def search(self, what, cat="all"):
""" Performs search """
query = "".join(
(
self.url,
"/index.php?page=torrents&search=",
what,
"&category=",
self.supported_categories.get(cat, "0"),
"&active=1",
)
)
get_table = re_compile('(?s)<table\sclass="lista".*>(.*)</table>')
data = get_table.search(retrieve_url(query)).group(0)
# extract first ten pages of next results
next_pages = re_compile('(?m)<option value="(.*)">[0-9]+</option>')
next_pages = ["".join((self.url, page)) for page in next_pages.findall(data)[:10]]
parser = self.MyHtmlParseWithBlackJack(self.url)
parser.feed(data)
parser.close()
for page in next_pages:
parser.feed(get_table.search(retrieve_url(page)).group(0))
parser.close()
def search(self, what, cat='all'):
""" Performs search """
#prepare query
cat = self.supported_categories[cat.lower()]
query = "".join((self.url, "/files/?category=", cat, "&subcategory=All&quality=All&seeded=2&external=2&query=", what, "&uid=0&sort=S"))
data = retrieve_url(query)
add_res_list = re_compile("/files.*page=[0-9]+")
torrent_list = re_compile("start torrent list -->(.*)<!-- end torrent", DOTALL)
data = torrent_list.search(data).group(0)
list_results = add_res_list.findall(data)
parser = self.MyHtmlParseWithBlackJack(self.url)
parser.feed(data)
del data
if list_results:
for search_query in islice((add_res_list.search(result).group(0) for result in list_results[1].split(" | ")), 0, 5):
response = retrieve_url(self.url + search_query)
parser.feed(torrent_list.search(response).group(0))
parser.close()
return
def search(self, what, cat='all'):
# Get token
baseURL = "https://torrentapi.org/pubapi_v2.php?%s"
params = urlencode({'get_token': 'get_token', 'app_id' : 'qbittorrent'})
response = retrieve_url(baseURL % params)
j = json.loads(response)
token = j['token']
sleep(2.1)
# get JSON
what = unquote(what)
category = self.supported_categories[cat]
params = urlencode({
'mode': 'search',
'search_string': what,
'ranked': 0,
'category': category,
'limit': 100,
'sort': 'seeders',
'format': 'json_extended',
'token': token,
'app_id' : 'qbittorrent'
})
response = retrieve_url(baseURL % params)
j = json.loads(response)
for i in j['torrent_results']:
tbytes = float(i['size'])
size = "-1"
if tbytes > 1024 * 1024 * 1024:
size = "%.1f GB" % (tbytes / (1024 * 1024 * 1024))
elif tbytes > 1024 * 1024:
size = "%.1f MB" % (tbytes / (1024 * 1024))
elif tbytes > 1024:
size = "%.1f KB" % (tbytes / 1024)
else:
size = "%.1f B" % (tbytes)
res = dict(link=i['download'],
name=i['title'],
size=size,
seeds=i['seeders'],
leech=i['leechers'],
engine_url=self.url,
desc_link=i['info_page'])
prettyPrinter(res)
def search(self, what, cat='all'):
# Get token
baseURL = "https://torrentapi.org/pubapi_v2.php?%s"
params = urlencode({'get_token': 'get_token'})
response = retrieve_url(baseURL % params)
j = json.loads(response)
token = j['token']
# get JSON
what = unquote(what)
categories = "1;4;14;15;16;17;21;22;42;18;19;41;27;28;29;30;31;32;40;23;24;25;26;33;34;43;44;45;46;47;48"
params = urlencode({'mode': 'search',
'search_string': what,
'ranked': 0,
'category': categories,
'limit': 100,
'sort': 'seeders',
'format': 'json_extended',
'token': token}
)
response = retrieve_url(baseURL % params)
j = json.loads(response)
for i in j['torrent_results']:
tbytes = float(i['size'])
size = "-1"
if tbytes > 1024 * 1024 * 1024:
size = "%.1f GB" % (tbytes / (1024 * 1024 * 1024))
elif tbytes > 1024 * 1024:
size = "%.1f MB" % (tbytes / (1024 * 1024))
elif tbytes > 1024:
size = "%.1f KB" % (tbytes / 1024)
else:
size = "%.1f B" % (tbytes)
res = dict(link=i['download'],
name=i['title'],
size=size,
seeds=i['seeders'],
leech=i['leechers'],
engine_url=self.url,
desc_link=i['info_page'])
prettyPrinter(res)
def search(self, what, cat='all'):
"""
Method called by nova2.
`what` is the already scaped search string, while `cat` restricts in
which category the search should be performed.
For each parsed line of the result, we put it in a dictionary and
pass it to the prettyPrint function.
"""
data = retrieve_url('http://psychocydd.co.uk/torrents.php?search=%s'
% what)
soup = BeautifulSoup(data)
res = soup.find_all('table', attrs={'width': '100%', 'class': 'lista'})
rows = res[5].find_all('tr') # by inspection, we want res[5]
for row in rows[2:]: # by inspection, we want rows[2:]
cells = row.find_all('td')
# Columns of interest, all determined by inspection
info = {
'name': cells[1].a.text,
'link': self.url + '/' + cells[4].a['href'],
'size': cells[6].text,
'seeds': cells[7].text,
'leech': cells[8].text,
'engine_url': self.url,
}
prettyPrinter(info)
def search(self, what, cat='all'):
# Remove {} since isohunt does not seem
# to handle those very well
what = what.replace('{', '').replace('}', '')
i = 1
while True and i<11:
res = 0
dat = retrieve_url(self.url+'/torrents.php?ihq=%s&iht=%s&ihp=%s&ihs1=2&iho1=d'%(what, self.supported_categories[cat],i))
# I know it's not very readable, but the SGML parser feels in pain
section_re = re.compile('(?s)id=link.*?</tr><tr')
torrent_re = re.compile('(?s)torrent_details/(?P<link>.*?[^/]+).*?'
'>(?P<name>.*?)</a>.*?'
'>(?P<size>[\d,\.]+\s+MB)</td>.*?'
'>(?P<seeds>\d+)</td>.*?'
'>(?P<leech>\d+)</td>')
for match in section_re.finditer(dat):
txt = match.group(0)
m = torrent_re.search(txt)
if m:
torrent_infos = m.groupdict()
torrent_infos['name'] = re.sub('<.*?>', '', torrent_infos['name'])
torrent_infos['engine_url'] = self.url
torrent_code = torrent_infos['link']
torrent_infos['link'] = self.url + '/download/' + torrent_code
torrent_infos['desc_link'] = self.url + '/torrent_details/' + torrent_code + '/dvdrip?tab=summary'
prettyPrinter(torrent_infos)
res = res + 1
if res == 0:
break
i = i + 1
def search(self, what, cat='all'):
req = urllib.unquote(what)
i = 0
results = 0
while i < 3:
data = retrieve_url('https://api.btdigg.org/api/public-8e9a50f8335b964f/s01?%s' % urllib.urlencode(dict(q = req, p = i)))
for line in data.splitlines():
if line.startswith('#'):
continue
info_hash, name, files, size, dl, seen = line.strip().split('\t')[:6]
name = name.replace('|', '')
res = dict(link = 'magnet:?xt=urn:btih:%s&dn=%s' % (info_hash, urllib.quote(name.encode('utf8'))),
name = name,
size = size,
seeds = int(dl),
leech = int(dl),
engine_url = self.url,
desc_link = '%s/search?%s' % (self.url, urllib.urlencode(dict(info_hash = info_hash, q = req))))
prettyPrinter(res)
results += 1
if results == 0:
break
i += 1
def search_page(self, what, cat, start):
results = []
cat = self.supported_categories[cat]
url = self.url + '/browse-movie/%s/720p/%s/0/seeds/%s'%(what, cat, start)
# print url
html = retrieve_url(url)
soup = BeautifulSoup(html)
divs = soup.findAll('div',{'class':'browse-info'})
for div in divs:
d = dict()
info = div.findNext('span',{'class':'info'})
links = div.findNext('span',{'class':'links'})
name_span = info.findNext('span',{'class':'browseTitleLink'})
d['name'] = name_span.text
size_span = info.findNext('span',{'class':'browseInfoList'})
d['size'] = size_span.text.replace('Size:','')
browseSeeds_span = info.findNext('span',{'class':'browseSeeds'})
leech_span = browseSeeds_span.findNext('span',{'class':'peers'})
d['leech'] = leech_span.text.replace('Peers:','')
seeds_span = browseSeeds_span.findNext('span',{'class':'seeds'})
d['seeds'] = seeds_span.text.replace('Seeds:','')
desc_link = links.findNext('a')
d['desc_link'] = desc_link['href']
d['link'] = desc_link.findNext('a')['href']
d['engine_url'] = self.url
results.append(d)
return results
def search(self, what, cat="all"):
json_data = retrieve_url(
"".join(
(
self.url,
"api/v2/torrents/search/?phrase=",
what,
"&category=",
self.supported_categories.get(cat, ""),
)
)
)
json_dict = json.loads(json_data)
if json_dict["results"] < 1:
return
for r in json_dict["torrents"]:
r_dict = {
"link": r["magnet_uri"],
"name": r["torrent_title"],
"size": str(r["size"]) + "B",
"seeds": r["seeds"],
"leech": r["leeches"],
"desc_link": r["page"],
"engine_url": self.url,
}
prettyPrinter(r_dict)
def search(self, what, cat='all'):
i = 1
while True and i<11:
results = []
url = self.url+'/api/list.json?sort=seeds&limit=50&keywords=%s&set=%s&genre=%s'%(what, i, self.supported_categories[cat])
json_data = retrieve_url(url)
try:
json_dict = json.loads(json_data)
except:
i += 1
continue
try:
results = json_dict['MovieList']
except KeyError:
return
else:
for r in results:
res_dict = dict()
res_dict['name'] = r['MovieTitle']
res_dict['size'] = r['Size']
res_dict['seeds'] = r['TorrentSeeds']
res_dict['leech'] = r['TorrentPeers']
res_dict['link'] = r['TorrentUrl']
res_dict['desc_link'] = r['MovieUrl']
res_dict['engine_url'] = self.url
prettyPrinter(res_dict)
i += 1
def search(self, what, cat='all'):
# Remove {} since btjunkie does not seem
# to handle those very well
what = what.replace('{', '').replace('}', '')
ret = []
i = 1
# ru: format changed, no need to loop
while True and i<2:
results = []
parser = self.SimpleSGMLParser(results, self.url)
dat = retrieve_url(self.url+'/search/%s/%s/'%(self.supported_categories[cat], what))
# Remove <font> tags from page
p = re.compile( '<[/]?font.*?>')
dat = p.sub('', dat)
#print dat
#return
results_re = re.compile('(?s)<span style="float:left">Torrent Name</span>.*</table>')
for match in results_re.finditer(dat):
res_tab = match.group(0)
parser.feed(res_tab)
parser.close()
break
if len(results) <= 0:
break
i += 1
def search(self, what, cat='all'):
ret = []
i = 1
while True and i<11:
results = []
json_data = retrieve_url(self.url+'/json.php?q=%s&page=%d'%(what, i))
try:
json_dict = json.loads(json_data)
except:
i += 1
continue
if int(json_dict['total_results']) <= 0: return
results = json_dict['list']
for r in results:
try:
if cat != 'all' and self.supported_categories[cat] != r['category']: continue
res_dict = dict()
res_dict['name'] = r['title']
res_dict['size'] = str(r['size'])
res_dict['seeds'] = r['seeds']
res_dict['leech'] = r['leechs']
res_dict['link'] = r['torrentLink']
res_dict['desc_link'] = r['link']
res_dict['engine_url'] = self.url
prettyPrinter(res_dict)
except:
pass
i += 1
def search(self, what, cat="all"):
""" Performs search """
query = "".join((self.url, "/advanced_search/?with=", what, "&s_cat=", self.supported_categories[cat]))
response = retrieve_url(query)
list_searches = []
parser = self.MyHtmlParseWithBlackJack(list_searches, self.url)
parser.feed(response)
parser.close()
for search_query in list_searches:
response = retrieve_url(self.url + search_query)
parser.feed(response)
parser.close()
return
def search(self, query, cat='all'):
query = query.replace(' ', '+')
parser = self.MyHtmlParseWithBlackJack(self.url)
torrent_list = re_compile("(?s)<table class=\"listing\">(.*)</table>")
additional_links = re_compile("/?lastid=[0-9]+&page=[0-9]+&terms={}".format(query))
request_url = '{0}/search.php?terms={1}&type={2}&size_min=&size_max=&username='.format(self.url, query, self.supported_categories[cat])
data = retrieve_url(request_url)
data = torrent_list.search(data).group(0)
parser.feed(data)
parser.close()
for res_link in map(lambda link: "".join((self.url, "/search.php?", link.group(0))), additional_links.finditer(data)):
data = retrieve_url(res_link)
data = torrent_list.search(data).group(0)
parser.feed(data)
parser.close()
def search(self, what, cat="all"):
""" Performs search """
query = "/".join((self.url, "search", what, self.supported_categories[cat], "seeds"))
response = retrieve_url(query)
list_searches = []
parser = self.MyHtmlParseWithBlackJack(list_searches, self.url)
parser.feed(response)
parser.close()
parser.next_queries = False
for search_query in list_searches:
response = retrieve_url(self.url + search_query)
parser.feed(response)
parser.close()
return
def search(self, what, cat='all'):
json_data = retrieve_url(self.url + 'api/v2/torrents/search/?phrase=' + what +
'&category=' + self.supported_categories.get(cat, ''))
json_dict = json.loads(json_data)
if json_dict['results'] < 1:
return
for r in json_dict['torrents']:
r_dict = {'link': r['magnet_uri'], 'name': r['torrent_title'], 'size': str(r['size']) + 'B',
'seeds': r['seeds'], 'leech': r['leeches'], 'desc_link': r['page'], 'engine_url': self.url}
prettyPrinter(r_dict)
def search(self, query, cat='all'):
""" Performs search """
query = query.replace("%20", "-")
parser = self.MyHtmlParser(self.url)
page = "".join((self.url, "/", self.supported_categories[cat], "/torrents/", query, ".html?sort=seeds&page=1"))
html = retrieve_url(page)
parser.feed(html)
counter = 1
additional_pages = re_compile("/{0}/torrents/{1}.html\?sort=seeds&page=[0-9]+".format(self.supported_categories[cat], query))
list_searches = additional_pages.findall(html)[:-1] #last link is next(i.e. second)
for page in map(lambda link: "".join((self.url, link)), list_searches):
html = retrieve_url(page)
parser.feed(html)
counter += 1
if counter > 3:
break
parser.close()
def search(self, what, cat='all'):
i = 1
while True and i < 11:
results = []
parser = self.SimpleSGMLParser(results, self.url)
dat = retrieve_url(self.url + '/?page=search&term=%s&offset=%d&cats=%s' % (what, i, self.supported_categories[cat]))
parser.feed(dat)
parser.close()
if len(results) <= 0:
break
i += 1
def search(self, what, cat="all"):
for page in range(1, 35):
results = []
parser = self.SimpleHTMLParser(results)
data = retrieve_url(
self.url + '/search?page={}&search={}'.format(page, what)
)
parser.feed(data)
parser.close()
if len(results) <= 0:
break
def search(self, what, cat='all'): i = 0 while True and i<11: results = [] parser = self.SimpleSGMLParser(results, self.url) dat = retrieve_url(self.url+'/ts.php?search=&words=%s&cid=%s&sid=&type=1&orderby=a.seeds&asc=0&skip=%s'%(what, self.supported_categories[cat], (i*35))) parser.feed(dat) parser.close() if len(results) <= 0: break i += 1
def search(self, what, cat='all'):
""" Performs search """
#prepare query. 7 is filtering by seeders
cat = cat.lower()
query = "/".join((self.url, "search", what, "0", "7", self.supported_categories[cat]))
response = retrieve_url(query)
list_searches = []
parser = self.MyHtmlParseWithBlackJack(list_searches, self.url)
parser.feed(response)
parser.close()
parser.add_query = False
for search_query in list_searches:
response = retrieve_url(self.url + search_query)
parser.feed(response)
parser.close()
return
def search(self, what, cat='all'):
ret = []
i = 0
while True and i<11:
results = []
parser = self.SimpleSGMLParser(results, self.url)
dat = retrieve_url(self.url+'/searchResult.php?search=%s&lngMainCat=%s&order=seeders&by=down&start=%d'%(what, self.supported_categories[cat], i))
parser.feed(dat)
parser.close()
if len(results) <= 0:
break
i += 1
def search(self, what, cat='all'):
results_list = []
parser = self.MyHtmlParser(results_list, self.url)
i = 0
while i < 6:
dat = retrieve_url(self.url+'/searchResult.php?search=%s&lngMainCat=%s&order=seeders&by=down&start=%d'%(what, self.supported_categories[cat], i))
parser.feed(dat)
if len(results_list) < 1:
break
del results_list[:]
i += 1
parser.close()
def search(self, what, cat='all'): ret = [] i = 0 order = 'se' while True and i<11: results = [] parser = self.SimpleSGMLParser(results, self.url) dat = retrieve_url(self.url+'/search/%s/%d/7/%s' % (what, i, self.supported_categories[cat])) parser.feed(dat) parser.close() if len(results) <= 0: break i += 1
def search(self, what, cat='all'):
i = 1
results = []
parser = self.NTParser(results, self.url)
while i < 51:
dat = retrieve_url(
'%s/?page=search&term=%s&offset=%d&cats=%s' % (self.url, what, i, self.supported_categories[cat]))
parser.feed(dat)
if len(results) <= 0:
break
del results[:]
i += 1
parser.close()
def search(self, what, cat='all'):
for page in range(100):
results = []
parser = self.SimpleHTMLParser(results, self.url)
data = ''
for t411_cat in self.supported_categories[cat]:
path = ('/torrents/search/?{}&search={}&order=seeders&type=desc&page={}'
.format(t411_cat, what, page))
data += retrieve_url(self.url + path)
parser.feed(data)
parser.close()
if len(results) <= 0:
break
def search(self, what, cat="all"):
for page in range(35):
results = []
parser = self.SimpleHTMLParser(results, self.url)
for subcat in self.supported_categories[cat]:
data = retrieve_url(
'{}/recherche/{}{}/page-{},trie-seeds-d'
.format(self.url, subcat, what, page)
)
parser.feed(data)
parser.close()
if len(results) <= 0:
break
def search(self, what, cat='all'):
i = 0
dat = ''
results = []
parser = self.SimpleHTMLParser(results, self.url)
while i < 9:
dat = retrieve_url('%s/torrents-search/%s/%s?sort=seeders.desc&type=all&period=none&categories=%s'%(self.url, what, (i*35), self.supported_categories[cat]))
parser.feed(dat)
if len(results) <= 0:
break
del results[:]
i += 1
parser.close()
def search(self, what, cat='all'):
""" Performs search """
results_list = []
parser = self.MyHtmlParser(results_list, self.url)
i = 1
while i < 31:
# "what" is already urlencoded
html = retrieve_url(self.url + '/q/%s/%d?sort=popular' % (what, i))
parser.feed(html)
if len(results_list) < 1:
break
del results_list[:]
i += 1
parser.close()
def search(self, what, cat='all'):
# initialize trackers for magnet links
trackers = '&' + '&'.join(urlencode({'tr' : tracker}) for tracker in self.trackers_list)
i = 0
while i < 6:
results_list = []
# "what" is already urlencoded
html = retrieve_url(self.url + '/any?f=%s&p=%d' % (what, i))
parser = self.MyHtmlParser(results_list, self.url, trackers)
parser.feed(html)
parser.close()
if len(results_list) < 1:
break
i += 1
def search(self, what, cat='all',sorttype='-1',page='1'):
result={}
result['state']=False
result['list']=[]
searchurl=self.url+'%s/%s'%(urllib.quote(what),str(int(page)))
#plugin.notify(searchurl)
try:
pageresult = retrieve_url(searchurl)
#xbmc.log(msg=pageresult)
rmain=r'target="_blank">(?P<title>.*?)</a></span>.*?收录时间.*?value">(?P<createtime>.*?)</span>.*?大小.*?value">(?P<filesize>.*?)</span>.*?文件数.*?value">(?P<filecount>.*?)</span>.*?href="(?P<magnet>.*?)">磁力链接'
reobj = re.compile(rmain, re.DOTALL)
for match in reobj.finditer(pageresult):
title=match.group('title')
#plugin.notify(title)
filesize=match.group('filesize')
createtime=match.group('createtime')
title=title.replace("<span class='highlight'>","").replace('</span>','')
filecount=match.group('filecount')
filesize=filesize.replace(' ',' ')
createtime=createtime.replace(' ',' ')
magnet=match.group('magnet')
res_dict = dict()
res_dict['name'] = title
res_dict['size'] = filesize
res_dict['seeds'] = ''
res_dict['leech'] = ''
res_dict['link'] = magnet
res_dict['date'] =createtime
res_dict['desc_link'] = ''
res_dict['engine_url'] = self.url
result['list'].append(res_dict)
if len(result['list'])>0:
result['nextpage']=True
except:
return result
result['state']=True
return result
def search(self, what, cat='all'):
query = "http://down.ali213.net/search?kw=" + what + "&submit="
data = retrieve_url(query)
found_games = re.findall(self.result_page_match, data)
if found_games:
if self.games_to_parse > len(found_games):
self.games_to_parse = len(found_games)
# handling each gamepage in parallel, to not waste time on waiting for requests
# for 10 games this speeds up from 37s to 6s run time
threads = []
for i in range(self.games_to_parse):
t = threading.Thread(target=self.handle_gamepage, args=(found_games[i],))
threads.append(t)
t.start()
# search method needs to stay alive until all threads are done
for t in threads:
t.join()
return
def search(self, what, cat='all'):
req = urllib.unquote(what)
what_list = req.decode('utf8').split()
i = 0
results = 0
while i < 3:
data = retrieve_url(
'https://api.btdigg.org/api/public-8e9a50f8335b964f/s01?%s' %
urllib.urlencode(dict(q=req, p=i)))
for line in data.splitlines():
if line.startswith('#'):
continue
info_hash, name, files, size, dl, seen = line.strip().split(
'\t')[:6]
name = name.replace('|', '')
# BTDigg returns unrelated results, we need to filter
if not all(word in name.lower() for word in what_list):
continue
res = dict(
link='magnet:?xt=urn:btih:%s&dn=%s' %
(info_hash, urllib.quote(name.encode('utf8'))),
name=name,
size=size,
seeds=int(dl),
leech=int(dl),
engine_url=self.url,
desc_link='%s/search?%s' %
(self.url,
urllib.urlencode(dict(info_hash=info_hash, q=req))))
prettyPrinter(res)
results += 1
if results == 0:
break
i += 1
def search(self, what, cat="all"):
""" Performs search """
query = "".join((self.url, "/rss.xml?type=search&search=", what, "&cid=", self.supported_categories[cat]))
response = retrieve_url(query)
xmldoc = minidom.parseString(response)
itemlist = xmldoc.getElementsByTagName('item')
for item in itemlist:
current_item = current_item = {"engine_url" : self.url}
current_item['name'] = item.getElementsByTagName('title')[0].childNodes[0].data
current_item["link"] = item.getElementsByTagName('enclosure')[0].attributes['url'].value
current_item["desc_link"] = item.getElementsByTagName('link')[0].childNodes[0].data
current_item["size"] = item.getElementsByTagName('size')[0].childNodes[0].data
current_item["leech"] = item.getElementsByTagName('leechers')[0].childNodes[0].data
if not current_item["leech"].isdigit():
current_item["leech"] = ''
current_item["seeds"] = item.getElementsByTagName('seeders')[0].childNodes[0].data
if not current_item["seeds"].isdigit():
current_item["seeds"] = ''
prettyPrinter(current_item)
return
def search(self, what, cat='all'):
query = self.url + '/api/v1/search/?q='\
+ what\
+ '&sort=seeders&category='\
+ self.supported_categories[cat]
response = json.loads(retrieve_url(query))
all_results = response['hits']['value']
for item in response['results']:
self.process_record(item)
i = 20
threads = list()
while all_results > i:
a = threading.Thread(target=self.launch_request, args=(query, i))
threads.append(a)
a.start()
i += 20
for thread in threads:
thread.join()
def search_threaded(url):
logging.debug('Starting a new thread.')
# PAGE_QUERY = re.compile(r'<a href="(magnet.*?)">.*?<span style="padding:0 5px 10px 7px;word-wrap: break-word;">(.+?)<\/span>.*?<span>Seed:(.*?)<\/span>.*?<\/i>(.*?)<\/span>', re.DOTALL)
page_query_regex = re.compile(
'break-word;">(.*?)</span>.*?Seed:(.*?)</span>.*?Leech:(.*?)</span>.*?Size:(.*?)</span>.*?href="(magnet.*?)"',
re.DOTALL)
magnet_query_regex = re.compile('href="(magnet.*?)"')
empty_page_regex = re.compile(
r'(<h3 style="color:blue;">No Results Found for \()')
curr_record = list()
curr_dict = dict()
curr_record.clear()
curr_dict.clear()
try:
a_v = retrieve_url(url)
except:
print('failed to connect')
quit()
match = re.search(empty_page_regex, a_v)
if match:
print('another one bites the dust')
quit()
c_v = re.findall(magnet_query_regex, a_v)
for b_v in re.finditer(page_query_regex, a_v):
for x in range(1, 5, 1):
curr_record.append(b_v.group(x).strip())
curr_dict['link'] = c_v[x]
curr_dict['name'] = curr_record[0]
curr_dict['seeds'] = curr_record[1]
curr_dict['size'] = curr_record[3].replace(',', '')
curr_dict['leech'] = curr_record[2]
curr_dict['engine_url'] = 'https://www.idope.site'
curr_dict['desc_link'] = str(-1)
curr_record.clear()
prettyPrinter(curr_dict)
curr_dict.clear()
def search(self, what, cat='all'):
query = "http://www.mkvcage.bid/?s=" + what
data = retrieve_url(query)
found_games = re.findall(self.result_page_match, data)
if found_games:
if self.games_to_parse > len(found_games):
self.games_to_parse = len(found_games)
# handling each page in parallel, to not waste time on waiting for requests
# for 8 entries this speeds up from 8s to 3s run time
threads = []
for i in range(self.games_to_parse):
# self.handle_page("http://" + found_games[i])
t = threading.Thread(target=self.handle_page,
args=("http://" + found_games[i], ))
threads.append(t)
t.start()
# search method needs to stay alive until all threads are done
for t in threads:
t.join()
return
def fetch_results(self, query):
results = json.loads(retrieve_url(query))
return results
def do_search(self, url):
webpage = retrieve_url(url)
tgParser = self.TorrentGalaxyParser()
tgParser.feed(webpage)
def search(self, what, cat='all', sorttype='-1', page='1'):
result = {}
result['state'] = False
result['list'] = []
if str(sorttype) == '-1':
dialog = xbmcgui.Dialog()
sorttype = dialog.select('btdigg搜索-选择排序类型',
['相关度', '下载热度', '创建时间', '文件大小', '文件数'])
if sorttype == -1:
return result
sorttype = str(sorttype)
result['sorttype'] = sorttype
searchurl = self.url + '?q=%s&order=%s&p=%s' % (
urllib.quote(what), sorttype, str(int(page) - 1))
data = urllib.urlencode({'u': searchurl, 'b': '12', 'f': 'norefer'})
pageresult = ''
for i in range(5):
try:
wp = webproxy.get('webproxy', '')
if not wp:
#plugin.notify('重新获取代理')
wp = self.getwebproxy()
#plugin.notify('当前代理：'+webproxy['webproxy'])
webproxyurl = wp + '/browse.php?' + data
pageresult = retrieve_url(webproxyurl, referer=wp)
if pageresult:
webproxy['webproxy'] = wp
webproxy.sync()
break
else:
continue
except:
continue
if pageresult == '':
webproxy['webproxy'] = ''
webproxy.sync()
return result
try:
rmain = r'"idx">.*?>(?P<title>[^<]+)</a>.*?href=".*?u=.*?(?P<magnet>magnet.*?)&.*?".*?attr_val">(?P<filesize>.*?)<.*?attr_val">(?P<filecount>.*?)<.*?attr_val">(?P<heatlevel>.*?)<.*?attr_val">(?P<createtime>.*?)<.*?attr_val">.*?attr_val">(?P<fake>.*?)<'
reobj = re.compile(rmain, re.DOTALL | re.MULTILINE)
#xbmc.log(msg=pageresult)
for match in reobj.finditer(pageresult):
fake = match.group('fake')
if fake == 'No' or fake == '否':
title = match.group('title')
filesize = match.group('filesize').replace(' ', ' ')
createtime = match.group('createtime').replace(
' ', ' ')
filecount = match.group('filecount')
magnet = match.group('magnet')
else:
magnet = ''
continue
res_dict = dict()
res_dict['name'] = title
res_dict['size'] = filesize
res_dict['seeds'] = match.group('heatlevel')
res_dict['leech'] = match.group('heatlevel')
res_dict['link'] = magnet
res_dict['date'] = createtime
res_dict['desc_link'] = ''
res_dict['engine_url'] = self.url
result['list'].append(res_dict)
if len(result['list']) > 0:
result['nextpage'] = True
except:
return result
result['state'] = True
return result
def search(self, what, cat='all', sorttype='-1', page='1'):
result = {}
result['state'] = False
result['list'] = []
if str(sorttype) == '-1':
dialog = xbmcgui.Dialog()
sorttype = dialog.select('btbook搜索-选择排序类型',
['创建时间', '文件大小', '下载热度', '相关度'])
if sorttype == -1:
return result
sorttype = str(sorttype + 1)
result['sorttype'] = sorttype
searchurl = self.url + '%s/%s-%s.html' % (
urllib.quote(what), str(int(page)), str(sorttype))
#plugin.notify(searchurl)
try:
'''
json_data = retrieve_url('http://int.dpool.sina.com.cn/iplookup/iplookup.php?format=js')
json_data= json_data.replace('\n','').replace('\r','')
json_data=json_data[json_data.index('{'):json_data.index('}')+1]
#xbmc.log(json_data)
json_dict = json.loads(json_data)
prov=json_dict['province']
#声明一个CookieJar对象实例来保存cookie
cookie = cookielib.CookieJar()
#利用urllib2库的HTTPCookieProcessor对象来创建cookie处理器
handler=urllib2.HTTPCookieProcessor(cookie)
#通过handler来构建opener
opener = urllib2.build_opener(handler)
#此处的open方法同urllib2的urlopen方法，也可以传入request
response = opener.open('http://www.btmilk.com/search/')
cookie_item = cookielib.Cookie(
version=0, name='prov', value=prov,
port=None, port_specified=None,
domain='http://www.btmilk.com/', domain_specified=None, domain_initial_dot=None,
path='/', path_specified=None,
secure=None,
expires=None,
discard=None,
comment=None,
comment_url=None,
rest=None,
rfc2109=False,
)
cookie.set_cookie(cookie_item)
response = opener.open(searchurl)
'''
pageresult = retrieve_url(searchurl)
#xbmc.log(pageresult)
#pageresult=response.read()
#xbmc.log(pageresult)
rmain = r'创建时间.*?<b.*?>(?P<createtime>.*?)</b>.*?文件大小.*?<b.*?>(?P<filesize>.*?)</b>.*?下载热度.*?<b.*?>(?P<heatlevel>.*?)</b>.*?最近下载.*?<b.*?>(?P<lastdown>.*?)</b>.*?wiki/(?P<magnet>.*?).html.*?decodeURIComponent\x28"(?P<title>.*?)"\x29'
reobj = re.compile(rmain, re.DOTALL)
for match in reobj.finditer(pageresult):
title = match.group('title').replace('"+"', '')
title = urllib.unquote(title)
#title=urllib.urldecode(match.group('title').replace('"+"',''))
#xbmc.log(title)
filesize = match.group('filesize')
createtime = match.group('createtime')
title = title.replace('<b>', '').replace('</b>', '')
magnet = match.group('magnet')
magnet = 'magnet:?xt=urn:btih:' + magnet
res_dict = dict()
res_dict['name'] = title
res_dict['size'] = filesize
res_dict['seeds'] = ''
res_dict['leech'] = ''
res_dict['link'] = magnet
res_dict['date'] = createtime
res_dict['desc_link'] = ''
res_dict['engine_url'] = self.url
result['list'].append(res_dict)
if len(result['list']) > 0:
result['nextpage'] = True
except:
return result
result['state'] = True
return result
def download_torrent(self, info):
html = retrieve_url(info)
m = re.search('(/tor/.+?\s)', html)
if m and len(m.groups()) > 0:
print(download_file(self.url + m.group(1)))
def do_search(self, url):
webpage = retrieve_url(url)
adexParser = self.anidexParser()
adexParser.feed(webpage)
def download_torrent(self, desc_link):
""" Downloader """
dl_link = re_compile("https://www\.hypercache\.pw/metadata/.+?/")
data = retrieve_url(desc_link)
dl_url = dl_link.findall(data)[0]
print(download_file(dl_url))
def launch_request(self, query, skip):
this_query = query + '&fuv=yes&skip=' + str(skip)
these_items = json.loads(retrieve_url(this_query))
for item in these_items['results']:
self.process_record(item)
def download_torrent(self, desc_link):
""" Downloader """
dl_link = re_compile("/downloading/[^\"]+")
data = retrieve_url(desc_link)
dl_url = dl_link.findall(data)[0]
print(download_file(self.url + dl_url))
def search(self, what, cat='all',sorttype='relevance',page='1'):
result={}
result['state']=False
result['list']=[]
result['sorttype']=sorttype
if sorttype=='addtime': sorttype='1'
elif sorttype=='size': sorttype='2'
elif sorttype=='files': sorttype='3'
elif sorttype=='popular': sorttype='4'
else : sorttype='0'
try:
whatcode=''
for i in range(20):
try:
locurl=urlgetlocation(self.url,data='keyword='+urllib.quote(what))
if str(locurl.getcode())=='302':
match = re.search("search\x2F(.*?)\x2F", locurl.geturl(), re.IGNORECASE | re.DOTALL)
if match:
whatcode = match.group(1)
else:
whatcode = ""
xbmc.log(msg='btdiggs-err:%s %s'%(int(locurl.getcode()),whatcode),level=xbmc.LOGERROR)
break
except Exception, errno:
xbmc.log(msg='btdiggs-err:%s'%(errno),level=xbmc.LOGERROR)
time.sleep(1)
continue
if whatcode=='':
return result
pageresult=''
for i in range(10):
searchurl=self.url+'search/%s/%s/%s/2.html'%(urllib.quote(whatcode),str(int(page)),str(sorttype),)
pageresult = retrieve_url(searchurl,referer=self.url)
if pageresult!='':
break
time.sleep(1)
#xbmc.log(msg=pageresult,level=xbmc.LOGERROR)
rmain=r'<dt><a.*?target=[\x22\x27]_blank[\x22\x27]>(?P<title>.*?)</a>.*?收录时间:<b>(?P<createtime>.*?)</b>.*?<span>文件大小:<b>(?P<filesize>.*?)</b>.*?<span>文件数:<b>(?P<filecount>.*?)</b>.*?<span>人气:<b>(?P<popular>.*?)</b>.*?href=[\x22\x27](?P<magnet>.*?)[\x22\x27]'
reobj = re.compile(rmain, re.DOTALL)
for match in reobj.finditer(pageresult):
title=match.group('title')
filesize=match.group('filesize')
createtime=match.group('createtime')
filecount=match.group('filecount')
title = re.sub(r'<span\s+class="__cf_email.*?</span>', '', title, re.IGNORECASE | re.DOTALL)
title=title.replace('<b>','').replace('</b>','')
magnet=match.group('magnet')
res_dict = dict()
res_dict['name'] = title
res_dict['size'] = filesize
res_dict['filecount'] = filecount
res_dict['seeds'] = ''
res_dict['leech'] = ''
res_dict['link'] = magnet
res_dict['date'] =createtime
res_dict['desc_link'] = ''
res_dict['engine_url'] = self.url
result['list'].append(res_dict)
result['nextpage']=True
def download_torrent(self, info):
""" Downloader """
html = retrieve_url(info)
m = re.search('<a\s?href=[\'\"](magnet\:\?.+?)[\'\"]', html)
if m and len(m.groups()) > 0:
print(m.group(1) + ' ' + info)
def download_torrent(self, desc_link):
""" Downloader """
dl_link = re_compile("/get_torrents/[a-zA-Z0-9]+")
data = retrieve_url(desc_link)
dl_url = dl_link.findall(data)[0]
print(download_file(self.url + dl_url))
def download_torrent(self, info):
html = helpers.retrieve_url(info)
magnet = re.search("magnet:\?[^\"]*(?=\")", html).group()
print(magnet + ' ' + info)
def search(self, what, cat='all'):
parser = self.Parser(self.url)
what = parser.generateQuery(what)
parser.feed(json.loads(retrieve_url(what)))
def load(self):
self.html = retrieve_url(self.url)
return self
def download_torrent(self, info):
if "trackerlist" not in self.__dict__:
self.trackerlist = json.loads(retrieve_url("https://downloadtorrentfile.com/trackerlist"))
magnet = f"magnet:?xt=urn:btih:{info.split('/')[-1]}&tr=" + "&tr=".join(self.trackerlist)
print(magnet + ' ' + info)
def handle_page(self, search_query):
response = retrieve_url(self.url + search_query)
parser = self.MyHtmlParseWithBlackJack(self.url)
parser.feed(self.torrent_list.search(response).group(0))
parser.close()
def download_torrent(self, info):
info_page = retrieve_url(info)
link = download_pattern.findall(info_page)[0]
print download_file(link)
def search(self, keyword, cat='all'):
job = score()
params = job.paramBuilder(unquote(keyword))
url = job.urlBuilder(self.url, ['api', 'v2', 'list_movies.json'],
params)
data = retrieve_url(url)
j = json.loads(data)
# with open("assets/yts.v181109.json", "w") as f:
# json.dump(j, f)
if j['data']['movie_count'] and 'movies' in j['data']:
page_of = '{}of{}'.format(
j['data']['page_number'],
int(
math.ceil(
int(j['data']['movie_count']) /
int(j['data']['limit']))))
for movies in j['data']['movies']:
for torrent in movies['torrents']:
res = {
'link':
job.magnetBuilder(torrent['hash'], movies['title']),
'name':
'{n} ({y}) [{q}]-[{p}]-[{i}]'.format(
n=movies['title'],
y=movies['year'],
q=torrent['quality'],
p=page_of,
i=self.name),
'size':
torrent['size'],
'seeds':
torrent['seeds'],
'leech':
torrent['peers'],
'engine_url':
'IMDB:{rating}, [{genres}]'.format(
rating=movies['rating'],
genres=', '.join(movies['genres'])),
'desc_link':
movies['url']
}
job.done(res)
elif job.supported_browse_params:
url_params = job.supported_browse_params
url_path = list(
map(lambda i: i in params and params[i] or url_params[i],
url_params))
url = job.urlBuilder(self.url, url_path, 'page' in params
and {'page': params['page']})
data = retrieve_url(url)
data = re.sub("\s\s+", "", data).replace('\n',
'').replace('\r', '')
data_container = re.findall(
'<div class="browse-content"><div class="container">.*?<section><div class="row">(.*?)</div></section>.*?</div></div>',
data)
if data_container and data_container[0]:
page_of = re.findall(
'<li class="pagination-bordered">(.*?)</li>',
data)[0] # 1 of 5
page_of = page_of and re.sub(' +', '', page_of).strip() or '?'
data_movie = re.findall(
'<div class=".?browse-movie-wrap.*?">.*?</div></div></div>',
data_container[0])
for hM in data_movie:
movie_link = re.findall(
'<a href="(.*?)" class="browse-movie-link">.*?</a>',
hM)[0]
response_detail = retrieve_url(movie_link)
response_detail = re.sub("\s\s+", "",
response_detail).replace(
'\n', '').replace('\r', '')
movie_id = re.findall('data-movie-id="(\d+)"',
response_detail)[0]
if movie_id:
url = job.urlBuilder(
self.url, ['api', 'v2', 'movie_details.json'],
{'movie_id': movie_id})
data_detail = retrieve_url(url)
j = json.loads(data_detail)
movies = j['data']['movie']
for torrent in movies['torrents']:
res = {
'link':
job.magnetBuilder(torrent['hash'],
movies['title']),
'name':
'{n} ({y}) [{q}]-[{p}]-[{i}]'.format(
n=movies['title'],
y=movies['year'],
q=torrent['quality'],
p=page_of,
i=self.name[:-1]),
'size':
torrent['size'],
'seeds':
torrent['seeds'],
'leech':
torrent['peers'],
'engine_url':
'IMDB:{rating}, [{genres}]'.format(
rating=movies['rating'],
genres=', '.join(movies['genres'])),
'desc_link':
movies['url']
}
job.done(res)
else:
# TODO: ??
movie_title = re.findall(
'<a.*?class="browse-movie-title".*?>(.*?)</a>',
hM)[0]
movie_year = re.findall(
'<div.?class="browse-movie-year".*?>(.*?)</div>',
hM)[0]
movie_rate = re.findall(
'<h4.?class="rating".*?>(.*?)</h4>', hM)[0]
movie_rate = movie_rate.split('/')[0]
movie_genre = re.findall(
'<figcaption class=".*?">.*?(<h4>.*</h4>).*?</figcaption>',
hM)[0]
movie_genre = re.findall('<h4>(.*?)</h4>',
movie_genre)
# print(movie_title,movie_link,movie_year,movie_rate,movie_genre)
job.done()
else:
# NOTE: No match found
job.done()
else:
# NOTE: not supported browsing
job.done()
