API tools faq
paste
Advertisement
Guest User

fysa

a guest
Feb 13th, 2009
277
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
Python 30.37 KB | None | 0 0
raw download clone embed print report
  1. #!/usr/bin/env python
  2. #encoding:utf-8
  3.  
  4. import urllib
  5. import xml.dom.minidom
  6. import re
  7. import time
  8. import os
  9. import sys                                        
  10. import string
  11.  
  12. from tvdb_api import (tvdb_error, tvdb_shownotfound, tvdb_seasonnotfound,
  13.     tvdb_episodenotfound, tvdb_episodenotfound, tvdb_attributenotfound, tvdb_userabort)
  14. from tvdb_api import Tvdb
  15.  
  16. ######
  17. # TV #
  18. ######
  19.  
  20. __author__ = "minimad/Neil"
  21. __version__ = "0.88"
  22.  
  23. ################################### MEGA IMPORTANT ##################################################
  24. #
  25. # This script also requires the tvdb_api from http://github.com/dbr/tvdb_api/tree/master
  26. # you will require ALL the files (well, maybe not the setup.py) and they need to be in the same dir
  27. # as this script
  28. #
  29. # Expected Show format is (Showname/Season XX/Showname - SxxExx - Episodename.ext e.g.
  30. # House/Season 02/House - S02E01 - Autopsy.avi
  31. #
  32. ################################### MEGA IMPORTANT ##################################################
  33.  
  34. ################################### CHANGE LOG ######################################################
  35. #
  36. # 090103 1600   Now uses SAB 0.4.6 illegal character replacement behaviour
  37. #
  38. # 090112 2300   Uses tvdb_api to validate show name
  39. #
  40. # 090114 2300   Cleaned up the code, used re.pattern in print statements where possible
  41. #               and tried to limit number of places to change for new formats by using vars
  42. #
  43. # 090117 2300   Fixed bug - Queued name is meant to be original report, NOT reformated version
  44. #
  45. # 090117 2330   Added required video format functionality
  46. #
  47. # 090117 2345   Moved Season/Episode regex formats to user config area
  48. #
  49. # 090120 2045   Added Debug setting for 'print' statements
  50. #               Fixed IsMissing regex to look for both cases of S and E i.e. s and S
  51. #               Fixed season_to_check variable
  52. #               A few wording changes
  53. #
  54. # 090121 2330   Made 'Smart' queue optional
  55. #               Removing Illegal Chars at end of cleanSeriesName if Win32
  56. #               Moved Format check into isWanted.  Check format before checking for show.
  57. #               Should reduce processing time by not checking all shows then finding out that format isn't wanted
  58. #               Removed sum_file_size function as not
  59. #
  60. # 090122 0015   Added 'extra' debug messages
  61. #               Fixed 'Smart' Queue
  62. #               Moved Change Log to Top of Script
  63. #               Added 'Known Issues'
  64. #               Made Code more consistant
  65. #
  66. # 090122 2200   Fixed 'isMissing', left a test string in place, so it always thought you needed the episode
  67. #               Also it 'bombed' out because I left an icorrectly anmed variable in
  68. #
  69. # 090123 2200   Added option to choose SABnzbd style or tvnamer.py style, illegal character replacement
  70. #               Added option to force Windows compliant names, useful if you run this on a linux box but access via windows
  71. #               Now we reformat a NewzBin into the same format as a 'non' newzbin feed, Smart Queue should work better now
  72. #               Added an 'Aliases' function to trasnlate known 'Aliases' into proper show names, at least until the tvdb_api has
  73. #               this functionality which is due in the next few weeks
  74. #
  75. # 090124 0015   'Smart' queue wasn't being smart, it was still checking filename against a reformated string, now fixed
  76. #               However the script is considerably slower due to the number of calls to tvdb_api, now once per queue entry per queue check
  77. #
  78. # 090124 2300   Fixed NewzBin adding to queue, was trying to add entire url (thanks markus101).
  79. #
  80. # 090125 0935   New Function, isInHistorySmart (ONLY 0.5.0 onwards), checks the history for the show, episode
  81. #               NOT COMPLETE, NOT ACTIVE IN CODE
  82. #
  83. # 090125 2200  0.80 NEW FEATURE - Per Show AND Season Format Matching.  Only get the format specified for the show and season
  84. #
  85. # 090126 1430  0.81 Should find files in ANY supported format (supported formats in Importnat Info section), no need to rename files
  86. #
  87. # 090126 2330       MAJOR Code Cleanup. Most probably broke everything.
  88. #
  89. # 090127 1100  0.82 Fixed - MATCH FOUND now returns the Season & Episode rather than the regex pattern that found it
  90. #                   (regex pattern looks like gibberish
  91. #                   Fixed - General Format Matching - I had changed the regex, now back to what it was.
  92. #
  93. # 090128 2220  0.84 Multiple Feed Functionality, Script now smart enough to know a newzbin feed
  94. #                   Fixed - NewzBin format check
  95. #
  96. # 090206 2050  0.88 Changed way isWanted looks for a show, it now loops through the tvdirs checking a lowercase
  97. #                   dir against a lowercase series_title
  98. #
  99. #
  100. ################################### CHANGE LOG ######################################################
  101.  
  102. ################################### KNOWN ISSUES ####################################################
  103. #
  104. # Script is too fast and gets 'Trying to fetch NZB from.....' in the Queue.  'Smart' queue and 'Normal' Queue
  105. # are unable to check show, episode or filename in this instance so they assume it isn't in the queue.
  106. #
  107. # This script is UNABLE to process feeds that are gzip'd, TVBINZ etc are now using gzip'd feeds
  108. # Use www.feedburner.com to turn them back into 'raw' feeds.
  109. #
  110. # Seems to have a problem with shows that have a : (colon) in them e.g. CSI: Miami, CSI: NY etc
  111. #
  112. ################################### KNOWN ISSUES ####################################################
  113.  
  114. ################################### TO DO (NOT IN ORDER) ############################################
  115. #
  116. # Improve script speed, All those tvdb_api calls, REALLY slows it down, maybe cache the answers????
  117. # Have config settings in another file.
  118. #
  119. ################################### TO DO ###########################################################
  120.  
  121.  
  122. ################################### IMPORTANT INFO ##################################################
  123. #  To ignore a whole season, create a file or directory in the directory for your show with this name
  124. #  ignore Season x
  125. #  e.g. c:\tv\lost\ignore Season 1
  126. #
  127. #  To use Per Show and Season format matching, create a file or directory in the SHOW directory with
  128. #  name format Sxx.yyyy.format
  129. #  Where xx is the season number
  130. #  Where yyyy is the format, either xvid or x264
  131. #  e.g. S01.xvid.format
  132. #       S02.x264.format
  133. #
  134. #  Supported File Naming Formats:-
  135. #
  136. #  seriesname.s01e02.dsr.nf.avi
  137. #  seriesname.S01E02.PROPER.dsr.nf.avi
  138. #  seriesname.s01.e02.avi
  139. #  seriesname-s01e02.avi
  140. #  seriesname-s01e02.the.wrong.ep.name.avi
  141. #  seriesname - [01x02].avi
  142. #  seriesname - [01x002].avi
  143. #  seriesname-[01x02].avi
  144. #  seriesname [01x02].avi
  145. #  seriesname [01x02] epname.avi
  146. #  seriesname [01x02] - the wrong ep name.avi
  147. #  seriesname - [01x02] - the wrong ep name.avi
  148. #  seriesname.01x02.epname.avi
  149. #  seriesname.102.epname.avi
  150. #  seriesname_s1e02_epname.avi
  151. #  seriesname - s01e02 - dsr.nf.avi
  152. #  seriesname - s01e02 - the wrong ep name.avi
  153. #  seriesname - s01e02 - the_wrong_ep_name!.avi
  154. #
  155. ################################### IMPORTANT INFO ##################################################
  156.  
  157. #################################### CHANGE TO YOUR OWN VALUES ######################################
  158. #
  159. # set this to the location of your downloads.  the first entry must be your live download area
  160. if sys.platform == "win32":
  161.     tv_dirs=[ "Z:" ]
  162. else:
  163.     tv_dirs=[ "/share/Qmultimedia/TV_Shows" ]
  164.  
  165. # the RSS link to your search
  166. nzbfeeds=[
  167. "http://myfeed.rss",
  168. "http://feeds.feedburner.com/minimad-csi"
  169. ]
  170.  
  171. # your SABNZB address
  172. my_SAB="http://192.168.1.200:8800"
  173. # /sabnzbd is added below
  174.  
  175. # additional SAB parameters to e.g. specify the category, and/or script to run.  see http://sabnzbd.wikidot.com/automation-support
  176. my_SAB_params="&cat=tv"
  177.  
  178. # Use NewzBin feed
  179. # Changes several sections to use NewzBin specific functionality
  180. # NO LONGER USED, Script is Mart enough to know a NewzBin feed when it sees it
  181. # becuase the feed has newzbin in the url e.g. http://www.newzbin.com
  182. #NewzBin = False
  183.  
  184. # theTVDB api
  185. # Set tvdb_interactive=True to select shows returned, otherwise it takes first show returned (usually the right one)
  186. tvdb_interactive=False
  187.  
  188. # Required video formats
  189. # for x264 enter 'x264'
  190. # for xvid enter 'xvid'
  191. # for 720p enter '720p'
  192. # for 1080p enter '1080'
  193. # for multiple formats put | between them and brackets around each group e.g.
  194. # ([x264])|([xvid])
  195. #
  196. video_formats='x264'
  197.  
  198. # Season/Episode Formats
  199. # Standard Regex with brackets around each format and seperated by |
  200. season_formats="([sS][0-9][0-9])|([0-9]?[0-9][xX])"
  201. episode_formats="([eE][0-9][0-9])|([xX][0-9][0-9])"
  202.  
  203. # DEBUG
  204. # Set debug to True, to see what this scrip is doing
  205. debug = True
  206. # theTVDB api
  207. # Set tvdb_debug=True to see debug info from theTVDB api
  208. tvdb_debug=False
  209.  
  210. # 'Smart' Queue checking
  211. # Set to True to use 'Smart' Queue checking
  212. # Looks for the Show, Episode in Queue rather than the filename
  213. useSmartQueue = True
  214.  
  215. # SABnzbd or tvnamer.py style illegal char replaement
  216. # Set to True to use SABnzbd Style
  217. SABnzbdIllegalCharsStyle = False
  218.  
  219. # Force Windows Compliant Names
  220. # Set to True to force script to use windows compliant names
  221. force_windows_compliant_filenames = True
  222.  
  223. ################################### CHANGE TO YOUR OWN VALUES #####################################
  224.  
  225. config = {}
  226.  
  227. reportdict = {}
  228.  
  229. config['valid_filename_chars'] = """0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ!@£$%^&*()_+=-[]:{}"'.,<>`~? """
  230.  
  231. config['with_ep_name'] = '%(seriesname)s - S%(seasno)02dE%(epno)02d - %(epname)s'
  232.  
  233. # Force the stripping of invalid Windows characters, even if the current
  234. # platform is not detected as Windows
  235. config['force_windows_compliant_filenames'] = True
  236.  
  237. if sys.platform == "win32" or config['force_windows_compliant_filenames']:
  238.     # " * : < > ? | \ are all invalid on Windows
  239.     config['valid_filename_chars'] = config['valid_filename_chars'].replace("\"*:<>?|\\","")
  240.  
  241. config['valid_filename_chars_regex'] = re.escape(config['valid_filename_chars'])
  242.  
  243. # Regex's to parse filenames with. Must have 3 groups, seriesname, season number
  244. # and episode number. Use (?: optional) non-capturing groups if you need others.
  245. # taken from tvnamer.py script
  246. config['name_parse'] = [
  247.     # foo_[s01]_[e01]
  248.     re.compile('''^([%s]+?)[ \._\-]\[[Ss]([0-9]+?)\]_\[[Ee]([0-9]+?)\]?([%s]+)[^\\/]*$''' % (config['valid_filename_chars_regex'], config['valid_filename_chars_regex']) ),
  249.     # foo.1x09*
  250.     re.compile('''^([%s]+?)[ \._\-]\[?([0-9]+)x([0-9]+)([%s]+)[^\\/]*$''' % (config['valid_filename_chars_regex'], config['valid_filename_chars_regex']) ),
  251.     # foo.s01e01.title
  252.     re.compile('''^([%s]+?)[ \._\-][Ss]([0-9]+)[\.\- ]?[Ee]([0-9]+)[ \._\-]([%s]+)[^\\/]*$''' % (config['valid_filename_chars_regex'], config['valid_filename_chars_regex']) ),
  253.     # foo.s01.e01, foo.s01_e01, foo.s01e01
  254.     re.compile('''^([%s]+?)[ \._\-][Ss]([0-9]+)[\.\- ]?[Ee]([0-9]+)([%s]+)[^\\/]*$''' % (config['valid_filename_chars_regex'], config['valid_filename_chars_regex']) ),
  255.     # foo.103*
  256.     re.compile('''^([%s]+)[ \._\-]([0-9]{1})([0-9]{2})[\._ -]([%s]+)[^\\/]*$''' % (config['valid_filename_chars_regex'], config['valid_filename_chars_regex']) ),
  257.     # foo.0103*
  258.     re.compile('''^([%s]+)[ \._\-]([0-9]{2})([0-9]{2,3})[\._ -]([%s]+)[^\\/]*$''' % (config['valid_filename_chars_regex'], config['valid_filename_chars_regex']) ),
  259. ]
  260.  
  261.  
  262. # Class to allow an exception to be raised
  263. # if format is not wanted
  264. class FormatNotWanted:
  265.     pass
  266.  
  267. class formatError:
  268.     pass
  269.  
  270. # SABnzbd style illegal chars
  271. illegal = r'\/<>?*:;|"'
  272. legal   = r'++{}!@--#`'
  273. translate_table = string.maketrans(illegal, legal)
  274.  
  275. #Directory Seperator Character (default linux)
  276. ds="/"
  277. #If Win32 then double backslash
  278. if sys.platform == "win32":
  279.     ds="\\"
  280.  
  281. already=[]
  282.  
  283. #RegEx Compiles
  284. daily=re.compile("([0-9][0-9][0-9][0-9]-[0-9][0-9]-[0-9][0-9])|([0-9][0-9][0-9][0-9]\.[0-9][0-9]\.[0-9][0-9])")
  285. season_re = re.compile( season_formats )
  286. episode_re = re.compile( episode_formats )
  287. video_formats_re = re.compile( video_formats, re.IGNORECASE )                                                
  288.                
  289.  
  290.  
  291. #### SimpleCache Start - jason.fisher@gmail.com
  292.  
  293. class SimpleCache:
  294.     def __init__(self, filename="simplecache.pyd", debug=1, safe=1):
  295.                
  296.         self.file = os.path.join(os.path.dirname(sys.argv[0]),filename)
  297.         self.debug = debug
  298.         self.safe = safe
  299.         self.init = 0
  300.  
  301.         self.msg("loading " + self.file + " .. ")    
  302.         try:
  303.             cache = open(self.file,"r")
  304.         except IOError, EOFError:
  305.             try:
  306.                 self.msg("new cache file: " + self.file)
  307.                 cache = open(self.file,"w")
  308.                 self.data = {'evalcacheversion_creation':'20090212a-jmf'}
  309.                 self.msg(self.data)
  310.                 pickle.dump(self.data, cache)
  311.                 cache.close()
  312.                 self.msg(".. created.")
  313.                 cache = open(self.file,"r")
  314.             except IOError, EOFError:
  315.                 self.msg("cannot open/create " + self.file)
  316.                 return 0
  317.                
  318.         self.data = pickle.load(cache)
  319.         self.msg(".. done.")
  320.         self.msg(self.data)
  321.         cache.close()
  322.        
  323.     def msg(self, val):
  324.         if self.debug:
  325.             print val
  326.            
  327.     def save(self):
  328.         self.msg("saving " + self.file)
  329.         self.msg(self.data)
  330.         try:
  331.             cache = open(self.file,"w")
  332.             pickle.dump(self.data, cache)
  333.             cache.close()
  334.         except IOError:
  335.             self.msg("error")
  336.         self.msg(".. done.")       
  337.  
  338.     def read(self, key):           
  339.         self.msg("looking for " + str(key))
  340.         if str(key) in self.data:
  341.             if self.debug:
  342.                 self.msg("hit: " + str(key) + " = " + str(self.data[str(key)]))
  343.             return self.data[str(key)]
  344.            
  345.         self.msg("not cached.")
  346.         return 0
  347.        
  348.     def write(self, key, value):
  349.         self.msg("storing " + str(key))
  350.         self.data[str(key)] = str(value)
  351.        
  352.         if self.debug and self.data[str(key)]:
  353.             self.msg(".. done: " + str(self.data[str(key)]))
  354.        
  355.         if self.safe:
  356.             self.save()
  357.            
  358.         return self.data[str(key)]
  359.  
  360. #### Simple Caching End
  361.  
  362. import pickle
  363. cache = SimpleCache()
  364.  
  365. ####           
  366.        
  367.  
  368.  
  369. def removeIllegalChars(origstring):
  370.  
  371.     if SABnzbdIllegalCharsStyle:
  372.         try:
  373.             return str(origstring).translate(translate_table)
  374.         except:
  375.             return origstring
  376.     else:
  377.         try:
  378.             # convert unicode to ASCII
  379.             newstring = origstring.encode('ascii', 'ignore')
  380.             # replace illegal chars with nothing
  381.             return re.sub("[*:<>|]", "", newstring).strip()
  382.         except:
  383.             return origstring
  384.  
  385.     #end if SABnzbdIllegalStyle
  386.  
  387. #end def removeIllegalChars
  388.  
  389. def isInQueue(download_title):
  390.     queue=xml.dom.minidom.parse(urllib.urlopen(my_SAB+"/sabnzbd/api?mode=qstatus&output=xml"))
  391.     for job in queue.getElementsByTagName("job"):
  392.         filename=job.getElementsByTagName("filename")[0].childNodes[0].data
  393.         regex_download_title_string = removeIllegalChars(download_title)
  394.         regex_download_title = re.compile(regex_download_title_string, re.IGNORECASE)
  395.         if re.match(regex_download_title, filename):
  396.             if debug:
  397.                 print("IS IN QUEUE: " + regex_download_title.pattern)
  398.             #end if debug
  399.             return 1
  400.         #end if re.match
  401.     #end for job
  402.     if debug:
  403.         print("IS NOT IN QUEUE: " + regex_download_title.pattern)
  404.     #end if debug
  405.     return 0
  406. #end def isInQueue
  407.  
  408. def isInQueueSmart(series, season, episode):
  409.     print("ENTERED isInQueueSmart")
  410.     # Compile the regex
  411.     regex_download_title = re.compile(series + " - S" + season + "E" + episode, re.IGNORECASE)
  412.  
  413.     # Get the Queue
  414.     queue=xml.dom.minidom.parse(urllib.urlopen(my_SAB+"/sabnzbd/api?mode=qstatus&output=xml"))
  415.  
  416.     # Process each job in Queue
  417.     for job in queue.getElementsByTagName("job"):
  418.         filename=job.getElementsByTagName("filename")[0].childNodes[0].data
  419.         try:
  420.             if debug:
  421.                 print("CHECK QUEUE: " + filename)
  422.             #end if debug
  423.  
  424.             filename = formatReport(filename)
  425.             series,epstr,eptitle=filename.split(' - ')
  426.             series=cleanSeriesName(series)
  427.             filename=series + " - " + epstr + " - " + eptitle
  428.  
  429.             if debug:
  430.                 print("CHECK REFORMAT QUEUE: " + filename)
  431.             #end if debug
  432.             if re.search(regex_download_title, filename):
  433.                 if debug:
  434.                     print("IS IN QUEUE: " + regex_download_title.pattern)
  435.                 #end if debug
  436.                 return 1
  437.             #end if re.match
  438.         except:
  439.             # Queue Check Failed, so assume it's not in Queue
  440.             pass
  441.     #end for job
  442.     if debug:
  443.         print("IS NOT IN QUEUE: " + regex_download_title.pattern)
  444.     #end if debug
  445.     return 0
  446. #end def isInQueue
  447.  
  448. def isInHistorySmart(series, season, episode):
  449.     # Compile the regex
  450.     regex_download_title = re.compile(series + " - S" + season + "E" + episode, re.IGNORECASE)
  451.  
  452.     # Get the Histroy
  453.     queue=xml.dom.minidom.parse(urllib.urlopen(my_SAB+"/sabnzbd/api?mode=history&output=xml"))
  454.  
  455.     # Process each job in Queue
  456.     for job in queue.getElementsByTagName("slot"):
  457.         jobname=job.getElementsByTagName("name")[0].childNodes[0].data
  458.         try:
  459.             if debug:
  460.                 print("CHECK HISTORY: " + jobname)
  461.             #end if debug
  462.             jobname=reformatReport(filename)
  463.             series,epstr,eptitle=jobname.split(' - ')
  464.             series=cleanSeriesName(series)
  465.             jobname=series + " - " + epstr + " - " + eptitle
  466.             if debug:
  467.                 print("CHECK REFORMAT HISTORY: " + jobname)
  468.             #end if debug
  469.             if re.search(regex_download_title, jobname):
  470.                 if debug:
  471.                     print("IS IN HISTORY: " + regex_download_title.pattern)
  472.                 #end if debug
  473.                 return 1
  474.             #end if re.match
  475.         except:
  476.             # Queue Check Failed, so assume it's not in Queue
  477.             pass
  478.     #end for job
  479.     if debug:
  480.         print("IS NOT IN HISTORY: " + regex_download_title.pattern)
  481.     #end if debug
  482.     return 0
  483. #end def isInHistorySmart
  484.  
  485. def isWanted(series_title):
  486.     if debug:
  487.         print("CHECK WANTED: " + series_title)
  488.     #end if debug
  489.  
  490.     for dir in tv_dirs:
  491.         for filename in os.listdir(dir):
  492.             print("DEBUG: " + filename.lower() )
  493.             print("DEBUG: " + series_title.lower() )
  494.             if debug:
  495.                 print("LOOKING FOR: " + dir + ds + series_title)
  496.             #end if debug
  497.             if filename.lower() == series_title.lower():
  498.                 if debug:
  499.                     print("SHOW WANTED: " + series_title)
  500.                 #end if debug
  501.                 return 1
  502.             #end if os.path
  503.         #end for filename
  504.     #end for dir
  505.     if debug:
  506.         print("SHOW NOT WANTED: " + series_title)
  507.     #end if debug
  508.     return 0
  509. #end def isWanted
  510.  
  511. def isFormatWanted(series_title, report, season, feed_type):
  512.     # Override Format checking for NewzBin feeds
  513.     if feed_type == 'NewzBin':
  514.         if debug:
  515.             print("NEWZBIN FORMAT OVERRIDE: " + report)
  516.         #end if debug
  517.         return 1
  518.     #end if feed_type
  519.  
  520.     # Allow per Show/Season Format OverRide
  521.     for dir in tv_dirs:
  522.         if os.path.exists(dir + ds + series_title):
  523.             for filename in os.listdir(dir + ds + series_title):
  524.                 if filename[9:] == 'format':
  525.                     if filename[1:3] == season:
  526.                         if re.search(filename[4:8], report , re.IGNORECASE):
  527.                             if debug:
  528.                                 print("SHOW FORMAT WANTED: " + report)
  529.                             #end if debug
  530.                             return 1
  531.                         else:
  532.                             if debug:
  533.                                 print("SHOW FORMAT NOT WANTED: " + report)
  534.                             #end if debug
  535.                             return 0
  536.                         #end if re.search
  537.                     #end if file[1:3]
  538.                 #end if file[9:]
  539.             #end for file
  540.         #end if os.path
  541.     #end for dir
  542.  
  543.     # General Format Wanted
  544.     # Used if Show/Season not specified
  545.     format_object = video_formats_re.search( report , re.IGNORECASE)
  546.     if format_object:
  547.         if debug:
  548.             print("FORMAT WANTED: " + report)
  549.         #end if debug
  550.         return 1
  551.     #end if format_object
  552.  
  553.     if debug:
  554.  
  555.         print("FORMAT NOT WANTED: " + video_formats_re.pattern + " " + report)
  556.     #end if debug
  557.  
  558.     raise FormatNotWanted
  559.  
  560. #end def isFormatWanted
  561.  
  562. def isMissing(series_title, season_number, episode_number):
  563.  
  564.     print("LOOKING: " + "Season " + str(season_number) + ", Episode " + str(episode_number))
  565.  
  566.     for dir in tv_dirs:
  567.  
  568.         series_path=dir + ds + showToFolder(series_title) + ds + "Season " + season_number
  569.  
  570.         print("CHECK: " + series_title + " for seasons to IGNORE")
  571.  
  572.         # ignore this season if told to do so (existence of file or directory called ignore Season x)
  573.         if os.path.exists(dir + ds + showToFolder(series_title) + ds + "ignore Season " + season_number):
  574.             if debug:
  575.                 print("IGNORE: Season " + season_number)
  576.             #end if debug
  577.             return 0
  578.         else:
  579.             if debug:
  580.                 print("PROCESS: Season " + season_number)
  581.             #end if debug
  582.         #end if os.path.exists
  583.  
  584.         if os.path.exists(series_path):
  585.             if debug:
  586.                 print("EXIST: " + series_path)
  587.             #end if debug
  588.             for tested_episode in os.listdir(series_path):
  589.                 if debug:
  590.                     print("CHECK: " + tested_episode)
  591.                 #end if debug
  592.                 for r in config['name_parse']:
  593.                     match = r.match(tested_episode)
  594.                     if match:
  595.                         seriesname, seasno, epno, epname = match.groups()
  596.                         if re.search(series_title, seriesname, re.IGNORECASE):
  597.                             if seasno == season_number:
  598.                                 if epno == episode_number:
  599.                                     if debug:
  600.                                         print("MATCH FOUND: " + "Season " + season_number + ", Episode " + episode_number)
  601.                                     #end if debug
  602.                                     return 0
  603.                                 #end if epno
  604.                             #end if seasno
  605.                         #end if seriesname
  606.                     #end if match
  607.                 #end for r
  608.             #end for tested_episode
  609.         else:
  610.             if debug:
  611.                 print("NOT EXIST: " + series_path)
  612.             #end if debug
  613.         #end if os.path.exists
  614.  
  615.         if debug:
  616.             print("MISSING: " + "Season " + season_number + ", Episode " + episode_number)
  617.         #end if debug
  618.     #end for dir
  619.     return 1
  620. #end def isMissing
  621.  
  622. def download(report_id):
  623.  
  624.     print "ADD QUEUE: " + time.strftime("%Y-%m-%d %H:%M:%S")+": "+ report_id
  625.  
  626.     # Check report_id, if it starts http, its not a NewzBin id
  627.     if report_id[:4] == 'http':
  628.         #'Other' NZB RSS
  629.         urllib.urlopen(my_SAB+"/sabnzbd/api?mode=addurl&name="+report_id+my_SAB_params)
  630.     else:
  631.         #NewzBin Style
  632.         urllib.urlopen(my_SAB+"/sabnzbd/api?mode=addid&name="+report_id+my_SAB_params)
  633.     #end if NewzBin
  634.  
  635. #end def download
  636.  
  637.  
  638. def cleanSeriesName(series_title):
  639.     global cache
  640.                  
  641.     theTVDB = Tvdb(debug = tvdb_debug, interactive = tvdb_interactive)
  642.  
  643.     good_series_title = removeIllegalChars(series_title)
  644.     good_series_title = good_series_title.replace("(", "\(").replace(")", "\)")
  645.     good_series_title = re.sub('\.|_', ' ', good_series_title)
  646.  
  647.     if debug:
  648.         print "NZB: ", good_series_title
  649.     #end if debug
  650.    
  651.     try:
  652.         good_series_title = showAlias(good_series_title)                            
  653.  
  654.         if cache.read(good_series_title.lower()):
  655.             good_series_title = cache.read(good_series_title.lower())
  656.         else:
  657.             good_series_title = cache.write(good_series_title.lower(),theTVDB[good_series_title]['seriesname'])
  658.  
  659.         if debug:
  660.             print "TVDB: ", good_series_title
  661.         #end if debug
  662.  
  663.     except tvdb_shownotfound:
  664.         # Didn't find the show @ theTVDB,
  665.         # most likely has 'and' and theTVDB has '&'
  666.         try:
  667.             if cache.read(re.sub(' [aA]nd ', ' & ', good_series_title.lower())):
  668.                 good_series_title = cache.read(re.sub(' [aA]nd ', ' & ', good_series_title.lower()))
  669.             else:
  670.                 good_series_title = cache.write(good_series_title.strtolower(),theTVDB[re.sub(' [aA]nd ', ' & ', good_series_title.strtolower())]['seriesname'])
  671.            
  672.             if debug:
  673.                 print "TVDB: ", good_series_title
  674.             #end if debug
  675.  
  676.         except tvdb_shownotfound:
  677.             # Well, didn't find it a second time, even using '&'
  678.             # return cleaned good_series_title
  679.             good_series_title = good_series_title
  680.             if debug:
  681.                 print "TVDB NOT FOUND: ", good_series_title
  682.             #end if debug
  683.  
  684.     #If Win32 then remove illegal chars
  685.     if sys.platform == "win32" or force_windows_compliant_filenames:
  686.         good_series_title = removeIllegalChars(good_series_title)
  687.     #end if sys.platform
  688.  
  689.     return good_series_title
  690.  
  691. #end def cleanSeriesName
  692.  
  693.  
  694. def formatReport( report ):
  695.     # format into ' - ' seperated parts
  696.     # showname - seasonepisode - title
  697.  
  698.     for r in config['name_parse']:
  699.         match = r.match( report )
  700.         if match:
  701.             seriesname, seasno, epno, epname = match.groups()
  702.  
  703.             # Remove any space dash space that might be left over
  704.             # We're going to put them in anyway but need to make sure we don't 'double' them
  705.             reportdict['seriesname'] = re.sub("\s\-\s|\s\-", "", seriesname)
  706.             reportdict['seasno'] = int(seasno)
  707.             reportdict['epno'] = int(epno)
  708.             reportdict['epname'] = re.sub("\s\-\s|\s\-", "", epname)
  709.  
  710.             # Format the report name
  711.             report = config['with_ep_name'] % (reportdict)
  712.  
  713.             return report
  714.         #end if match
  715.     #end for r
  716.     raise formatError
  717. #end def formatReport
  718.  
  719.  
  720. def showAlias(showname):
  721.     # Takes a showname and matches it to an alias
  722.     # e.g. CSI should map to CSI: Crime Scene Investigation and not CSI: NY
  723.     # as returned by theTVDB api
  724.  
  725.     if re.match('CSI.+?N?.+?Y', showname, re.IGNORECASE):
  726.         print("MATCHED CSI: NY")
  727.         return "CSI: NY"
  728.     #end if re.match
  729.  
  730.     if re.match("CSI Miami", showname, re.IGNORECASE):
  731.         print("MATCHED CSI Miami")
  732.         return "CSI: Miami"
  733.     #end if re.match
  734.  
  735.     if re.match("CSI", showname, re.IGNORECASE):
  736.         print("MATCHED CSI")
  737.         return "CSI: Crime Scene Investigation"
  738.     #end if re.match
  739.  
  740.     if re.match("DEMONS", showname, re.IGNORECASE):
  741.             print("MATCHED DEMONS")
  742.             return "Demons"
  743.     #end if re.match
  744.  
  745.     # Didn't match anything so return the passed showname
  746.     return showname
  747.  
  748. #def showAlias
  749.  
  750.  
  751. def showToFolder(showname):
  752.     # Takes a showname and returns the foldername associated
  753.     # e.g. CSI NY could return CSI New York
  754.  
  755.     if re.match('CSI.+?N?.+?Y', showname, re.IGNORECASE):
  756.         print("MATCHED CSI: NY")
  757.         return "CSI NY"
  758.     #end if re.match
  759.  
  760.     # Didn't match anything so return the passed showname
  761.     return showname
  762.  
  763. #def showToFolder
  764.  
  765.  
  766. def Main():
  767.     for feed in nzbfeeds:
  768.         print("PROCESS NZB FEED: " + feed)
  769.  
  770.         # Set feed type
  771.         # NewzBin feeds have different 'titles'
  772.         if re.search('newzbin', feed, re.IGNORECASE):
  773.             feed_type = 'NewzBin'
  774.             if debug:
  775.                 print("FEED: " + feed_type)
  776.             #end if debug
  777.         else:
  778.             feed_type = 'Other'
  779.             if debug:
  780.                 print("FEED: " + feed_type)
  781.             #end if debug
  782.         #end if re.search
  783.  
  784.         dom=xml.dom.minidom.parse(urllib.urlopen(feed))
  785.         for node in dom.getElementsByTagName("item"):
  786.             report=node.getElementsByTagName("title")[0].childNodes[0].data
  787.             report_original=report
  788.             print "PROCESSING:"+report
  789.             #try-catch block because some of this stuff fails hard when it gets a weird report, and pythons default behavior is to terminate
  790.             try:
  791.                 report=formatReport(report)
  792.  
  793.                 #Split report into 3 parts
  794.                 series,epstr,title=report.split(' - ')
  795.  
  796.                 if daily.match(epstr):
  797.                     year,month,date=epstr.split("-")
  798.                     season=year+"-"+month
  799.                     episode=date
  800.                 else:
  801.                     season=epstr[1:3]
  802.                     episode=epstr[4:]
  803.                 #end if daily.match
  804.  
  805.                 # Clean series name here (reduces number of times the same code is called)
  806.                 series=cleanSeriesName(series)
  807.  
  808.                 toDownload = False
  809.  
  810.                 if not useSmartQueue:
  811.                     if isWanted(series, report, season, feed_type) and isMissing(series, season, episode, feed_type) and (not isInQueue(report_original)):
  812.                         toDownload = True
  813.                     else:
  814.                         toDownload = False
  815.                     #end if isWanted(series)
  816.                 else:
  817.                     if isWanted(series):
  818.                         if isFormatWanted(series, report, season, feed_type):
  819.                             if isMissing(series, season, episode):
  820.                                 if not isInQueueSmart(series, season, episode):
  821.                                     toDownload = True
  822.                                 #end if not isInQueueSmart
  823.                             #end if isMissing
  824.                     #end if isWanted(seies)
  825.                 #end if not useSmartQueue
  826.  
  827.                 if toDownload:
  828.                     if feed_type == 'NewzBin':
  829.                         msgid=node.getElementsByTagName("report:id")[0].childNodes[0].data
  830.                     else:
  831.                         msgid=node.getElementsByTagName("link")[0].childNodes[0].data
  832.                     #end if NewzBin
  833.                     msgid=urllib.quote(msgid)
  834.                     download(msgid)
  835.                 #end if toDownload
  836.  
  837.             except:
  838.                 print("FAILED PROCESSING: " + report)
  839.                 pass
  840.  
  841.             #end try:
  842.         #end for node
  843.     #end for feed
  844. #end def Main
  845.  
  846. if __name__ == '__main__':
  847.     Main()
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!