Apkawa/tsru/torrentru.py

   1 # -*- coding: utf-8 -*-
   2 import urllib2, httplib,re,sys, time
   3 import optparse
   4 from BeautifulSoup import BeautifulSoup as bfsoup
   5 from BeautifulSoup import BeautifulStoneSoup as BfSS
   6
   7 '''
   8 ----------------------------
   9 Имя пользователя: testdesu_2
  10 Пароль: qazqaz
  11 ----------------------------
  12 '''
  13
  14 USER_AGENT='Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.7.12) \
  15                         Gecko/20050922 Firefox/1.0.7 (Debian package 1.0.7-1)'
  16
  17 class tsru:
  18     def __init__(self):
  19         self.user = ''
  20         self.paswd = ''
  21         self.url = 'http://torrents.ru/forum'
  22
  23     def auth(self):
  24         def get_cookie():
  25             body = 'login_username=%s&login_password=%s&autologin=1&login=%%C2%%F5%%EE%%E4'%(self.user, self.paswd)
  26             header = httplib.HTTPConnection('torrents.ru')
  27             header.putrequest('POST','/forum/login.php')
  28             header.putheader('Content-Length', str(len(body)))
  29             header.putheader('Referer', 'http://torrents.ru/forum/index.php')
  30             header.putheader('User-Agent', USER_AGENT)
  31             header.putheader('Content-Type','application/x-www-form-urlencoded')
  32             header.endheaders()
  33             header.send(body)
  34             self.cookie = header.getresponse().getheader('set-cookie')
  35             return self.cookie
  36
  37         chk = None
  38         count = 0
  39         while not chk:
  40             sys.stderr.write('Попытка авторизации №%d\r'%count)
  41             count+=1
  42             time.sleep(5)
  43             chk = get_cookie()
  44
  45     def get_html(self,url,size=None):
  46         req = urllib2.Request(url)
  47         req.add_header('Cookie', self.cookie)
  48         return urllib2.urlopen(req).read(size)
  49
  50     def profile(self):
  51         stage1 = bfsoup(self.get_html('http://torrents.ru/forum/index.php'))
  52         stage1 = self.url+'/'+stage1.find('div',attrs = {'class':'topmenu'}).find('a',{'href':re.compile('profile.php\?mode=viewprofile')}).get('href')
  53         stage2 = BfSS(self.get_html(stage1))
  54         html_profile = stage2.find('table', {'class':'user_profile bordered w100'})
  55         print html_profile
  56
  57
  58     def test(self,file):
  59         f = open(file)
  60         html = f.read()
  61         f.close()
  62         return html
  63
  64     def search(self, word):
  65         def parse(html):
  66             def extract(tBody):
  67                 check = tBody.find(attrs = {'class':'row1 tCenter'})
  68                 if check: check = check.find('span').get('class')
  69                 else: check = '' #tBody.find(attrs = {'class':'row1 tCenter clickable tor-status-td'}).find('span',attrs = {'class':True})
  70                 if check == 'tor-icon tor-not-approved' or check == 'tor-icon tor-approved':
  71
  72                     temp = {
  73                         'topic_link': self.url+tBody.find(attrs = {'class':'genmed tLink'}).get('href')[1:],
  74                         'topic_text': tBody.find(attrs = {'class':'genmed tLink'}).find(text=True),
  75                         'status'    : check,
  76                         'author'    : tBody.find(attrs = {'class':'med'}).find(text=True),            #class='med'
  77                         'torrent'   : self.url+tBody.find(attrs = {'class':'med dLink'}).get('href')[1:],           #class='med dLink'
  78                         'size'      : tBody.find(attrs = {'class':'row4 small nowrap'}).find(text=True),              #class='row4 small nowrap'
  79                         'seed'      : tBody.find(attrs = {'class':'row4 seedmed'}).find(text=True),              #class='row4 seedmed'
  80                         'leech'     : tBody.find(attrs = {'class':'row4 leechmed'}).find(text=True),             #class='row4 leechmed'
  81                         'downloaded': tBody.find(attrs = {'class':'row4 small'}).find(text=True),        #class='row4 small'
  82                         'added'     : ' '.join([i.find(text=True) for i in tBody.find(attrs = {'class':'row4 small nowrap','title':True}).findAll('p')])
  83                             }
  84
  85                     for i in temp.keys():
  86                         temp[i] = BfSS(temp[i],convertEntities='html')
  87                     return temp
  88                 else: return False
  89
  90             soup = bfsoup(html)
  91             tbody = soup.findAll('tbody')
  92             result = [extract(i) for i in tbody]
  93             return result
  94
  95         #url=self.url+'/tracker.php'
  96         #quere = '%s?max=1&to=1&nm=%s'%(url,urllib2.quote(word))
  97         #html = self.get_html(quere)
  98         html = self.test('search.html')
  99         _parse = parse(html)
 100         return self.output(_parse)
 101
 102     def output(self, result):
 103         count = 1
 104         out_format_base = ' | %s |\n[%s] S: [%s] L: [%s] D: [%s] A: [%s]\n %s\n'
 105         out_format_1 = '%d) %s'+out_format_base
 106         out_format_2 = '%d) %.69s'+out_format_base
 107         ls = []
 108         for i in result:
 109             if i:
 110                 out = len(i['topic_text'].contents[0]) > 69 and out_format_2 or out_format_1
 111                 out = out%(count,
 112                                                 i['topic_text'],
 113                                                 i['author'],
 114                                                 i['size'],
 115                                                 i['seed'],
 116                                                 i['leech'],
 117                                                 i['downloaded'],
 118                                                 i['added'],
 119                                                 i['topic_link'])
 120                 count+=1
 121                 ls.append(out)
 122             else: pass
 123         return ls
 124
 125 def optparse(args):
 126
 127         pass
 128
 129 if __name__ == '__main__':
 130     s = tsru()
 131     #s.auth()
 132     s.search(' '.join(sys.argv[1:]))
 133     #s.profile()
 134
 135
 136
 137 '''
 138 ----------------------------
 139 Имя пользователя: geeqie_001
 140 Пароль: qaz
 141 ----------------------------
 142
 143
 144 Cookie: bb_data=a%3A3%3A%7Bs%3A2%3A%22uk%22%3BN%3Bs%3A3%3A%22uid%22%3Bi%3A314002%3Bs%3A3%3A%22sid%22%3Bs%3A20%3A%22dBI3Kxtsy5fJTOdS5iBi%22%3B%7D; bb_sid=dBI3Kxtsy5fJTOdS5iBi; bb_isl=0
 145 Auth
 146
 147 POST /forum/login.php HTTP/1.1
 148 Host: torrents.ru
 149 User-Agent: Mozilla/5.0 (X11; U; Linux i686; ru-RU; rv:1.9.0.2pre) Gecko/2008072703 Firefox/3.0.2pre (Swiftfox)
 150 Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8
 151 Accept-Language: ru,en-us;q=0.7,en;q=0.3
 152 Accept-Encoding: gzip,deflate
 153 Accept-Charset: windows-1251,utf-8;q=0.7,*;q=0.7
 154 Keep-Alive: 300
 155 Proxy-Connection: keep-alive
 156 Referer: http://torrents.ru/forum/viewforum.php?f=1813
 157 Content-Type: application/x-www-form-urlencoded
 158 Content-Length: 64
 159 login_username=Apkawa&login_password=xerosexo&login=%C2%F5%EE%E4
 160
 161 search
 162
 163 POST /forum/tracker.php HTTP/1.1
 164 Host: torrents.ru
 165 User-Agent: Mozilla/5.0 (X11; U; Linux i686; ru-RU; rv:1.9.0.2pre) Gecko/2008072703 Firefox/3.0.2pre (Swiftfox)
 166 Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8
 167 Accept-Language: ru,en-us;q=0.7,en;q=0.3
 168 Accept-Encoding: gzip,deflate
 169 Accept-Charset: windows-1251,utf-8;q=0.7,*;q=0.7
 170 Keep-Alive: 300
 171 Proxy-Connection: keep-alive
 172 Referer: http://torrents.ru/forum/index.php
 173 Cookie: bb_data=a%3A3%3A%7Bs%3A2%3A%22uk%22%3BN%3Bs%3A3%3A%22uid%22%3Bi%3A314002%3Bs%3A3%3A%22sid%22%3Bs%3A20%3A%22dBI3Kxtsy5fJTOdS5iBi%22%3B%7D; bb_sid=dBI3Kxtsy5fJTOdS5iBi; bb_isl=0
 174 Content-Type: application/x-www-form-urlencoded
 175 Content-Length: 24
 176 max=1&to=1&nm=soul+eater
 177
 178 example
 179
 180 <tbody id="tor_11248324">
 181 <tr class="tCenter">
 182 <td class="row1"><img src="http://static.torrents.ru/templates/default/images/icon_minipost.gif" class="icon1" alt="post" /></td>
 183 <td class="row1 tCenter" title="не проверено"><span class="tor-icon tor-not-approved">*</span></td>
 184 <td class="row1"><a class="gen" href="tracker.php?f=1389">Аниме (основной подраздел)</a></td>
 185 <td class="row4 med tLeft">
 186 <div>
 187 <a class="genmed tLink" href="./viewtopic.php?t=1024117"><b>Пожиратель душ / Soul Eater (Игараси Такуя) [JAP+SUB][2008,приключ<wbr>ения, комедия, фэнтези, сёнэн, TVrip]</wbr></b></a>
 188 </div>
 189 </td>
 190 <td class="row1"><a class="med" href="tracker.php?pid=981210">a-f14</a></td>
 191 <td class="row4 med nowrap"><a class="med dLink" href="./download.php?id=873028">[<span class="dlSp"> </span><span class="bold" onclick="this.className='normal'">DL</span><span class="dlSp"> </span>]</a></td>
 192 <td class="row4 small nowrap">1.47&nbsp;GB</td>
 193 <td class="row4 seedmed" title="Seeders"><b>4</b></td>
 194 <td class="row4 leechmed" title="Leechers"><b>5</b></td>
 195 <td class="row4 small">3</td>
 196 <td class="row4 small nowrap" style="padding: 1px 3px 2px;" title="Добавлен">
 197 <p>23:29</p>
 198 <p>8-Сен-08</p>
 199 </td>
 200 </tr>
 201 </tbody>
 202
 203
 204 def utf8_cp1251(text):
 205     u=unicode(text, 'utf8')
 206     cyrillic_cp1251=u.encode('cp1251')
 207     return cyrillic_cp1251
 208 def cp1251_utf8(text):
 209     cyrillic_cp1251=unicode(text, 'cp1251')
 210     text=cyrillic_cp1251.encode('utf8')
 211     return text
 212
 213 console color
 214 if [ "$USECOLOR" = "YES" -o "$USECOLOR" = "yes" ]; then
 215         C_MAIN="\033[1;37;40m"      # main text
 216         C_OTHER="\033[1;34;40m"     # prefix & brackets
 217         C_SEPARATOR="\033[1;30;40m" # separator
 218
 219         C_BUSY="\033[0;36;40m"      # busy
 220         C_FAIL="\033[1;31;40m"      # failed
 221         C_DONE="\033[1;37;40m"      # completed
 222         C_BKGD="\033[1;35;40m"      # backgrounded
 223
 224         C_H1="\033[1;37;40m"        # highlight text 1
 225         C_H2="\033[1;36;40m"        # highlight text 2
 226
 227         C_CLEAR="\033[1;0m"
 228 '''