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. 145
      src/searchengine/nova/engines/piratebay.py
  2. 2
      src/searchengine/nova/engines/versions.txt
  3. 143
      src/searchengine/nova3/engines/piratebay.py
  4. 2
      src/searchengine/nova3/engines/versions.txt

145
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:
@ -27,93 +28,111 @@
# 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):
self.results = []
self.parser = self.SimpleSGMLParser(self.results, self.url)
def download_torrent(self, info): def download_torrent(self, info):
print download_file(info) print(download_file(info))
class SimpleSGMLParser(sgmllib.SGMLParser): class MyHtmlParseWithBlackJack(HTMLParser):
def __init__(self, results, url, *args): def __init__(self, results, url):
sgmllib.SGMLParser.__init__(self) HTMLParser.__init__(self)
self.td_counter = None
self.current_item = None
self.results = results
self.url = url self.url = url
self.code = 0 self.results = results
self.in_name = None 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 }
def start_a(self, attr): def handle_tag_a_ref(self, attrs):
params = dict(attr) params = dict(attrs)
#1
if params['href'].startswith('/torrent/'): if params['href'].startswith('/torrent/'):
get_id = params['href'].split('/')[2]
if not get_id in PREVIOUS_IDS:
self.current_item = {} self.current_item = {}
self.td_counter = 0
self.current_item['desc_link'] = self.url + params['href'].strip() self.current_item['desc_link'] = self.url + params['href'].strip()
self.in_name = True self.current_item['name'] = params['title'][12:].strip()
self.current_item['id'] = params['href'].split('/')[2] self.current_item['id'] = get_id
elif params['href'].startswith('magnet:'): #2
self.current_item['link']=params['href'].strip() elif (not self.current_item is None) and (params['href'].startswith('magnet:')):
self.in_name = False self.current_item['link'] = params['href'].strip()
def handle_data(self, data): def handle_tag_font_size(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'): #3
self.current_item['name'] = '' if params['class'] == "detDesc":
self.current_item['name']+= data.strip() self.size_found = True
def handle_tag_td_sl(self, attrs):
if not self.current_item is None:
params = dict(attrs)
if not self.current_item is None:
if self.seed_found:
#5
self.current_item['leech'] = ''
self.leech_found = True
self.seed_found = False
else: else:
#Parse size #4
if 'Size' in data:
self.current_item['size'] = data[data.index("Size")+5:]
self.current_item['size'] = self.current_item['size'][:self.current_item['size'].index(',')]
elif self.td_counter == 1:
if not self.current_item.has_key('seeds'):
self.current_item['seeds'] = '' self.current_item['seeds'] = ''
self.current_item['seeds']+= data.strip() self.seed_found = True
elif self.td_counter == 2:
if not self.current_item.has_key('leech'): def handle_starttag(self, tag, attrs):
self.current_item['leech'] = '' if tag in self.dispatcher:
self.current_item['leech']+= data.strip() self.dispatcher[tag](attrs)
def start_td(self,attr): def handle_data(self, data):
if isinstance(self.td_counter,int): if not self.current_item is None:
self.td_counter += 1 if self.size_found:
if self.td_counter > 3: #with utf-8 you're going to have something like that: ['Uploaded', '10-02'], ['15:31,', 'Size', '240.34'], ['MiB,', 'ULed', 'by']
self.td_counter = None temp = data.split()
# Display item if 'Size' in temp:
if self.current_item: sizeIn = temp.index('Size')
if self.current_item['id'] in PREVIOUS_IDS: self.current_item['size'] = temp[sizeIn + 1]
self.results = [] self.size_found = False
self.reset() self.unit_found = True
return elif self.unit_found:
temp = data.split()
self.current_item['size'] = ' '.join((self.current_item['size'], temp[0]))
self.unit_found = False
elif self.seed_found:
self.current_item['seeds'] += data.rstrip()
elif self.leech_found:
self.current_item['leech'] += data.rstrip()
self.current_item['engine_url'] = self.url self.current_item['engine_url'] = self.url
if not self.current_item['seeds'].isdigit():
self.current_item['seeds'] = 0
if not self.current_item['leech'].isdigit():
self.current_item['leech'] = 0
prettyPrinter(self.current_item) prettyPrinter(self.current_item)
PREVIOUS_IDS.add(self.current_item['id']) PREVIOUS_IDS.add(self.current_item['id'])
self.results.append('a') self.results.append('a')
self.current_item = None
self.size_found = False
self.unit_found = False
self.seed_found = False
self.leech_found = False
def search(self, what, cat='all'): def search(self, what, cat='all'):
ret = [] ret = []
i = 0 i = 0
order = 'se' while i < 11:
while True and i<11:
results = [] results = []
parser = self.SimpleSGMLParser(results, self.url) parser = self.MyHtmlParseWithBlackJack(results, self.url)
dat = retrieve_url(self.url+'/search/%s/%d/7/%s' % (what, i, self.supported_categories[cat])) query = '%s/search/%s/%d/99/%s' % (self.url, what, i, self.supported_categories[cat])
parser.feed(dat) dat = urllib2.urlopen(query)
parser.feed(dat.read().decode('utf-8'))
parser.close() parser.close()
if len(results) <= 0: if len(results) <= 0:
break break

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

143
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:
@ -27,93 +28,111 @@
# 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):
self.results = []
self.parser = self.SimpleSGMLParser(self.results, self.url)
def download_torrent(self, info): def download_torrent(self, info):
print(download_file(info)) print(download_file(info))
class SimpleSGMLParser(sgmllib3.SGMLParser): class MyHtmlParseWithBlackJack(HTMLParser):
def __init__(self, results, url, *args): def __init__(self, results, url):
sgmllib3.SGMLParser.__init__(self) super().__init__()
self.td_counter = None
self.current_item = None
self.results = results
self.url = url self.url = url
self.code = 0 self.results = results
self.in_name = None 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 }
def start_a(self, attr): def handle_tag_a_ref(self, attrs):
params = dict(attr) params = dict(attrs)
#1
if params['href'].startswith('/torrent/'): if params['href'].startswith('/torrent/'):
get_id = params['href'].split('/')[2]
if not get_id in PREVIOUS_IDS:
self.current_item = {} self.current_item = {}
self.td_counter = 0
self.current_item['desc_link'] = self.url + params['href'].strip() self.current_item['desc_link'] = self.url + params['href'].strip()
self.in_name = True self.current_item['name'] = params['title'][12:].strip()
self.current_item['id'] = params['href'].split('/')[2] self.current_item['id'] = get_id
elif params['href'].startswith('magnet:'): #2
self.current_item['link']=params['href'].strip() elif (not self.current_item is None) and (params['href'].startswith('magnet:')):
self.in_name = False self.current_item['link'] = params['href'].strip()
def handle_data(self, data): def handle_tag_font_size(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: #3
self.current_item['name'] = '' if params['class'] == "detDesc":
self.current_item['name']+= data.strip() self.size_found = True
def handle_tag_td_sl(self, attrs):
if not self.current_item is None:
params = dict(attrs)
if not self.current_item is None:
if self.seed_found:
#5
self.current_item['leech'] = ''
self.leech_found = True
self.seed_found = False
else: else:
#Parse size #4
if 'Size' in data:
self.current_item['size'] = data[data.index("Size")+5:]
self.current_item['size'] = self.current_item['size'][:self.current_item['size'].index(',')]
elif self.td_counter == 1:
if 'seeds' not in self.current_item:
self.current_item['seeds'] = '' self.current_item['seeds'] = ''
self.current_item['seeds']+= data.strip() self.seed_found = True
elif self.td_counter == 2:
if 'leech' not in self.current_item: def handle_starttag(self, tag, attrs):
self.current_item['leech'] = '' if tag in self.dispatcher:
self.current_item['leech']+= data.strip() self.dispatcher[tag](attrs)
def start_td(self,attr): def handle_data(self, data):
if isinstance(self.td_counter,int): if not self.current_item is None:
self.td_counter += 1 if self.size_found:
if self.td_counter > 3: #with utf-8 you're going to have something like that: ['Uploaded', '10-02'], ['15:31,', 'Size', '240.34'], ['MiB,', 'ULed', 'by']
self.td_counter = None temp = data.split()
# Display item if 'Size' in temp:
if self.current_item: sizeIn = temp.index('Size')
if self.current_item['id'] in PREVIOUS_IDS: self.current_item['size'] = temp[sizeIn + 1]
self.results = [] self.size_found = False
self.reset() self.unit_found = True
return elif self.unit_found:
temp = data.split()
self.current_item['size'] = ' '.join((self.current_item['size'], temp[0]))
self.unit_found = False
elif self.seed_found:
self.current_item['seeds'] += data.rstrip()
elif self.leech_found:
self.current_item['leech'] += data.rstrip()
self.current_item['engine_url'] = self.url self.current_item['engine_url'] = self.url
if not self.current_item['seeds'].isdigit():
self.current_item['seeds'] = 0
if not self.current_item['leech'].isdigit():
self.current_item['leech'] = 0
prettyPrinter(self.current_item) prettyPrinter(self.current_item)
PREVIOUS_IDS.add(self.current_item['id']) PREVIOUS_IDS.add(self.current_item['id'])
self.results.append('a') self.results.append('a')
self.current_item = None
self.size_found = False
self.unit_found = False
self.seed_found = False
self.leech_found = False
def search(self, what, cat='all'): def search(self, what, cat='all'):
ret = [] ret = []
i = 0 i = 0
order = 'se' while i < 11:
while True and i<11:
results = [] results = []
parser = self.SimpleSGMLParser(results, self.url) parser = self.MyHtmlParseWithBlackJack(results, self.url)
dat = retrieve_url(self.url+'/search/%s/%d/7/%s' % (what, i, self.supported_categories[cat])) query = '%s/search/%s/%d/99/%s' % (self.url, what, i, self.supported_categories[cat])
parser.feed(dat) dat = urllib.request.urlopen(query)
parser.feed(dat.read().decode('utf-8'))
parser.close() parser.close()
if len(results) <= 0: if len(results) <= 0:
break break

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