dev improvements
This commit is contained in:
Juanjo Salvador
108
NyaaPy/nyaa.py
108
NyaaPy/nyaa.py
@@ -1,54 +1,54 @@
|
||||
import requests
|
||||
import urllib.parse
|
||||
from bs4 import BeautifulSoup
|
||||
from NyaaPy.utils import 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))
|
||||
|
||||
soup = BeautifulSoup(r.text, 'html.parser')
|
||||
rows = soup.select('table tr')
|
||||
|
||||
return utils.parse_nyaa(rows, limit=None)
|
||||
|
||||
def get(self, id):
|
||||
r = requests.get("{}/view/{}".format(self.URI, id))
|
||||
soup = BeautifulSoup(r.text, 'html.parser')
|
||||
content = soup.findAll("div", {"class": "panel", "id": None})
|
||||
|
||||
return utils.parse_single(content)
|
||||
|
||||
def get_user(self, username):
|
||||
r = requests.get("{}/user/{}".format(self.URI, username))
|
||||
soup = BeautifulSoup(r.text, 'html.parser')
|
||||
|
||||
return utils.parse_nyaa(soup.select('table tr'), limit=None)
|
||||
|
||||
def news(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)
|
||||
import requests
|
||||
import urllib.parse
|
||||
from bs4 import BeautifulSoup
|
||||
from NyaaPy import 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))
|
||||
|
||||
soup = BeautifulSoup(r.text, 'html.parser')
|
||||
rows = soup.select('table tr')
|
||||
|
||||
return utils.parse_nyaa(rows, limit=None)
|
||||
|
||||
def get(self, id):
|
||||
r = requests.get("{}/view/{}".format(self.URI, id))
|
||||
soup = BeautifulSoup(r.text, 'html.parser')
|
||||
content = soup.findAll("div", {"class": "panel", "id": None})
|
||||
|
||||
return utils.parse_single(content)
|
||||
|
||||
def get_user(self, username):
|
||||
r = requests.get("{}/user/{}".format(self.URI, username))
|
||||
soup = BeautifulSoup(r.text, 'html.parser')
|
||||
|
||||
return utils.parse_nyaa(soup.select('table tr'), limit=None)
|
||||
|
||||
def news(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)
|
||||
|
||||
@@ -1,40 +1,40 @@
|
||||
import requests
|
||||
from NyaaPy.utils import utils
|
||||
|
||||
class Pantsu:
|
||||
|
||||
def __init__(self):
|
||||
self.BASE_URL = "https://nyaa.pantsu.cat/api"
|
||||
|
||||
# Torrents - GET
|
||||
def search(self, keyword, **kwargs):
|
||||
request = requests.get("{}/search{}".format(
|
||||
self.BASE_URL, utils.query_builder(keyword, kwargs)))
|
||||
return request.json()
|
||||
|
||||
def view(self, item_id):
|
||||
request = requests.get("{}/view/{}".format(self.BASE_URL, item_id))
|
||||
|
||||
return request.json()
|
||||
|
||||
# Torrents - POST
|
||||
|
||||
def upload(self):
|
||||
return "Work in progress!"
|
||||
|
||||
def update(self):
|
||||
return "Work in progress!"
|
||||
|
||||
# Users
|
||||
|
||||
def login(self, username, password):
|
||||
login = requests.post("{}/login/".format(
|
||||
self.BASE_URL), data={'username': username, 'password': password})
|
||||
|
||||
return login.json()
|
||||
|
||||
def profile(self, user_id):
|
||||
profile = requests.post("{}/profile/".format(
|
||||
self.BASE_URL), data={'id': user_id})
|
||||
|
||||
return profile.json()
|
||||
import requests
|
||||
from NyaaPy import utils
|
||||
|
||||
class Pantsu:
|
||||
|
||||
def __init__(self):
|
||||
self.BASE_URL = "https://nyaa.pantsu.cat/api"
|
||||
|
||||
# Torrents - GET
|
||||
def search(self, keyword, **kwargs):
|
||||
request = requests.get("{}/search{}".format(
|
||||
self.BASE_URL, utils.query_builder(keyword, kwargs)))
|
||||
return request.json()
|
||||
|
||||
def view(self, item_id):
|
||||
request = requests.get("{}/view/{}".format(self.BASE_URL, item_id))
|
||||
|
||||
return request.json()
|
||||
|
||||
# Torrents - POST
|
||||
|
||||
def upload(self):
|
||||
return "Work in progress!"
|
||||
|
||||
def update(self):
|
||||
return "Work in progress!"
|
||||
|
||||
# Users
|
||||
|
||||
def login(self, username, password):
|
||||
login = requests.post("{}/login/".format(
|
||||
self.BASE_URL), data={'username': username, 'password': password})
|
||||
|
||||
return login.json()
|
||||
|
||||
def profile(self, user_id):
|
||||
profile = requests.post("{}/profile/".format(
|
||||
self.BASE_URL), data={'id': user_id})
|
||||
|
||||
return profile.json()
|
||||
|
||||
@@ -1,84 +1,84 @@
|
||||
import requests
|
||||
from bs4 import BeautifulSoup
|
||||
from NyaaPy.utils import utils
|
||||
|
||||
class SukebeiNyaa:
|
||||
def search(self, 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(
|
||||
"http://sukebei.nyaa.si", filters, category, subcategory,
|
||||
keyword, page))
|
||||
else:
|
||||
r = requests.get("{}/?f={}&c={}_{}&q={}".format(
|
||||
"http://sukebei.nyaa.si", filters, category, subcategory,
|
||||
keyword))
|
||||
|
||||
soup = BeautifulSoup(r.text, 'html.parser')
|
||||
rows = soup.select('table tr')
|
||||
|
||||
return utils.parse_nyaa(rows, limit=None)
|
||||
|
||||
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})
|
||||
|
||||
return utils.parse_single(content)
|
||||
|
||||
def get_user(self, 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 news(self, 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)
|
||||
|
||||
|
||||
class SukebeiPantsu:
|
||||
BASE_URL = "https://sukebei.pantsu.cat/api"
|
||||
|
||||
# Torrents - GET
|
||||
def search(self, keyword, **kwargs):
|
||||
request = requests.get("{}/search{}".format(
|
||||
SukebeiPantsu.BASE_URL, utils.query_builder(keyword, kwargs)))
|
||||
|
||||
return request.json()
|
||||
|
||||
def view(self, item_id):
|
||||
request = requests.get("{}/view/{}".format(
|
||||
SukebeiPantsu.BASE_URL, item_id))
|
||||
|
||||
return request.json()
|
||||
|
||||
# Torrents - POST
|
||||
|
||||
def upload(self):
|
||||
return "Work in progress!"
|
||||
|
||||
def update(self):
|
||||
return "Work in progress!"
|
||||
|
||||
# Users
|
||||
|
||||
def login(self, username, password):
|
||||
login = requests.post("{}/login/".format(
|
||||
SukebeiPantsu.BASE_URL), data={'username': username,
|
||||
'password': password})
|
||||
|
||||
return login.json()
|
||||
|
||||
def profile(self, user_id):
|
||||
profile = requests.post("{}/profile/".format(
|
||||
SukebeiPantsu.BASE_URL), data={'id': user_id})
|
||||
|
||||
return profile.json()
|
||||
import requests
|
||||
from bs4 import BeautifulSoup
|
||||
from NyaaPy import utils
|
||||
|
||||
class SukebeiNyaa:
|
||||
def search(self, 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(
|
||||
"http://sukebei.nyaa.si", filters, category, subcategory,
|
||||
keyword, page))
|
||||
else:
|
||||
r = requests.get("{}/?f={}&c={}_{}&q={}".format(
|
||||
"http://sukebei.nyaa.si", filters, category, subcategory,
|
||||
keyword))
|
||||
|
||||
soup = BeautifulSoup(r.text, 'html.parser')
|
||||
rows = soup.select('table tr')
|
||||
|
||||
return utils.parse_nyaa(rows, limit=None)
|
||||
|
||||
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})
|
||||
|
||||
return utils.parse_single(content)
|
||||
|
||||
def get_user(self, 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 news(self, 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)
|
||||
|
||||
|
||||
class SukebeiPantsu:
|
||||
BASE_URL = "https://sukebei.pantsu.cat/api"
|
||||
|
||||
# Torrents - GET
|
||||
def search(self, keyword, **kwargs):
|
||||
request = requests.get("{}/search{}".format(
|
||||
SukebeiPantsu.BASE_URL, utils.query_builder(keyword, kwargs)))
|
||||
|
||||
return request.json()
|
||||
|
||||
def view(self, item_id):
|
||||
request = requests.get("{}/view/{}".format(
|
||||
SukebeiPantsu.BASE_URL, item_id))
|
||||
|
||||
return request.json()
|
||||
|
||||
# Torrents - POST
|
||||
|
||||
def upload(self):
|
||||
return "Work in progress!"
|
||||
|
||||
def update(self):
|
||||
return "Work in progress!"
|
||||
|
||||
# Users
|
||||
|
||||
def login(self, username, password):
|
||||
login = requests.post("{}/login/".format(
|
||||
SukebeiPantsu.BASE_URL), data={'username': username,
|
||||
'password': password})
|
||||
|
||||
return login.json()
|
||||
|
||||
def profile(self, user_id):
|
||||
profile = requests.post("{}/profile/".format(
|
||||
SukebeiPantsu.BASE_URL), data={'id': user_id})
|
||||
|
||||
return profile.json()
|
||||
|
||||
506
NyaaPy/utils.py
506
NyaaPy/utils.py
@@ -1,253 +1,253 @@
|
||||
'''
|
||||
Module utils
|
||||
'''
|
||||
|
||||
import re
|
||||
|
||||
def nyaa_categories(b):
|
||||
c = b.replace('/?c=', '')
|
||||
cats = c.split('_')
|
||||
|
||||
cat = cats[0]
|
||||
subcat = cats[1]
|
||||
|
||||
categories = {
|
||||
"1": {
|
||||
"name": "Anime",
|
||||
"subcats": {
|
||||
"1": "Anime Music Video",
|
||||
"2": "English-translated",
|
||||
"3": "Non-English-translated",
|
||||
"4": "Raw"
|
||||
}
|
||||
},
|
||||
"2": {
|
||||
"name": "Audio",
|
||||
"subcats": {
|
||||
"1": "Lossless",
|
||||
"2": "Lossy"
|
||||
}
|
||||
},
|
||||
"3": {
|
||||
"name": "Literature",
|
||||
"subcats": {
|
||||
"1": "English-translated",
|
||||
"2": "Non-English-translated",
|
||||
"3": "Raw"
|
||||
}
|
||||
},
|
||||
"4": {
|
||||
"name": "Live Action",
|
||||
"subcats": {
|
||||
"1": "English-translated",
|
||||
"2": "Idol/Promotional Video",
|
||||
"3": "Non-English-translated",
|
||||
"4": "Raw"
|
||||
}
|
||||
},
|
||||
"5": {
|
||||
"name": "Pictures",
|
||||
"subcats": {
|
||||
"1": "Graphics",
|
||||
"2": "Photos"
|
||||
}
|
||||
},
|
||||
"6": {
|
||||
"name": "Software",
|
||||
"subcats": {
|
||||
"1": "Applications",
|
||||
"2": "Games"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
try:
|
||||
category_name = "{} - {}".format(
|
||||
categories[cat]['name'], categories[cat]['subcats'][subcat])
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
return category_name
|
||||
|
||||
def parse_nyaa(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'):
|
||||
if td.find_all('a'):
|
||||
for link in td.find_all('a'):
|
||||
if link.get('href')[-9:] != '#comments':
|
||||
block.append(link.get('href'))
|
||||
if link.text.rstrip():
|
||||
block.append(link.text)
|
||||
|
||||
if td.text.rstrip():
|
||||
block.append(td.text.rstrip())
|
||||
|
||||
if row.has_attr('class'):
|
||||
if row['class'][0] == 'danger':
|
||||
block.append("remake")
|
||||
elif row['class'][0] == 'success':
|
||||
block.append("trusted")
|
||||
else:
|
||||
block.append("default")
|
||||
|
||||
try:
|
||||
torrent = {
|
||||
'id': block[1].replace("/view/", ""),
|
||||
'category': nyaa_categories(block[0]),
|
||||
'url': "http://nyaa.si{}".format(block[1]),
|
||||
'name': block[2],
|
||||
'download_url': "http://nyaa.si{}".format(block[4]),
|
||||
'magnet': block[5],
|
||||
'size': block[6],
|
||||
'date': block[7],
|
||||
'seeders': block[8],
|
||||
'leechers': block[9],
|
||||
'completed_downloads': block[10],
|
||||
'type': block[11],
|
||||
}
|
||||
|
||||
torrents.append(torrent)
|
||||
except IndexError as ie:
|
||||
pass
|
||||
|
||||
return torrents
|
||||
|
||||
def parse_single(content):
|
||||
torrent = {}
|
||||
data = []
|
||||
torrent_files = []
|
||||
|
||||
for row in content[0].find_all('div', {'class': 'row'}):
|
||||
for div in row.find_all('div', {'class': 'col-md-5'}):
|
||||
data.append(div.text.replace("\n", ""))
|
||||
|
||||
files = content[2].find('div',
|
||||
{'class', 'torrent-file-list'}).find_all('li')
|
||||
|
||||
for file in files:
|
||||
torrent_files.append(file.text)
|
||||
|
||||
torrent['title'] = re.sub('\n|\r|\t', '', content[0].find('h3', {
|
||||
"class": "panel-title"}).text.replace("\n", ""))
|
||||
torrent['category'] = data[0]
|
||||
torrent['uploader'] = data[2]
|
||||
torrent['uploader_profile'] = "https://nyaa.si/user/{}".format(data[2])
|
||||
torrent['website'] = re.sub('\t', '', data[4])
|
||||
torrent['size'] = data[6]
|
||||
torrent['date'] = data[1]
|
||||
torrent['seeders'] = data[3]
|
||||
torrent['leechers'] = data[5]
|
||||
torrent['completed'] = data[7]
|
||||
torrent['hash'] = data[8]
|
||||
torrent['description'] = re.sub('\t', '', content[1].find('div', {
|
||||
'id': 'torrent-description'}).text)
|
||||
torrent['files'] = torrent_files
|
||||
|
||||
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=', '')
|
||||
cats = c.split('_')
|
||||
|
||||
cat = cats[0]
|
||||
subcat = cats[1]
|
||||
|
||||
categories = {
|
||||
"1": {
|
||||
"name": "Art",
|
||||
"subcats": {
|
||||
"1": "Anime",
|
||||
"2": "Doujinshi",
|
||||
"3": "Games",
|
||||
"4": "Manga",
|
||||
"5": "Pictures",
|
||||
}
|
||||
},
|
||||
"2": {
|
||||
"name": "Real Life",
|
||||
"subcats": {
|
||||
"1": "Photobooks & Pictures",
|
||||
"2": "Videos"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
try:
|
||||
category_name = "{} - {}".format(
|
||||
categories[cat]['name'], categories[cat]['subcats'][subcat])
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
return category_name
|
||||
|
||||
# Pantsu Utils
|
||||
def query_builder(q, params):
|
||||
available_params = ["category", "page", "limit", "userID", "fromID",
|
||||
"status", "maxage", "toDate", "fromDate",
|
||||
"dateType", "minSize", "maxSize", "sizeType",
|
||||
"sort", "order", "lang"]
|
||||
query = "?q={}".format(q.replace(" ", "+"))
|
||||
|
||||
for param, value in params.items():
|
||||
if param in available_params:
|
||||
if (param != "category" and param != "status" and
|
||||
param != "lang"):
|
||||
query += "&{}={}".format(param, value)
|
||||
elif param == "category":
|
||||
query += "&c={}_{}".format(value[0], value[1])
|
||||
|
||||
elif param == "status":
|
||||
query += "&s={}".format(value)
|
||||
|
||||
elif param == "lang":
|
||||
for lang in value:
|
||||
query += "&lang={}".format(lang)
|
||||
|
||||
return query
|
||||
'''
|
||||
Module utils
|
||||
'''
|
||||
|
||||
import re
|
||||
|
||||
def nyaa_categories(b):
|
||||
c = b.replace('/?c=', '')
|
||||
cats = c.split('_')
|
||||
|
||||
cat = cats[0]
|
||||
subcat = cats[1]
|
||||
|
||||
categories = {
|
||||
"1": {
|
||||
"name": "Anime",
|
||||
"subcats": {
|
||||
"1": "Anime Music Video",
|
||||
"2": "English-translated",
|
||||
"3": "Non-English-translated",
|
||||
"4": "Raw"
|
||||
}
|
||||
},
|
||||
"2": {
|
||||
"name": "Audio",
|
||||
"subcats": {
|
||||
"1": "Lossless",
|
||||
"2": "Lossy"
|
||||
}
|
||||
},
|
||||
"3": {
|
||||
"name": "Literature",
|
||||
"subcats": {
|
||||
"1": "English-translated",
|
||||
"2": "Non-English-translated",
|
||||
"3": "Raw"
|
||||
}
|
||||
},
|
||||
"4": {
|
||||
"name": "Live Action",
|
||||
"subcats": {
|
||||
"1": "English-translated",
|
||||
"2": "Idol/Promotional Video",
|
||||
"3": "Non-English-translated",
|
||||
"4": "Raw"
|
||||
}
|
||||
},
|
||||
"5": {
|
||||
"name": "Pictures",
|
||||
"subcats": {
|
||||
"1": "Graphics",
|
||||
"2": "Photos"
|
||||
}
|
||||
},
|
||||
"6": {
|
||||
"name": "Software",
|
||||
"subcats": {
|
||||
"1": "Applications",
|
||||
"2": "Games"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
try:
|
||||
category_name = "{} - {}".format(
|
||||
categories[cat]['name'], categories[cat]['subcats'][subcat])
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
return category_name
|
||||
|
||||
def parse_nyaa(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'):
|
||||
if td.find_all('a'):
|
||||
for link in td.find_all('a'):
|
||||
if link.get('href')[-9:] != '#comments':
|
||||
block.append(link.get('href'))
|
||||
if link.text.rstrip():
|
||||
block.append(link.text)
|
||||
|
||||
if td.text.rstrip():
|
||||
block.append(td.text.rstrip())
|
||||
|
||||
if row.has_attr('class'):
|
||||
if row['class'][0] == 'danger':
|
||||
block.append("remake")
|
||||
elif row['class'][0] == 'success':
|
||||
block.append("trusted")
|
||||
else:
|
||||
block.append("default")
|
||||
|
||||
try:
|
||||
torrent = {
|
||||
'id': block[1].replace("/view/", ""),
|
||||
'category': nyaa_categories(block[0]),
|
||||
'url': "http://nyaa.si{}".format(block[1]),
|
||||
'name': block[2],
|
||||
'download_url': "http://nyaa.si{}".format(block[4]),
|
||||
'magnet': block[5],
|
||||
'size': block[6],
|
||||
'date': block[7],
|
||||
'seeders': block[8],
|
||||
'leechers': block[9],
|
||||
'completed_downloads': block[10],
|
||||
'type': block[11],
|
||||
}
|
||||
|
||||
torrents.append(torrent)
|
||||
except IndexError as ie:
|
||||
pass
|
||||
|
||||
return torrents
|
||||
|
||||
def parse_single(content):
|
||||
torrent = {}
|
||||
data = []
|
||||
torrent_files = []
|
||||
|
||||
for row in content[0].find_all('div', {'class': 'row'}):
|
||||
for div in row.find_all('div', {'class': 'col-md-5'}):
|
||||
data.append(div.text.replace("\n", ""))
|
||||
|
||||
files = content[2].find('div',
|
||||
{'class', 'torrent-file-list'}).find_all('li')
|
||||
|
||||
for file in files:
|
||||
torrent_files.append(file.text)
|
||||
|
||||
torrent['title'] = re.sub('\n|\r|\t', '', content[0].find('h3', {
|
||||
"class": "panel-title"}).text.replace("\n", ""))
|
||||
torrent['category'] = data[0]
|
||||
torrent['uploader'] = data[2]
|
||||
torrent['uploader_profile'] = "https://nyaa.si/user/{}".format(data[2])
|
||||
torrent['website'] = re.sub('\t', '', data[4])
|
||||
torrent['size'] = data[6]
|
||||
torrent['date'] = data[1]
|
||||
torrent['seeders'] = data[3]
|
||||
torrent['leechers'] = data[5]
|
||||
torrent['completed'] = data[7]
|
||||
torrent['hash'] = data[8]
|
||||
torrent['description'] = re.sub('\t', '', content[1].find('div', {
|
||||
'id': 'torrent-description'}).text)
|
||||
torrent['files'] = torrent_files
|
||||
|
||||
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=', '')
|
||||
cats = c.split('_')
|
||||
|
||||
cat = cats[0]
|
||||
subcat = cats[1]
|
||||
|
||||
categories = {
|
||||
"1": {
|
||||
"name": "Art",
|
||||
"subcats": {
|
||||
"1": "Anime",
|
||||
"2": "Doujinshi",
|
||||
"3": "Games",
|
||||
"4": "Manga",
|
||||
"5": "Pictures",
|
||||
}
|
||||
},
|
||||
"2": {
|
||||
"name": "Real Life",
|
||||
"subcats": {
|
||||
"1": "Photobooks & Pictures",
|
||||
"2": "Videos"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
try:
|
||||
category_name = "{} - {}".format(
|
||||
categories[cat]['name'], categories[cat]['subcats'][subcat])
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
return category_name
|
||||
|
||||
# Pantsu Utils
|
||||
def query_builder(q, params):
|
||||
available_params = ["category", "page", "limit", "userID", "fromID",
|
||||
"status", "maxage", "toDate", "fromDate",
|
||||
"dateType", "minSize", "maxSize", "sizeType",
|
||||
"sort", "order", "lang"]
|
||||
query = "?q={}".format(q.replace(" ", "+"))
|
||||
|
||||
for param, value in params.items():
|
||||
if param in available_params:
|
||||
if (param != "category" and param != "status" and
|
||||
param != "lang"):
|
||||
query += "&{}={}".format(param, value)
|
||||
elif param == "category":
|
||||
query += "&c={}_{}".format(value[0], value[1])
|
||||
|
||||
elif param == "status":
|
||||
query += "&s={}".format(value)
|
||||
|
||||
elif param == "lang":
|
||||
for lang in value:
|
||||
query += "&lang={}".format(lang)
|
||||
|
||||
return query
|
||||
|
||||
Reference in New Issue
Block a user