KomSuite/KomSuite-NyaaPy
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases 3 Wiki Activity

Nyaa.si & sukebei.nyaa.si LXML fully ready

Browse Source
This commit is contained in:
Ferenc Nánási
2020-02-01 15:11:35 +01:00
parent bf01a922f0
commit fd28e65c8b
8 changed files with 190 additions and 109 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
.gitignore vendored
View File

@@ -4,3 +4,4 @@ nyaapy.egg-info
.vscode
env/
*.pyc
test_files

32
NyaaPy/nyaa.py
View File

@@ -1,25 +1,27 @@
import requests
import urllib.parse
from NyaaPy import utils
class Nyaa:
def __init__(self):
self.URI = "http://nyaa.si"
self.SITE = utils.TorrentSite.NYAASI
def last_uploads(self, number_of_results):
r = requests.get(self.URI)
r = requests.get(self.SITE.value)
# If anything up with nyaa servers let the user know.
r.raise_for_status()
return utils.parse_nyaa(
request_text=r.text,
limit=number_of_results + 1
limit=number_of_results + 1,
site=self.SITE
)
def search(self, keyword, **kwargs):
url = self.SITE.value
user = kwargs.get('user', None)
category = kwargs.get('category', 0)
subcategory = kwargs.get('subcategory', 0)
@@ -33,24 +35,32 @@ class Nyaa:
if page > 0:
r = requests.get("{}/{}?f={}&c={}_{}&q={}&p={}".format(
self.URI, user_uri, filters, category, subcategory, keyword,
url, user_uri, filters, category, subcategory, keyword,
page))
else:
r = requests.get("{}/{}?f={}&c={}_{}&q={}".format(
self.URI, user_uri, filters, category, subcategory, keyword))
url, user_uri, filters, category, subcategory, keyword))
r.raise_for_status()
return utils.parse_nyaa(request_text=r.text, limit=None)
return utils.parse_nyaa(
request_text=r.text,
limit=None,
site=self.SITE
)
def get(self, id):
r = requests.get("{}/view/{}".format(self.URI, id))
r = requests.get("{}/view/{}".format(self.SITE.value, id))
r.raise_for_status()
return utils.parse_single(request_text=r.text)
return utils.parse_single(request_text=r.text, site=self.SITE)
def get_user(self, username):
r = requests.get("{}/user/{}".format(self.URI, username))
r = requests.get("{}/user/{}".format(self.SITE.value, username))
r.raise_for_status()
return utils.parse_nyaa(request_text=r.text, limit=None)
return utils.parse_nyaa(
request_text=r.text,
limit=None,
site=self.SITE
)

20
NyaaPy/pantsu.py
View File

@@ -1,18 +1,24 @@
import requests
from NyaaPy import utils
class Pantsu:
def __init__(self):
self.BASE_URL = "https://nyaa.pantsu.cat/api"
self.SITE = utils.TorrentSite.NYAANET
def last_uploads(self, number_of_results):
r = requests.get(self.URI)
soup = BeautifulSoup(r.text, 'html.parser')
rows = soup.select('table tr')
return utils.parse_nyaa(rows, limit=number_of_results + 1)
r = requests.get(self.SITE.value)
r.raise_for_status()
with open("test.html", "w") as f:
f.write(r.text)
return utils.parse_nyaa(
request_text=r.text,
limit=number_of_results + 1,
site=self.SITE
)
# Torrents - GET
def search(self, keyword, **kwargs):
@@ -23,10 +29,11 @@ class Pantsu:
def view(self, item_id):
request = requests.get("{}/view/{}".format(self.BASE_URL, item_id))
request.raise_for_status()
return request.json()
# Torrents - POST
def upload(self):
return "Work in progress!"
@@ -34,7 +41,6 @@ class Pantsu:
return "Work in progress!"
# Users
def login(self, username, password):
login = requests.post("{}/login/".format(
self.BASE_URL), data={'username': username, 'password': password})

43
NyaaPy/sukebei.py
View File

@@ -1,9 +1,14 @@
import requests
from bs4 import BeautifulSoup
from NyaaPy import utils
class SukebeiNyaa:
def __init__(self):
self.SITE = utils.TorrentSite.SUKEBEINYAASI
def search(self, keyword, **kwargs):
uri = self.SITE.value
category = kwargs.get('category', 0)
subcategory = kwargs.get('subcategory', 0)
filters = kwargs.get('filters', 0)
@@ -11,37 +16,37 @@ class SukebeiNyaa:
if page > 0:
r = requests.get("{}/?f={}&c={}_{}&q={}&p={}".format(
"http://sukebei.nyaa.si", filters, category, subcategory,
uri, filters, category, subcategory,
keyword, page))
else:
r = requests.get("{}/?f={}&c={}_{}&q={}".format(
"http://sukebei.nyaa.si", filters, category, subcategory,
uri, filters, category, subcategory,
keyword))
soup = BeautifulSoup(r.text, 'html.parser')
rows = soup.select('table tr')
return utils.parse_nyaa(rows, limit=None)
r.raise_for_status()
return utils.parse_nyaa(r.text, limit=None, site=self.SITE)
def get(self, id):
r = requests.get("http://sukebei.nyaa.si/view/{}".format(id))
soup = BeautifulSoup(r.text, 'html.parser')
content = soup.findAll("div", {"class": "panel", "id": None})
r = requests.get("{}/view/{}".format(self.SITE.value, id))
r.raise_for_status()
return utils.parse_single(content)
return utils.parse_single(r.text, self.SITE)
def get_user(self, username):
r = requests.get("http://sukebei.nyaa.si/user/{}".format(username))
soup = BeautifulSoup(r.text, 'html.parser')
r = requests.get("{}/user/{}".format(self.SITE.value, username))
r.raise_for_status()
return utils.parse_nyaa(soup.select('table tr'), limit=None)
return utils.parse_nyaa(r.text, limit=None, site=self.SITE)
def news(self, number_of_results):
r = requests.get("http://sukebei.nyaa.si/")
soup = BeautifulSoup(r.text, 'html.parser')
rows = soup.select('table tr')
def last_uploads(self, number_of_results):
r = requests.get(self.SITE.value)
r.raise_for_status()
return utils.parse_sukebei(rows, limit=number_of_results + 1)
return utils.parse_nyaa(
r.text,
limit=number_of_results + 1,
site=self.SITE
)
class SukebeiPantsu:

87
NyaaPy/utils.py
View File

@@ -3,9 +3,22 @@
'''
import re
from enum import Enum
from lxml import etree
class TorrentSite(Enum):
"""
Contains torrent sites
"""
NYAASI = "https://nyaa.si"
SUKEBEINYAASI = "https://sukebei.nyaa.si"
# * nyaa.pantsu.cat redirects to nyaa.net
NYAANET = "https://nyaa.net"
SUKEBEINYAANET = "https://sukebei.nyaa.net"
def nyaa_categories(b):
c = b.replace('?c=', '')
cats = c.split('_')
@@ -72,10 +85,13 @@ def nyaa_categories(b):
return category_name
def parse_nyaa(request_text, limit):
def parse_nyaa(request_text, limit, site):
parser = etree.HTMLParser()
tree = etree.fromstring(request_text, parser)
# Put proper domain here.
uri = site.value
torrents = []
# Going through table rows
@@ -94,25 +110,36 @@ def parse_nyaa(request_text, limit):
if link.text and link.text.strip():
block.append(link.text.strip())
if td.text and td.text.strip():
if td.text is not None and td.text.strip():
block.append(td.text.strip())
# Add type of torrent based on tr class.
if tr.attrib.get("class") is not None:
if 'danger' in tr.attrib.get("class"):
block.append("remake")
elif 'success' in tr.attrib.get("class"):
block.append("trusted")
else:
block.append("default")
else:
block.append("default")
# Decide category.
if site in [TorrentSite.NYAASI, TorrentSite.NYAANET]:
category = nyaa_categories(block[0])
elif site in [TorrentSite.SUKEBEINYAASI, TorrentSite.SUKEBEINYAANET]:
category = sukebei_categories(block[0])
else:
raise ArgumentException("Unknown TorrentSite received!")
# Create torrent object
try:
torrent = {
'id': block[1],
'category': nyaa_categories(block[0]),
'url': "https://nyaa.si/view/{}".format(block[1]),
'category': category,
'url': "{}/view/{}".format(uri, block[1]),
'name': block[2],
'download_url': "https://nyaa.si/download/{}".format(block[3]),
'download_url': "{}/download/{}".format(uri, block[3]),
'magnet': block[4],
'size': block[5],
'date': block[6],
@@ -127,10 +154,13 @@ def parse_nyaa(request_text, limit):
return torrents
def parse_single(request_text):
def parse_single(request_text, site):
parser = etree.HTMLParser()
tree = etree.fromstring(request_text, parser)
# Put proper domain here.
uri = site.value
torrent = {}
data = []
torrent_files = []
@@ -152,7 +182,7 @@ def parse_single(request_text):
tree.xpath("//h3[@class='panel-title']/text()")[0].strip()
torrent['category'] = data[0]
torrent['uploader'] = data[4]
torrent['uploader_profile'] = "http://nyaa.si/user/{}".format(data[4])
torrent['uploader_profile'] = "{}/user/{}".format(uri, data[4])
torrent['website'] = data[6]
torrent['size'] = data[8]
torrent['date'] = data[3]
@@ -169,49 +199,8 @@ def parse_single(request_text):
return torrent
def parse_sukebei(table_rows, limit):
if limit == 0:
limit = len(table_rows)
torrents = []
for row in table_rows[:limit]:
block = []
for td in row.find_all('td'):
for link in td.find_all('a'):
if link.get('href')[-9:] != '#comments':
block.append(link.get('href'))
block.append(link.text.rstrip())
if td.text.rstrip():
block.append(td.text.rstrip())
try:
torrent = {
'id': block[1].replace("/view/", ""),
'category': sukebei_categories(block[0]),
'url': "http://sukebei.nyaa.si{}".format(block[1]),
'name': block[2],
'download_url': "http://sukebei.nyaa.si{}".format(
block[4]),
'magnet': block[5],
'size': block[6],
'date': block[7],
'seeders': block[8],
'leechers': block[9],
'completed_downloads': block[10],
}
except IndexError as ie:
pass
torrents.append(torrent)
return torrents
def sukebei_categories(b):
c = b.replace('/?c=', '')
c = b.replace('?c=', '')
cats = c.split('_')
cat = cats[0]

34
tests/test.py
View File

@@ -1,32 +1,43 @@
from NyaaPy import Pantsu, Nyaa
from NyaaPy import Nyaa
from pprint import pprint
from datetime import datetime
import json
import sys
import os
# Creating a folder for test_files
# ! not included in github project.
if not os.path.isdir("test_files"):
os.makedirs("test_files")
# pantsu = Pantsu()
nyaa = Nyaa()
# Get fresh torrents
dt_latest_torrents_begin = datetime.now()
latest_torrents = nyaa.last_uploads(100)
dt_latest_torrents_end = datetime.now()
with open("test_files/nyaa_latest_torrent_test.json", 'w') as f:
json.dump(latest_torrents, f)
# I'd like to watch Tenki no ko, but not uploaded yet.
# Search some nasty stuff
dt_search_begin = datetime.now()
test_search = nyaa.search("Kimi no Na wa")
test_search = nyaa.search("kimi no na wa")
dt_search_end = datetime.now()
# pprint(test_search)
with open("test_files/nyaa_search_test.json", 'w') as f:
json.dump(test_search, f)
# Get first torrent from found torrents
# print("First result torrent info:")
dt_single_torrent_begin = datetime.now()
single_torrent = nyaa.get(test_search[0]["id"])
dt_single_torrent_end = datetime.now()
#pprint(single_torrent)
with open("test_files/nyaa_single_torrent_test.json", 'w') as f:
json.dump(single_torrent, f)
dt_user_begin = datetime.now()
user_torrents = nyaa.get_user("Lilith-Raws")
user_torrents = nyaa.get_user("HorribleSubs")
dt_user_end = datetime.now()
#pprint(user_torrents)
with open("test_files/nyaa_single_user_test.json", 'w') as f:
json.dump(user_torrents, f)
print(
"Latest torrents time:",
@@ -47,8 +58,3 @@ print(
(dt_user_end - dt_user_begin).microseconds / 1000,
"msec"
)
"""
print(pantsu.search(keyword='koe no katachi',
lang=["es", "ja"], category=[1, 3]))
"""

6
tests/test_pantsu.py Normal file
View File

@@ -0,0 +1,6 @@
"""
* Pantsu need some serious work
Regular data single_torrent parser not working from other Nyaa alternatives
Needs some work
"""
print("TODO")

58
tests/test_sukebei.py Normal file
View File

@@ -0,0 +1,58 @@
from NyaaPy import SukebeiNyaa
from datetime import datetime
import json
import os
# Creating a folder for test_files
# ! not included in github project.
if not os.path.isdir("test_files"):
os.makedirs("test_files")
nyaa = SukebeiNyaa()
# Get fresh torrents
dt_latest_torrents_begin = datetime.now()
latest_torrents = nyaa.last_uploads(100)
dt_latest_torrents_end = datetime.now()
with open("test_files/sukebei_latest_torrent_test.json", 'w') as f:
json.dump(latest_torrents, f)
# Search some nasty stuff
dt_search_begin = datetime.now()
test_search = nyaa.search("G Senjou no maou")
dt_search_end = datetime.now()
with open("test_files/sukebei_search_test.json", 'w') as f:
json.dump(test_search, f)
# Get first torrent from found torrents
dt_single_torrent_begin = datetime.now()
single_torrent = nyaa.get(test_search[0]["id"])
dt_single_torrent_end = datetime.now()
with open("test_files/sukebei_single_torrent_test.json", 'w') as f:
json.dump(single_torrent, f)
dt_user_begin = datetime.now()
user_torrents = nyaa.get_user("RUNBKK")
dt_user_end = datetime.now()
with open("test_files/sukebei_single_user_test.json", 'w') as f:
json.dump(user_torrents, f)
print(
"Latest torrents time:",
(dt_latest_torrents_end - dt_latest_torrents_begin).microseconds / 1000,
"msec")
print(
"Test search time:",
(dt_search_end - dt_search_begin).microseconds / 1000,
"msec"
)
print(
"Single torrent time:",
(dt_single_torrent_end - dt_single_torrent_begin).microseconds / 1000,
"msec"
)
print(
"Single user time:",
(dt_user_end - dt_user_begin).microseconds / 1000,
"msec"
)