def search(keyword, **kwargs):
category = kwargs.get('category', 0)
subcategory = kwargs.get('subcategory', 0)
filters = kwargs.get('filters', 0)
page = kwargs.get('page', 0)
if page > 0:
r = requests.get("{}/?f={}&c={}_{}&q={}&p={}".format(
Nyaa.URI, filters, category, subcategory, keyword, page))
else:
r = requests.get("{}/?f={}&c={}_{}&q={}".format(
Nyaa.URI, filters, category, subcategory, keyword))
soup = BeautifulSoup(r.text, 'html.parser')
rows = soup.select('table tr')
return utils.parse_nyaa(rows, limit=None)
def get_raw_data(self, content=None):
'''
:param content:
:return:
'''
raw_data = RAWDataInstance()
soup = BeautifulSoup(content, 'html.parser')
try:
ttable = soup.select('table tr')
if ttable != []:
try:
dict_result = Utils.parse_nyaa(ttable, limit=None)
for item in dict_result:
size = item['size']
if 'MiB' in size:
size = size.replace('MiB', 'MB')
size = float(size[:-2])
elif 'GiB' in size:
size = size.replace('GiB', 'GB')
size = float(size[:-2]) * 1000
seed = str(item['seeders'])
if seed == '0':
seed = '1'
leech = str(item['leechers'])
if leech == '0':
leech = '1'
magnet_link = item['magnet']
raw_data.add_new_row(size, seed, leech, magnet_link)
self.logger.debug('{0} New Entry Raw Values: {1:7} {2:>4}/{3:4} {4}'.format(
self.name, str(size), str(seed), str(leech), magnet_link))
except Exception as err:
raise WebScraperParseError(self.name, 'ParseError: unable to retrieve values: {0}'.format(err),
traceback.format_exc())
except Exception as err:
raise WebScraperContentError(self.name, 'ContentError: unable to retrieve values {0}'.format(err),
traceback.format_exc())
return raw_data
def search(keyword, **kwargs):
request = requests.get("{}/search{}".format(
SukebeiPantsu.BASE_URL, utils.query_builder(keyword, kwargs)))
return request.json()
def news(number_of_results):
r = requests.get("http://sukebei.nyaa.si/")
soup = BeautifulSoup(r.text, 'html.parser')
rows = soup.select('table tr')
return utils.parse_sukebei(rows, limit=number_of_results + 1)
def get_user(username):
r = requests.get("http://sukebei.nyaa.si/user/{}".format(username))
soup = BeautifulSoup(r.text, 'html.parser')
return utils.parse_nyaa(soup.select('table tr'), limit=None)
def get(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})
return utils.parse_single(content)
def news(number_of_results):
r = requests.get(Nyaa.URI)
soup = BeautifulSoup(r.text, 'html.parser')
rows = soup.select('table tr')
return utils.parse_nyaa(rows, limit=number_of_results + 1)
def get_user(username):
r = requests.get("{}/user/{}".format(Nyaa.URI, username))
soup = BeautifulSoup(r.text, 'html.parser')
return utils.parse_nyaa(soup.select('table tr'), limit=None)
import requests
import urllib.parse
from bs4 import BeautifulSoup
from NyaaPy.utils import Utils
utils = Utils()
class Nyaa:
def __init__(self):
self.URI = "http://nyaa.si"
def search(self, keyword, **kwargs):
user = kwargs.get('user', None)
category = kwargs.get('category', 0)
subcategory = kwargs.get('subcategory', 0)
filters = kwargs.get('filters', 0)
page = kwargs.get('page', 0)
if user:
user_uri = "user/{}".format(user)
else:
user_uri = ""
if page > 0:
r = requests.get("{}/{}?f={}&c={}_{}&q={}&p={}".format(
self.URI, user_uri, filters, category, subcategory, keyword,
page))
else:
r = requests.get("{}/{}?f={}&c={}_{}&q={}".format(
self.URI, user_uri, filters, category, subcategory, keyword))
