API tools faq
paste
Advertisement
Guest User

Untitled

a guest
Feb 24th, 2013
1,304
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
Python 16.80 KB | None | 0 0
raw download clone embed print report
  1. # -*- coding: UTF-8 -*-
  2.  
  3. import os, sys, re, xbmc, xbmcgui, string, time, urllib, urllib2
  4. from utilities import languageTranslate, log
  5.  
  6. main_url = "http://v2.subscene.com/"
  7. debug_pretext = ""
  8.  
  9. # Seasons as strings for searching
  10. seasons = ["Specials", "First", "Second", "Third", "Fourth", "Fifth", "Sixth", "Seventh", "Eighth", "Ninth", "Tenth"]
  11. seasons = seasons + ["Eleventh", "Twelfth", "Thirteenth", "Fourteenth", "Fifteenth", "Sixteenth", "Seventeenth", "Eighteenth", "Nineteenth", "Twentieth"]
  12. seasons = seasons + ["Twenty-first", "Twenty-second", "Twenty-third", "Twenty-fourth", "Twenty-fifth", "Twenty-sixth", "Twenty-seventh", "Twenty-eighth", "Twenty-ninth"]
  13.  
  14. #====================================================================================================================
  15. # Regular expression patterns
  16. #====================================================================================================================
  17.  
  18. # subtitle pattern example:
  19. """
  20.         <tr>
  21.             <td>
  22.                 <a class="a1" href="/arabic/Magnolia/subtitle-311056.aspx" title="Subtitle - Magnolia  - Arabic">
  23.                     <span class="r0" >
  24.  
  25.                         Arabic
  26.                     </span>
  27.                      <span id="r311056">Magnolia.1999.720p.BluRay.x264-LEVERAGE</span>
  28.                 </a>
  29.  
  30.  
  31.  
  32.             </td>
  33.             <td class="a3">1
  34.             </td>
  35.             <td><div id=imgEar title='Hearing Impaired'>&nbsp;</div>
  36.             </td>
  37.  
  38. """
  39. subtitle_pattern = "..<tr>.{5}<td>.{6}<a class=\"a1\" href=\"/([^\n\r]{10,200}?-\d{3,10}.aspx)\" title=\"[^\n\r]{10,200}\">\
  40. [\r\n\t ]+?<span class=\"r(0|100)\" >[\r\n\t\ ]+([^\r\n\t]+?) [\r\n\t]+</span>[\r\n\t ]+?<span id=\"r\d+\">([^\r\n\t]{5,500})</span>\
  41. [\r\n\t]+?</a>[\r\n\t ]+?</td>[\r\n\t ]+?<td class=\"a3\">1[\r\n\t\ ]+?</td>[\r\n\t\ ]+?<td>(|.{52})\r\n\t\t\t</td>"
  42. # group(1) = downloadlink, group(2) = qualitycode, group(3) = language, group(4) = filename, group(5) = hearing impaired
  43.  
  44.  
  45. # movie/seasonfound pattern example:
  46. """
  47.             <a href="/inception/subtitles-80839.aspx" class=popular>
  48.                 Inception (2010)
  49.                 <dfn>(327)</dfn>
  50. """
  51. movie_season_pattern = "...<a href=\"([^\n\r\t]*?/subtitles-\d{1,10}.aspx)\".{1,14}>\r\n{0,3}.{4}([^\n\r\t\&#]*?) \((\d\d\d\d)\) \r\n{0,3}.{1,4}<dfn>\(.{1,5}</dfn>"
  52. # group(1) = link, group(2) = movie_season_title,  group(3) = year
  53.  
  54.  
  55.  
  56.  
  57. # download link pattern example:
  58. """
  59.         <a href="/subtitle/download?mac=LxawhQiaMYm9O2AsoNMHXbXDYN2b4yBreI8TJIBfpdw7UIo1JP5566Sbb2ei_zUC0" rel="nofollow" onclick="DownloadSubtitle(this)" id="downloadButton" class="button Positive">
  60. """
  61. downloadlink_pattern = "...<a href=\"(.+?)\" rel=\"nofollow\" onclick=\"DownloadSubtitle"
  62. # group(1) = link
  63.  
  64. # <input type="hidden" name="__VIEWSTATE" id="__VIEWSTATE" value="/wEPDwUKLTk1MDk4NjQwM2Rk5ncGq+1a601mEFQDA9lqLwfzjaY=" />
  65. viewstate_pattern = "<input type=\"hidden\" name=\"__VIEWSTATE\" id=\"__VIEWSTATE\" value=\"([^\n\r\t]*?)\" />"
  66.  
  67. # <input type="hidden" name="__PREVIOUSPAGE" id="__PREVIOUSPAGE" value="V1Stm1vgLeLd6Kbt-zkC8w2" />
  68. previouspage_pattern = "<input type=\"hidden\" name=\"__PREVIOUSPAGE\" id=\"__PREVIOUSPAGE\" value=\"([^\n\r\t]*?)\" />"
  69.  
  70. # <input type="hidden" name="subtitleId" id="subtitleId" value="329405" />
  71. subtitleid_pattern = "<input type=\"hidden\" name=\"subtitleId\" id=\"subtitleId\" value=\"(\d+?)\" />"
  72.  
  73. # <input type="hidden" name="typeId" value="zip" />
  74. typeid_pattern = "<input type=\"hidden\" name=\"typeId\" value=\"([^\n\r\t]{3,15})\" />"
  75.  
  76. # <input type="hidden" name="filmId" value="78774" />
  77. filmid_pattern = "<input type=\"hidden\" name=\"filmId\" value=\"(\d+?)\" />"
  78.  
  79.  
  80. #====================================================================================================================
  81. # Functions
  82. #====================================================================================================================
  83.  
  84. def to_subscene_lang(language):
  85.     if language == "Chinese":            return "Chinese BG code"
  86.     elif language == "PortugueseBrazil": return "Brazillian Portuguese"
  87.     elif language == "SerbianLatin":     return "Serbian"
  88.     elif language == "Ukrainian":        return "Ukranian"
  89.     else:                                return language
  90.  
  91.  
  92.  
  93. def find_movie(content, title, year):
  94.     url_found = None
  95.     for matches in re.finditer(movie_season_pattern, content, re.IGNORECASE | re.DOTALL):
  96.         log( __name__ ,"%s Found movie on search page: %s (%s)" % (debug_pretext, matches.group(2), matches.group(3)))
  97.         if string.find(string.lower(matches.group(2)),string.lower(title)) > -1:
  98.             if matches.group(3) == year:
  99.                 log( __name__ ,"%s Matching movie found on search page: %s (%s)" % (debug_pretext, matches.group(2), matches.group(3)))
  100.                 url_found = matches.group(1)
  101.                 break
  102.     return url_found
  103.  
  104.  
  105. def find_tv_show_season(content, tvshow, season):
  106.     url_found = None
  107.     for matches in re.finditer(movie_season_pattern, content, re.IGNORECASE | re.DOTALL):
  108.         log( __name__ ,"%s Found tv show season on search page: %s" % (debug_pretext, matches.group(2).decode("utf-8")))
  109.         if string.find(string.lower(matches.group(2)),string.lower(tvshow) + " ") > -1:
  110.             if string.find(string.lower(matches.group(2)),string.lower(season)) > -1:
  111.                 log( __name__ ,"%s Matching tv show season found on search page: %s" % (debug_pretext, matches.group(2).decode("utf-8")))
  112.                 url_found = matches.group(1)
  113.                 break
  114.     return url_found
  115.  
  116.  
  117. def getallsubs(response_url, content, language, title, subtitles_list, search_string):
  118.     for matches in re.finditer(subtitle_pattern, content, re.IGNORECASE | re.DOTALL):
  119.         languagefound = matches.group(3)
  120.         if languagefound == to_subscene_lang(language):
  121.             link = main_url + matches.group(1)
  122.             languageshort = languageTranslate(language,0,2)
  123.             filename   = matches.group(4)
  124.             hearing_imp = len(matches.group(5)) > 0
  125.             if search_string != "":
  126.                 log( __name__ , "string.lower(filename) = >" + string.lower(filename) + "<" )
  127.                 log( __name__ , "string.lower(search_string) = >" + string.lower(search_string) + "<" )
  128.                 if string.find(string.lower(filename),string.lower(search_string)) > -1:
  129.                     log( __name__ ,"%s Subtitles found: %s, %s" % (debug_pretext, languagefound, filename))
  130.                     subtitles_list.append({'rating': '0', 'movie':  title, 'filename': filename, 'sync': False, 'link': link, 'language_flag': 'flags/' + languageshort + '.gif', 'language_name': language, 'hearing_imp': hearing_imp})
  131.             else:
  132.                 log( __name__ ,"%s Subtitles found: %s, %s" % (debug_pretext, languagefound, filename))
  133.                 subtitles_list.append({'rating': '0', 'movie':  title, 'filename': filename, 'sync': False, 'link': link, 'language_flag': 'flags/' + languageshort + '.gif', 'language_name': language, 'hearing_imp': hearing_imp})
  134.  
  135.  
  136. def geturl(url):
  137.     log( __name__ ,"%s Getting url:%s" % (debug_pretext, url))
  138.     try:
  139.         response   = urllib2.urlopen(url)
  140.         content    = response.read()
  141.         #Fix non-unicode charachters in movie titles
  142.         strip_unicode = re.compile("([^-_a-zA-Z0-9!@#%&=,/'\";:~`\$\^\*\(\)\+\[\]\.\{\}\|\?\<\>\\]+|[^\s]+)")
  143.         content    = strip_unicode.sub('', content)
  144.         return_url = response.geturl()
  145.     except:
  146.         log( __name__ ,"%s Failed to get url:%s" % (debug_pretext, url))
  147.         content    = None
  148.         return_url = None
  149.     return(content, return_url)
  150.  
  151.  
  152. def search_subtitles( file_original_path, title, tvshow, year, season, episode, set_temp, rar, lang1, lang2, lang3, stack ): #standard input
  153.     subtitles_list = []
  154.     msg = ""
  155.     if len(tvshow) == 0:
  156.         search_string = title
  157.     if len(tvshow) > 0:
  158.         search_string = tvshow + " - " + seasons[int(season)] + " Season"
  159.     log( __name__ ,"%s Search string = %s" % (debug_pretext, search_string))
  160.     url = main_url + "filmsearch.aspx?q=" + urllib.quote_plus(search_string)
  161.     content, response_url = geturl(url)
  162.     if content is not None:
  163.         if re.search("subtitles-\d{2,10}\.aspx", response_url, re.IGNORECASE):
  164.             log( __name__ ,"%s One movie found, getting subs ..." % debug_pretext)
  165.             getallsubs(response_url, content, lang1, title, subtitles_list,  "")
  166.             if (lang2 != lang1): getallsubs(response_url, content, lang2, title, subtitles_list, "")
  167.             if ((lang3 != lang2) and (lang3 != lang1)): getallsubs(response_url, content, lang3, title, subtitles_list, "")
  168.         else:
  169.             if len(tvshow) == 0:
  170.                 log( __name__ ,"%s Multiple movies found, searching for the right one ..." % debug_pretext)
  171.                 subspage_url = find_movie(content, title, year)
  172.                 if subspage_url is not None:
  173.                     log( __name__ ,"%s Movie found in list, getting subs ..." % debug_pretext)
  174.                     url = main_url + subspage_url
  175.                     content, response_url = geturl(url)
  176.                     if content is not None:
  177.                         getallsubs(response_url, content, lang1, title, subtitles_list, "")
  178.                         if (lang2 != lang1): getallsubs(response_url, content, lang2, title, subtitles_list, "")
  179.                         if ((lang3 != lang2) and (lang3 != lang1)): getallsubs(response_url, content, lang3, title, subtitles_list, "")
  180.                 else:
  181.                     log( __name__ ,"%s Movie not found in list: %s" % (debug_pretext, title))
  182.                     if string.find(string.lower(title),"&") > -1:
  183.                         title = string.replace(title, "&", "and")
  184.                         log( __name__ ,"%s Trying searching with replacing '&' to 'and': %s" % (debug_pretext, title))
  185.                         subspage_url = find_movie(content, title, year)
  186.                         if subspage_url is not None:
  187.                             log( __name__ ,"%s Movie found in list, getting subs ..." % debug_pretext)
  188.                             url = main_url + subspage_url
  189.                             content, response_url = geturl(url)
  190.                             if content is not None:
  191.                                 getallsubs(response_url, content, lang1, title, subtitles_list, "")
  192.                                 if (lang2 != lang1): getallsubs(response_url, content, lang2, title, subtitles_list, "")
  193.                                 if ((lang3 != lang2) and (lang3 != lang1)): getallsubs(response_url, content, lang3, title, subtitles_list, "")
  194.                         else:
  195.                             log( __name__ ,"%s Movie not found in list: %s" % (debug_pretext, title))
  196.             if len(tvshow) > 0:
  197.                 log( __name__ ,"%s Multiple tv show seasons found, searching for the right one ..." % debug_pretext)
  198.                 tv_show_seasonurl = find_tv_show_season(content, tvshow, seasons[int(season)])
  199.                 if tv_show_seasonurl is not None:
  200.                     log( __name__ ,"%s Tv show season found in list, getting subs ..." % debug_pretext)
  201.                     url = main_url + tv_show_seasonurl
  202.                     content, response_url = geturl(url)
  203.                     if content is not None:
  204.                         search_string = "s%#02de%#02d" % (int(season), int(episode))
  205.                         getallsubs(response_url, content, lang1, title, subtitles_list, search_string)
  206.                         if (lang2 != lang1): getallsubs(response_url, content, lang2, title, subtitles_list, search_string)
  207.                         if ((lang3 != lang2) and (lang3 != lang1)): getallsubs(response_url, content, lang3, title, subtitles_list, search_string)
  208.  
  209.  
  210.     return subtitles_list, "", msg #standard output
  211.  
  212.  
  213. def download_subtitles (subtitles_list, pos, zip_subs, tmp_sub_dir, sub_folder, session_id): #standard input
  214.     url = subtitles_list[pos][ "link" ]
  215.     language = subtitles_list[pos][ "language_name" ]
  216.     content, response_url = geturl(url)
  217.     match=  re.compile(downloadlink_pattern).findall(content)
  218.     if match:
  219.         downloadlink = "http://subscene.com"  + match[0]
  220.         log( __name__ ,"%s Downloadlink: %s " % (debug_pretext, downloadlink))
  221.         viewstate = 0
  222.         previouspage = 0
  223.         subtitleid = 0
  224.         typeid = "zip"
  225.         filmid = 0
  226.         postparams = urllib.urlencode( { '__EVENTTARGET': 's$lc$bcr$downloadLink', '__EVENTARGUMENT': '' , '__VIEWSTATE': viewstate, '__PREVIOUSPAGE': previouspage, 'subtitleId': subtitleid, 'typeId': typeid, 'filmId': filmid} )
  227.         class MyOpener(urllib.FancyURLopener):
  228.             version = 'User-Agent=Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.2.3) Gecko/20100401 Firefox/3.6.3 ( .NET CLR 3.5.30729)'
  229.         my_urlopener = MyOpener()
  230.         my_urlopener.addheader('Referer', url)
  231.         log( __name__ ,"%s Fetching subtitles using url '%s' with referer header '%s' and post parameters '%s'" % (debug_pretext, downloadlink, url, postparams))
  232.         response = my_urlopener.open(downloadlink, postparams)
  233.         local_tmp_file = os.path.join(tmp_sub_dir, "subscene.xxx")
  234.         try:
  235.             log( __name__ ,"%s Saving subtitles to '%s'" % (debug_pretext, local_tmp_file))
  236.             if not os.path.exists(tmp_sub_dir):
  237.                 os.makedirs(tmp_sub_dir)
  238.             local_file_handle = open(local_tmp_file, "w" + "b")
  239.             local_file_handle.write(response.read())
  240.             local_file_handle.close()
  241.             #Check archive type (rar/zip/else) through the file header (rar=Rar!, zip=PK)
  242.             myfile = open(local_tmp_file, "rb")
  243.             myfile.seek(0)
  244.             if (myfile.read(1) == 'R'):
  245.                 typeid = "rar"
  246.                 packed = True
  247.                 log( __name__ , "Discovered RAR Archive")
  248.             else:
  249.                 myfile.seek(0)
  250.                 if (myfile.read(1) == 'P'):
  251.                     typeid = "zip"
  252.                     packed = False
  253.                     log( __name__ , "Discovered ZIP Archive")
  254.                 else:
  255.                     typeid = "srt"
  256.                     packed = False
  257.                     subs_file = local_tmp_file
  258.                     log( __name__ , "Discovered a non-archive file")
  259.             myfile.close()
  260.             local_tmp_file = os.path.join(tmp_sub_dir, "subscene." + typeid)
  261.             os.rename(os.path.join(tmp_sub_dir, "subscene.xxx"), local_tmp_file)
  262.             log( __name__ , "Saving to %s", local_tmp_file)
  263.         except:
  264.             log( __name__ ,"%s I don't know why this exception happens!" % (debug_pretext))
  265.         if packed:
  266.             files = os.listdir(tmp_sub_dir)
  267.             init_filecount = len(files)
  268.             max_mtime = 0
  269.             filecount = init_filecount
  270.             # determine the newest file from tmp_sub_dir
  271.             for file in files:
  272.                 if (string.split(file,'.')[-1] in ['srt','sub','txt']):
  273.                     mtime = os.stat(os.path.join(tmp_sub_dir, file)).st_mtime
  274.                     if mtime > max_mtime:
  275.                         max_mtime =  mtime
  276.             init_max_mtime = max_mtime
  277.             time.sleep(2)  # wait 2 seconds so that the unpacked files are at least 1 second newer
  278.             xbmc.executebuiltin("XBMC.Extract(" + local_tmp_file + "," + tmp_sub_dir +")")
  279.             waittime  = 0
  280.             while (filecount == init_filecount) and (waittime < 20) and (init_max_mtime == max_mtime): # nothing yet extracted
  281.                 time.sleep(1)  # wait 1 second to let the builtin function 'XBMC.extract' unpack
  282.                 files = os.listdir(tmp_sub_dir)
  283.                 filecount = len(files)
  284.                 # determine if there is a newer file created in tmp_sub_dir (marks that the extraction had completed)
  285.                 for file in files:
  286.                     if (string.split(file,'.')[-1] in ['srt','sub','txt']):
  287.                         mtime = os.stat(os.path.join(tmp_sub_dir, file)).st_mtime
  288.                         if (mtime > max_mtime):
  289.                             max_mtime =  mtime
  290.                 waittime  = waittime + 1
  291.             if waittime == 20:
  292.                 log( __name__ ,"%s Failed to unpack subtitles in '%s'" % (debug_pretext, tmp_sub_dir))
  293.             else:
  294.                 log( __name__ ,"%s Unpacked files in '%s'" % (debug_pretext, tmp_sub_dir))
  295.                 for file in files:
  296.                     # there could be more subtitle files in tmp_sub_dir, so make sure we get the newly created subtitle file
  297.                     if (string.split(file, '.')[-1] in ['srt', 'sub', 'txt']) and (os.stat(os.path.join(tmp_sub_dir, file)).st_mtime > init_max_mtime): # unpacked file is a newly created subtitle file
  298.                         log( __name__ ,"%s Unpacked subtitles file '%s'" % (debug_pretext, file))
  299.                         subs_file = os.path.join(tmp_sub_dir, file)
  300.         log( __name__ ,"%s Subtitles saved to '%s'" % (debug_pretext, local_tmp_file))
  301.         return False, language, subs_file #standard output
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!