria2](), you can automate search and downloading of torrents like so: +```python +import subprocess +from tpblite import TPB + +t = TPB() +torrents = t.search('GIMP 2.10.8') +torrent = torrents.getBestTorrent() +subprocess.call(['aria2c', torrent.magnetlink]) +```
\ No newline at end of file @@ -2,21 +2,25 @@ from setuptools import setup, find_packages -setup(name='tpblite', - version='0.1.3', - description='The Unofficial Pirate Bay Lightweight Python API', - author='Matt Lyon', - author_email='matthewlyon18@gmail.com', - python_requires='>=3.6', - license='MIT License', - packages=['tpblite', 'tpblite/models'], - install_requires=[ +setup(name = 'tpblite', + version = '0.2.0', + description = 'The Unofficial Pirate Bay Lightweight Python API', + author = 'Matt Lyon', + author_email = 'matthewlyon18@gmail.com', + python_requires = '>=3.6', + url = 'https://github.com/mattlyon93/tpb-lite', + license = 'MIT License', + packages = ['tpblite', 'tpblite/models'], + install_requires = [ 'beautifulsoup4', - 'purl', - ], - classifiers=[ + 'purl'], + classifiers = [ + 'Development Status :: 3 - Alpha', 'Programming Language :: Python', 'Operating System :: Unix', - 'Operating System :: MacOS' - ], + 'Operating System :: MacOS', + 'Topic :: Internet :: WWW/HTTP :: Browsers', + 'Topic :: Internet :: WWW/HTTP :: Indexing/Search', + 'Topic :: Utilities'], + keywords = ['ThePirateBay', 'PirateBay', 'torrent'] )
\ No newline at end of file diff --git a/tpblite/__init__.py b/tpblite/__init__.py index e69de29..6a397d1 100644 --- a/tpblite/__init__.py +++ b/tpblite/__init__.py @@ -0,0 +1,2 @@ +from tpblite.tpblite import TPB +from tpblite.models.constants import ORDERS, CATEGORIES
\ No newline at end of file diff --git a/tpblite/models/torrents.py b/tpblite/models/torrents.py index 87a3b6b..eb007cb 100644 --- a/tpblite/models/torrents.py +++ b/tpblite/models/torrents.py @@ -2,7 +2,6 @@ import re import unicodedata from bs4 import BeautifulSoup -#TODO: implement a pretty print for Torrents object #TODO: write better comments def fileSizeStrToInt(size_str): @@ -73,7 +72,7 @@ class Torrents(object): self.__search_set = None self.html_source = html_source - self.list = self._createTorrentListMod() + self.list = self._createTorrentList() def __str__(self): return 'Torrents object: {} torrents'.format(len(self.list)) @@ -87,21 +86,16 @@ class Torrents(object): def __len__(self): return len(self.list) + def __getitem__(self,index): + return self.list[index] + @property - def search_set(self): + def _search_set(self): if self.__search_set == None: self.__search_set = set(filter(None, re.split(r'[\s.|\(|\)]',self.search_str.lower()))) return self.__search_set - - def _createTorrentList(self): - soup = BeautifulSoup(self.html_source, features='html.parser') - rows = self.__getRows(soup) - torrents = [] - for row in rows: - torrents.append(Torrent(row)) - return torrents - def _createTorrentListMod(self): + def _createTorrentList(self): soup = BeautifulSoup(self.html_source, features='html.parser') rows = soup.body.find_all('tr') torrents = [] @@ -109,7 +103,7 @@ class Torrents(object): # Get the lowercase unique set from the row text text_set = set(filter(None, re.split(r'[\s.|\(|\)]',row.text.lower()))) # Check if search string is subset - if self.search_set.issubset(text_set): + if self._search_set.issubset(text_set): torrents.append(Torrent(row)) return torrents |