d4708
/
qBittorrent
mirror of https://github.com/d47081/qBittorrent.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
Browse Source

Pirate bay search engine update

adaptive-webui-19844
DoumanAsh 10 years ago
parent
0e0e8f7c27
commit
a62e30ea88
4 changed files with 204 additions and 166 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Unified View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 183
      src/searchengine/nova/engines/piratebay.py
  2. 2
      src/searchengine/nova/engines/versions.txt
  3. 183
      src/searchengine/nova3/engines/piratebay.py
  4. 2
      src/searchengine/nova3/engines/versions.txt

183
src/searchengine/nova/engines/piratebay.py
Unescape View File

@ -1,6 +1,7 @@
#VERSION: 1.53 #VERSION: 2.00
#AUTHORS: Fabien Devaux (fab@gnux.info) #AUTHORS: Fabien Devaux (fab@gnux.info)
#CONTRIBUTORS: Christophe Dumez (chris@qbittorrent.org) #CONTRIBUTORS: Christophe Dumez (chris@qbittorrent.org)
# Arthur (custparasite@gmx.se)
# Redistribution and use in source and binary forms, with or without # Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met: # modification, are permitted provided that the following conditions are met:
@ -27,94 +28,112 @@
# POSSIBILITY OF SUCH DAMAGE. # POSSIBILITY OF SUCH DAMAGE.
from novaprinter import prettyPrinter from novaprinter import prettyPrinter
import sgmllib from HTMLParser import HTMLParser
from helpers import retrieve_url, download_file from helpers import download_file
import urllib2
PREVIOUS_IDS = set() PREVIOUS_IDS = set()
class piratebay(object): class piratebay(object):
url = 'https://thepiratebay.se' url = 'http://thepiratebay.se'
name = 'The Pirate Bay' name = 'The Pirate Bay'
supported_categories = {'all': '0', 'movies': '200', 'music': '100', 'games': '400', 'software': '300'} supported_categories = {'all': '0', 'music': '100', 'movies': '200', 'games': '400', 'software': '300'}
def __init__(self): def download_torrent(self, info):
self.results = [] print(download_file(info))
self.parser = self.SimpleSGMLParser(self.results, self.url)
def download_torrent(self, info): class MyHtmlParseWithBlackJack(HTMLParser):
print download_file(info) def __init__(self, results, url):
HTMLParser.__init__(self)
self.url = url
self.results = results
self.current_item = None
self.size_found = False
self.unit_found = False
self.seed_found = False
self.skip_td = False
self.leech_found = False
self.dispatcher = {'a' : self.handle_tag_a_ref,
'font' : self.handle_tag_font_size,
'td' : self.handle_tag_td_sl }
class SimpleSGMLParser(sgmllib.SGMLParser): def handle_tag_a_ref(self, attrs):
def __init__(self, results, url, *args): params = dict(attrs)
sgmllib.SGMLParser.__init__(self) #1
self.td_counter = None if params['href'].startswith('/torrent/'):
self.current_item = None get_id = params['href'].split('/')[2]
self.results = results if not get_id in PREVIOUS_IDS:
self.url = url self.current_item = {}
self.code = 0 self.current_item['desc_link'] = self.url + params['href'].strip()
self.in_name = None self.current_item['name'] = params['title'][12:].strip()
self.current_item['id'] = get_id
#2
elif (not self.current_item is None) and (params['href'].startswith('magnet:')):
self.current_item['link'] = params['href'].strip()
def start_a(self, attr): def handle_tag_font_size(self, attrs):
params = dict(attr) if not self.current_item is None:
if params['href'].startswith('/torrent/'): params = dict(attrs)
self.current_item = {} #3
self.td_counter = 0 if params['class'] == "detDesc":
self.current_item['desc_link'] = self.url + params['href'].strip() self.size_found = True
self.in_name = True
self.current_item['id'] = params['href'].split('/')[2]
elif params['href'].startswith('magnet:'):
self.current_item['link']=params['href'].strip()
self.in_name = False
def handle_data(self, data): def handle_tag_td_sl(self, attrs):
if self.td_counter == 0: if not self.current_item is None:
if self.in_name: params = dict(attrs)
if not self.current_item.has_key('name'): if not self.current_item is None:
self.current_item['name'] = '' if self.seed_found:
self.current_item['name']+= data.strip() #5
else: self.current_item['leech'] = ''
#Parse size self.leech_found = True
if 'Size' in data: self.seed_found = False
self.current_item['size'] = data[data.index("Size")+5:] else:
self.current_item['size'] = self.current_item['size'][:self.current_item['size'].index(',')] #4
elif self.td_counter == 1: self.current_item['seeds'] = ''
if not self.current_item.has_key('seeds'): self.seed_found = True
self.current_item['seeds'] = ''
self.current_item['seeds']+= data.strip()
elif self.td_counter == 2:
if not self.current_item.has_key('leech'):
self.current_item['leech'] = ''
self.current_item['leech']+= data.strip()
def start_td(self,attr): def handle_starttag(self, tag, attrs):
if isinstance(self.td_counter,int): if tag in self.dispatcher:
self.td_counter += 1 self.dispatcher[tag](attrs)
if self.td_counter > 3:
self.td_counter = None def handle_data(self, data):
# Display item if not self.current_item is None:
if self.current_item: if self.size_found:
if self.current_item['id'] in PREVIOUS_IDS: #with utf-8 you're going to have something like that: ['Uploaded', '10-02'], ['15:31,', 'Size', '240.34'], ['MiB,', 'ULed', 'by']
self.results = [] temp = data.split()
self.reset() if 'Size' in temp:
return sizeIn = temp.index('Size')
self.current_item['engine_url'] = self.url self.current_item['size'] = temp[sizeIn + 1]
if not self.current_item['seeds'].isdigit(): self.size_found = False
self.current_item['seeds'] = 0 self.unit_found = True
if not self.current_item['leech'].isdigit(): elif self.unit_found:
self.current_item['leech'] = 0 temp = data.split()
prettyPrinter(self.current_item) self.current_item['size'] = ' '.join((self.current_item['size'], temp[0]))
PREVIOUS_IDS.add(self.current_item['id']) self.unit_found = False
self.results.append('a') elif self.seed_found:
def search(self, what, cat='all'): self.current_item['seeds'] += data.rstrip()
ret = [] elif self.leech_found:
i = 0 self.current_item['leech'] += data.rstrip()
order = 'se' self.current_item['engine_url'] = self.url
while True and i<11: prettyPrinter(self.current_item)
results = [] PREVIOUS_IDS.add(self.current_item['id'])
parser = self.SimpleSGMLParser(results, self.url) self.results.append('a')
dat = retrieve_url(self.url+'/search/%s/%d/7/%s' % (what, i, self.supported_categories[cat])) self.current_item = None
parser.feed(dat) self.size_found = False
parser.close() self.unit_found = False
if len(results) <= 0: self.seed_found = False
break self.leech_found = False
i += 1
def search(self, what, cat='all'):
ret = []
i = 0
while i < 11:
results = []
parser = self.MyHtmlParseWithBlackJack(results, self.url)
query = '%s/search/%s/%d/99/%s' % (self.url, what, i, self.supported_categories[cat])
dat = urllib2.urlopen(query)
parser.feed(dat.read().decode('utf-8'))
parser.close()
if len(results) <= 0:
break
i += 1

2
src/searchengine/nova/engines/versions.txt
Unescape View File

@ -1,6 +1,6 @@
torrentreactor: 1.33 torrentreactor: 1.33
mininova: 1.50 mininova: 1.50
piratebay: 1.53 piratebay: 2.00
vertor: 1.3 vertor: 1.3
extratorrent: 1.2 extratorrent: 1.2
kickasstorrents: 1.24 kickasstorrents: 1.24

183
src/searchengine/nova3/engines/piratebay.py
Unescape View File

@ -1,6 +1,7 @@
#VERSION: 1.53 #VERSION: 2.00
#AUTHORS: Fabien Devaux (fab@gnux.info) #AUTHORS: Fabien Devaux (fab@gnux.info)
#CONTRIBUTORS: Christophe Dumez (chris@qbittorrent.org) #CONTRIBUTORS: Christophe Dumez (chris@qbittorrent.org)
# Arthur (custparasite@gmx.se)
# Redistribution and use in source and binary forms, with or without # Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met: # modification, are permitted provided that the following conditions are met:
@ -27,94 +28,112 @@
# POSSIBILITY OF SUCH DAMAGE. # POSSIBILITY OF SUCH DAMAGE.
from novaprinter import prettyPrinter from novaprinter import prettyPrinter
import sgmllib3 from html.parser import HTMLParser
from helpers import retrieve_url, download_file from helpers import download_file
import urllib.request
PREVIOUS_IDS = set() PREVIOUS_IDS = set()
class piratebay(object): class piratebay(object):
url = 'https://thepiratebay.se' url = 'http://thepiratebay.se'
name = 'The Pirate Bay' name = 'The Pirate Bay'
supported_categories = {'all': '0', 'movies': '200', 'music': '100', 'games': '400', 'software': '300'} supported_categories = {'all': '0', 'music': '100', 'movies': '200', 'games': '400', 'software': '300'}
def __init__(self): def download_torrent(self, info):
self.results = [] print(download_file(info))
self.parser = self.SimpleSGMLParser(self.results, self.url)
def download_torrent(self, info): class MyHtmlParseWithBlackJack(HTMLParser):
print(download_file(info)) def __init__(self, results, url):
super().__init__()
self.url = url
self.results = results
self.current_item = None
self.size_found = False
self.unit_found = False
self.seed_found = False
self.skip_td = False
self.leech_found = False
self.dispatcher = {'a' : self.handle_tag_a_ref,
'font' : self.handle_tag_font_size,
'td' : self.handle_tag_td_sl }
class SimpleSGMLParser(sgmllib3.SGMLParser): def handle_tag_a_ref(self, attrs):
def __init__(self, results, url, *args): params = dict(attrs)
sgmllib3.SGMLParser.__init__(self) #1
self.td_counter = None if params['href'].startswith('/torrent/'):
self.current_item = None get_id = params['href'].split('/')[2]
self.results = results if not get_id in PREVIOUS_IDS:
self.url = url self.current_item = {}
self.code = 0 self.current_item['desc_link'] = self.url + params['href'].strip()
self.in_name = None self.current_item['name'] = params['title'][12:].strip()
self.current_item['id'] = get_id
#2
elif (not self.current_item is None) and (params['href'].startswith('magnet:')):
self.current_item['link'] = params['href'].strip()
def start_a(self, attr): def handle_tag_font_size(self, attrs):
params = dict(attr) if not self.current_item is None:
if params['href'].startswith('/torrent/'): params = dict(attrs)
self.current_item = {} #3
self.td_counter = 0 if params['class'] == "detDesc":
self.current_item['desc_link'] = self.url + params['href'].strip() self.size_found = True
self.in_name = True
self.current_item['id'] = params['href'].split('/')[2]
elif params['href'].startswith('magnet:'):
self.current_item['link']=params['href'].strip()
self.in_name = False
def handle_data(self, data): def handle_tag_td_sl(self, attrs):
if self.td_counter == 0: if not self.current_item is None:
if self.in_name: params = dict(attrs)
if 'name' not in self.current_item: if not self.current_item is None:
self.current_item['name'] = '' if self.seed_found:
self.current_item['name']+= data.strip() #5
else: self.current_item['leech'] = ''
#Parse size self.leech_found = True
if 'Size' in data: self.seed_found = False
self.current_item['size'] = data[data.index("Size")+5:] else:
self.current_item['size'] = self.current_item['size'][:self.current_item['size'].index(',')] #4
elif self.td_counter == 1: self.current_item['seeds'] = ''
if 'seeds' not in self.current_item: self.seed_found = True
self.current_item['seeds'] = ''
self.current_item['seeds']+= data.strip()
elif self.td_counter == 2:
if 'leech' not in self.current_item:
self.current_item['leech'] = ''
self.current_item['leech']+= data.strip()
def start_td(self,attr): def handle_starttag(self, tag, attrs):
if isinstance(self.td_counter,int): if tag in self.dispatcher:
self.td_counter += 1 self.dispatcher[tag](attrs)
if self.td_counter > 3:
self.td_counter = None def handle_data(self, data):
# Display item if not self.current_item is None:
if self.current_item: if self.size_found:
if self.current_item['id'] in PREVIOUS_IDS: #with utf-8 you're going to have something like that: ['Uploaded', '10-02'], ['15:31,', 'Size', '240.34'], ['MiB,', 'ULed', 'by']
self.results = [] temp = data.split()
self.reset() if 'Size' in temp:
return sizeIn = temp.index('Size')
self.current_item['engine_url'] = self.url self.current_item['size'] = temp[sizeIn + 1]
if not self.current_item['seeds'].isdigit(): self.size_found = False
self.current_item['seeds'] = 0 self.unit_found = True
if not self.current_item['leech'].isdigit(): elif self.unit_found:
self.current_item['leech'] = 0 temp = data.split()
prettyPrinter(self.current_item) self.current_item['size'] = ' '.join((self.current_item['size'], temp[0]))
PREVIOUS_IDS.add(self.current_item['id']) self.unit_found = False
self.results.append('a') elif self.seed_found:
def search(self, what, cat='all'): self.current_item['seeds'] += data.rstrip()
ret = [] elif self.leech_found:
i = 0 self.current_item['leech'] += data.rstrip()
order = 'se' self.current_item['engine_url'] = self.url
while True and i<11: prettyPrinter(self.current_item)
results = [] PREVIOUS_IDS.add(self.current_item['id'])
parser = self.SimpleSGMLParser(results, self.url) self.results.append('a')
dat = retrieve_url(self.url+'/search/%s/%d/7/%s' % (what, i, self.supported_categories[cat])) self.current_item = None
parser.feed(dat) self.size_found = False
parser.close() self.unit_found = False
if len(results) <= 0: self.seed_found = False
break self.leech_found = False
i += 1
def search(self, what, cat='all'):
ret = []
i = 0
while i < 11:
results = []
parser = self.MyHtmlParseWithBlackJack(results, self.url)
query = '%s/search/%s/%d/99/%s' % (self.url, what, i, self.supported_categories[cat])
dat = urllib.request.urlopen(query)
parser.feed(dat.read().decode('utf-8'))
parser.close()
if len(results) <= 0:
break
i += 1

2
src/searchengine/nova3/engines/versions.txt
Unescape View File

@ -1,6 +1,6 @@
torrentreactor: 1.33 torrentreactor: 1.33
mininova: 1.50 mininova: 1.50
piratebay: 1.53 piratebay: 2.00
vertor: 1.3 vertor: 1.3
extratorrent: 1.2 extratorrent: 1.2
kickasstorrents: 1.24 kickasstorrents: 1.24

Write Preview
Loading…
Cancel
Save