def parse_results(self, raw_xml):
"""Parse the xml and return a list of dictionaries like:
[ {'IDSubtitle': 'foo',
'LinkUseNext': 'foo',
'MovieName': 'foo_movie',
...
},
{'IDSubtitle': 'foo',
'LinkUseNext': 'foo',
'MovieName': 'foo_movie',
...
},
...]
"""
dom = minidom.parseString(raw_xml) # Make the dom from raw xml
entries = dom.getElementsByTagName(
'opensubtitles') # Pull out all entry's
result_entries = [] # Make an empty container to fill up and return
data = None
# fetch the wanted result xml node
for entry in entries:
if len(entry.getElementsByTagName('results')) > 0:
for result in entry.getElementsByTagName('results'):
if len(result.getElementsByTagName('subtitle')) > 0:
data = result.getElementsByTagName('subtitle')
break
break
# print "data=", data
if not data:
return []
# catch all subtitles information
for entry in data:
try:
sub_obj = subtitlefile.SubtitleFile(online=True)
sub = {}
if entry.getElementsByTagName('EpisodeName'):
return
if entry.getElementsByTagName('IDSubtitle'):
sub['IDSubtitle'] = {'IDSubtitle': entry.getElementsByTagName('IDSubtitle')[0].firstChild.data,
'Link': entry.getElementsByTagName('IDSubtitle')[0].getAttribute('Link'),
'LinkImdb': entry.getElementsByTagName('IDSubtitle')[0].getAttribute('LinkImdb'),
'DownloadLink': entry.getElementsByTagName('IDSubtitle')[0].getAttribute('DownloadLink'),
'uuid': entry.getElementsByTagName('IDSubtitle')[0].getAttribute('uuid'),
}
sub_obj.setIdOnline(sub['IDSubtitle']['IDSubtitle'])
if entry.getElementsByTagName('IDSubtitleFile'):
sub['IDSubtitleFile'] = {'IDSubtitleFile': entry.getElementsByTagName('IDSubtitleFile')[0].firstChild.data,
}
sub_obj.setIdFileOnline(sub['IDSubtitleFile']['IDSubtitleFile'])
if entry.getElementsByTagName('UserID'):
sub['UserID'] = {'UserID': entry.getElementsByTagName('UserID')[0].firstChild.data,
'Link': entry.getElementsByTagName('UserID')[0].getAttribute('Link'),
}
if entry.getElementsByTagName('UserNickName') and entry.getElementsByTagName('UserNickName')[0].firstChild:
sub['UserNickName'] = entry.getElementsByTagName(
'UserNickName')[0].firstChild.data
sub_obj._uploader = sub['UserNickName']
if entry.getElementsByTagName('MovieID'):
#sub['MovieID'] = entry.getElementsByTagName('MovieID')[0].firstChild.data
sub['MovieID'] = {'MovieID': entry.getElementsByTagName('MovieID')[0].firstChild.data,
'Link': entry.getElementsByTagName('MovieID')[0].getAttribute('Link'),
'LinkImdb': entry.getElementsByTagName('MovieID')[0].getAttribute('LinkImdb'),
}
if entry.getElementsByTagName('MovieThumb') and entry.getElementsByTagName('MovieThumb')[0].firstChild:
sub['MovieThumb'] = entry.getElementsByTagName(
'MovieThumb')[0].firstChild.data
if entry.getElementsByTagName('LinkUseNext') and entry.getElementsByTagName('LinkUseNext')[0].firstChild:
sub['LinkUseNext'] = entry.getElementsByTagName(
'LinkUseNext')[0].firstChild.data
if entry.getElementsByTagName('LinkZoozle') and entry.getElementsByTagName('LinkZoozle')[0].firstChild:
sub['LinkZoozle'] = entry.getElementsByTagName(
'LinkZoozle')[0].firstChild.data
if entry.getElementsByTagName('LinkTorrentbar') and entry.getElementsByTagName('LinkTorrentbar')[0].firstChild:
sub['LinkTorrentbar'] = entry.getElementsByTagName(
'LinkTorrentbar')[0].firstChild.data
if entry.getElementsByTagName('LinkBoardreader') and entry.getElementsByTagName('LinkBoardreader')[0].firstChild:
sub['LinkBoardreader'] = entry.getElementsByTagName(
'LinkBoardreader')[0].firstChild.data
if entry.getElementsByTagName('MovieName') and entry.getElementsByTagName('MovieName')[0].firstChild:
sub['MovieName'] = entry.getElementsByTagName(
'MovieName')[0].firstChild.data
if entry.getElementsByTagName('MovieYear') and entry.getElementsByTagName('MovieYear')[0].firstChild:
sub['MovieYear'] = entry.getElementsByTagName(
'MovieYear')[0].firstChild.data
if entry.getElementsByTagName('MovieImdbRating') and entry.getElementsByTagName('MovieImdbRating')[0].firstChild:
sub['MovieImdbRating'] = entry.getElementsByTagName(
'MovieImdbRating')[0].firstChild.data
elif not entry.getElementsByTagName('MovieImdbRating')[0].firstChild:
sub['MovieImdbRating'] = 0
if entry.getElementsByTagName('MovieImdbID') and entry.getElementsByTagName('MovieImdbID')[0].firstChild:
sub['MovieImdbID'] = entry.getElementsByTagName(
'MovieImdbID')[0].firstChild.data
if entry.getElementsByTagName('SubAuthorComment'):
try:
sub['SubAuthorComment'] = entry.getElementsByTagName(
'SubAuthorComment')[0].firstChild.data
except AttributeError:
sub['SubAuthorComment'] = entry.getElementsByTagName(
'SubAuthorComment')[0].firstChild
if entry.getElementsByTagName('ISO639'):
sub['ISO639'] = {'ISO639': entry.getElementsByTagName('ISO639')[0].firstChild.data,
'LinkSearch': entry.getElementsByTagName('ISO639')[0].getAttribute('LinkSearch'),
'flag': entry.getElementsByTagName('ISO639')[0].getAttribute('flag'),
}
sub_obj.setLanguage(Language.from_xx(sub['ISO639']['ISO639']))
#sub_obj._onlineId = sub['IDSubtitle']['IDSubtitle']
# It does require the Subtitle ID to downlad, not the
# Subtitle File Id
sub_obj.setExtraInfo(
'downloadLink', "http://www.opensubtitles.org/download/sub/%s" % sub_obj.getIdOnline())
if entry.getElementsByTagName('LanguageName') and entry.getElementsByTagName('LanguageName')[0].firstChild:
sub['LanguageName'] = entry.getElementsByTagName(
'LanguageName')[0].firstChild.data
if entry.getElementsByTagName('SubFormat') and entry.getElementsByTagName('SubFormat')[0].firstChild:
sub['SubFormat'] = entry.getElementsByTagName(
'SubFormat')[0].firstChild.data
sub_obj.setExtraInfo('format', sub['SubFormat'])
if entry.getElementsByTagName('SubSumCD') and entry.getElementsByTagName('SubSumCD')[0].firstChild:
sub['SubSumCD'] = entry.getElementsByTagName(
'SubSumCD')[0].firstChild.data
sub_obj.setExtraInfo('totalCDs', sub['SubSumCD'])
if entry.getElementsByTagName('SubAddDate') and entry.getElementsByTagName('SubAddDate')[0].firstChild:
sub['SubAddDate'] = entry.getElementsByTagName(
'SubAddDate')[0].firstChild.data
if entry.getElementsByTagName('SubBad') and entry.getElementsByTagName('SubBad')[0].firstChild:
sub['SubBad'] = entry.getElementsByTagName(
'SubBad')[0].firstChild.data
if entry.getElementsByTagName('SubRating') and entry.getElementsByTagName('SubRating')[0].firstChild:
sub['SubRating'] = entry.getElementsByTagName(
'SubRating')[0].firstChild.data
sub_obj.setRating(sub['SubRating'])
if entry.getElementsByTagName('SubDownloadsCnt') and entry.getElementsByTagName('SubDownloadsCnt')[0].firstChild:
sub['SubDownloadsCnt'] = entry.getElementsByTagName(
'SubDownloadsCnt')[0].firstChild.data
sub_obj.setExtraInfo(
'totalDownloads', sub['SubDownloadsCnt'])
if entry.getElementsByTagName('SubMovieAka') and entry.getElementsByTagName('SubMovieAka')[0].firstChild:
sub['SubMovieAka'] = entry.getElementsByTagName(
'SubMovieAka')[0].firstChild.data
if entry.getElementsByTagName('SubDate') and entry.getElementsByTagName('SubDate')[0].firstChild:
sub['SubDate'] = entry.getElementsByTagName(
'SubDate')[0].firstChild.data
if entry.getElementsByTagName('SubComments') and entry.getElementsByTagName('SubComments')[0].firstChild:
sub['SubComments'] = entry.getElementsByTagName(
'SubComments')[0].firstChild.data
if entry.getElementsByTagName('TotalSubs') and entry.getElementsByTagName('TotalSubs')[0].firstChild:
sub['TotalSubs'] = entry.getElementsByTagName(
'TotalSubs')[0].firstChild.data
if entry.getElementsByTagName('Newest') and entry.getElementsByTagName('Newest')[0].firstChild:
sub['Newest'] = entry.getElementsByTagName(
'Newest')[0].firstChild.data
if sub:
# result_entries.append(sub)
temp_movie = Movie(sub)
movie_exists = False
for movie in result_entries:
if movie.MovieId == temp_movie.MovieId:
movie_exists = True
if hasattr(sub_obj, "_extraInfo") and sub_obj._extraInfo:
movie.subtitles.append(sub_obj)
# already_movie = result_entries.pop(result_entries.index(movie))
# temp_movie.subtitles = already_movie.subtitles
if not movie_exists:
if hasattr(sub_obj, "_extraInfo") and sub_obj._extraInfo:
temp_movie.subtitles.append(sub_obj)
result_entries.append(temp_movie)
except IndexError as e:
pass
return result_entries
def _xml_to_subtitles(self, xml):
subtitle_entries, nb_so_far, nb_provider = self._extract_subtitle_entries(
xml)
if subtitle_entries is None:
return None, None, None
subtitles = []
for subtitle_entry in subtitle_entries:
try:
ads_entries = subtitle_entry.getElementsByTagName(
'ads1') or subtitle_entry.getElementsByTagName('ads2')
if ads_entries:
continue
def try_get_first_child_data(key, default):
try:
return subtitle_entry.getElementsByTagName(
key)[0].firstChild.data
except (AttributeError, IndexError):
return default
subtitle_id_entry = subtitle_entry.getElementsByTagName(
'IDSubtitle')[0]
subtitle_id = subtitle_id_entry.firstChild.data
subtitle_link = 'http://www.opensubtitles.org' + subtitle_id_entry.getAttribute(
'Link')
subtitle_uuid = subtitle_id_entry.getAttribute('uuid')
subtitlefile_id = subtitle_entry.getElementsByTagName(
'IDSubtitleFile')[0].firstChild.data
user_entry = subtitle_entry.getElementsByTagName('UserID')[0]
user_id = int(user_entry.firstChild.data)
# user_link = 'http://www.opensubtitles.org' + user_entry.getAttribute('Link')
user_nickname = try_get_first_child_data('UserNickName', None)
# comment = try_get_first_child_data(''SubAuthorComment', None)
language_entry = subtitle_entry.getElementsByTagName(
'ISO639')[0]
language_iso639 = language_entry.firstChild.data
# language_link_search = 'http://www.opensubtitles.org' + language_entry.getAttribute('LinkSearch')
# language_flag = 'http:' + language_entry.getAttribute('flag')
# language_name = try_get_first_child_data('LanguageName', None)
subtitle_format = try_get_first_child_data('SubFormat', 'srt')
# subtitle_nbcds = int(try_get_first_child_data('SubSumCD', -1))
subtitle_add_date_locale = subtitle_entry.getElementsByTagName(
'SubAddDate')[0].getAttribute('locale')
subtitle_add_date = datetime.datetime.strptime(
subtitle_add_date_locale, '%d/%m/%Y %H:%M:%S')
# subtitle_bad = int(subtitle_entry.getElementsByTagName('SubBad')[0].firstChild.data)
subtitle_rating = float(
subtitle_entry.getElementsByTagName('SubRating')
[0].firstChild.data)
# download_count = int(try_get_first_child_data('SubDownloadsCnt', -1))
# subtitle_movie_aka = try_get_first_child_data('SubMovieAka', None)
# subtitle_comments = int(try_get_first_child_data('SubComments', -1))
# subtitle_total = int(try_get_first_child_data('TotalSubs', -1)) #PRESENT?
# subtitle_newest = try_get_first_child_data('Newest', None) #PRESENT?
language = Language.from_xx(language_iso639)
movie_release_name = subtitle_entry.getElementsByTagName(
'MovieReleaseName')[0].firstChild.data
filename = '{}.{}'.format(movie_release_name, subtitle_format)
download_link = 'http://www.opensubtitles.org/download/sub/{}'.format(
subtitle_id)
if user_nickname:
uploader = user_nickname
elif user_id != 0:
uploader = str(user_id)
else:
uploader = None
subtitle = OpenSubtitlesSubtitleFile(
filename=filename,
file_size=None,
md5_hash=subtitle_uuid,
id_online=subtitlefile_id,
download_link=download_link,
link=subtitle_link,
uploader=uploader,
language=language,
rating=subtitle_rating,
age=subtitle_add_date)
subtitles.append(subtitle)
except (AttributeError, IndexError, ValueError):
log.warning('subtitle_entry={}'.format(subtitle_entry.toxml()))
log.warning('XML entry has invalid format.',
exc_info=sys.exc_info())
return subtitles, nb_so_far, nb_provider
def subtitle_info(self, raw_xml):
dom = minidom.parseString(raw_xml) # Make the dom from raw xml
entries = dom.getElementsByTagName(
'opensubtitles') # Pull out all entry's
subtitle_entries = [] # Make an empty container to fill up and return
data = None
for entry in entries:
if entry.getElementsByTagName('SubBrowse'):
for result in entry.getElementsByTagName('SubBrowse'):
if result.getElementsByTagName('Subtitle'):
data = result.getElementsByTagName('Subtitle')
break
break
# print "data=", data
if not data:
return []
# catch subtitle information
for entry in data:
sub_obj = subtitlefile.SubtitleFile(online=True)
sub = {}
if entry.getElementsByTagName('LinkDetails') and entry.getElementsByTagName('LinkDetails')[0].firstChild:
sub['LinkDetails'] = entry.getElementsByTagName(
'LinkDetails')[0].firstChild.data
if entry.getElementsByTagName('IDSubtitle'):
sub['IDSubtitle'] = {'IDSubtitle': entry.getElementsByTagName('IDSubtitle')[0].firstChild.data,
'Link': entry.getElementsByTagName('IDSubtitle')[0].getAttribute('Link'),
}
sub_obj._onlineId = sub['IDSubtitle']['IDSubtitle']
if entry.getElementsByTagName('MovieReleaseName') and entry.getElementsByTagName('MovieReleaseName')[0].firstChild:
sub['MovieReleaseName'] = entry.getElementsByTagName(
'MovieReleaseName')[0].firstChild.data
if entry.getElementsByTagName('SubFormat') and entry.getElementsByTagName('SubFormat')[0].firstChild:
sub['SubFormat'] = entry.getElementsByTagName(
'SubFormat')[0].firstChild.data
sub_obj.setExtraInfo('format', sub['SubFormat'])
if entry.getElementsByTagName('SubSumCD') and entry.getElementsByTagName('SubSumCD')[0].firstChild:
sub['SubSumCD'] = entry.getElementsByTagName(
'SubSumCD')[0].firstChild.data
sub_obj.setExtraInfo('totalCDs', sub['SubSumCD'])
if entry.getElementsByTagName('SubAuthorComment') and entry.getElementsByTagName('SubAuthorComment')[0].firstChild:
sub['SubAuthorComment'] = entry.getElementsByTagName(
'SubAuthorComment')[0].firstChild.data
if entry.getElementsByTagName('SubAddDate') and entry.getElementsByTagName('SubAddDate')[0].firstChild:
sub['SubAddDate'] = entry.getElementsByTagName(
'SubAddDate')[0].firstChild.data
if entry.getElementsByTagName('SubSumVotes') and entry.getElementsByTagName('SubSumVotes')[0].firstChild:
sub['SubSumVotes'] = entry.getElementsByTagName(
'SubSumVotes')[0].firstChild.data
if entry.getElementsByTagName('SubRating') and entry.getElementsByTagName('SubRating')[0].firstChild:
sub['SubRating'] = entry.getElementsByTagName(
'SubRating')[0].firstChild.data
sub_obj.setRating(sub['SubRating'])
if entry.getElementsByTagName('SubDownloadsCnt') and entry.getElementsByTagName('SubDownloadsCnt')[0].firstChild:
sub['SubDownloadsCnt'] = entry.getElementsByTagName(
'SubDownloadsCnt')[0].firstChild.data
sub_obj.setExtraInfo('totalDownloads', sub['SubDownloadsCnt'])
if entry.getElementsByTagName('UserNickName') and entry.getElementsByTagName('UserNickName')[0].firstChild:
sub['UserNickName'] = entry.getElementsByTagName(
'UserNickName')[0].firstChild.data
sub_obj._uploader = sub['UserNickName']
if entry.getElementsByTagName('LanguageName') and entry.getElementsByTagName('LanguageName')[0].firstChild:
sub['LanguageName'] = entry.getElementsByTagName(
'LanguageName')[0].firstChild.data
sub_obj.setLanguage(Language.from_xx(
entry.getElementsByTagName('LanguageName')[0].getAttribute('ISO639')))
if entry.getElementsByTagName('SubtitleFile'):
SubtitleFile = {}
_SubtitleFile = entry.getElementsByTagName('SubtitleFile')[0]
_File = _SubtitleFile.getElementsByTagName('File')[0]
SubtitleFile['File'] = {'ID': _SubtitleFile.getElementsByTagName('File')[0].getAttribute('ID'),
'SubActualCD': {'SubActualCD': _File.getElementsByTagName('SubActualCD')[0].firstChild.data,
'SubSize': _File.getElementsByTagName('SubActualCD')[0].getAttribute('Link'),
'MD5': _File.getElementsByTagName('SubActualCD')[0].getAttribute('MD5'),
'SubFileName': _File.getElementsByTagName('SubActualCD')[0].getAttribute('SubFileName'),
'DownloadLink': _File.getElementsByTagName('SubActualCD')[0].getAttribute('DownloadLink'),
}
}
SubtitleFile['Download'] = {'Download': _SubtitleFile.getElementsByTagName('Download')[0].firstChild.data,
'DownloadLink': _SubtitleFile.getElementsByTagName('Download')[0].getAttribute('LinkDownloadBundle'),
}
sub['SubtitleFile'] = SubtitleFile
global OnlyLink
OnlyLink = _SubtitleFile.getElementsByTagName(
'Download')[0].getAttribute('LinkDownloadBundle')
OnlyLink = ((OnlyLink.replace('dl', 'www')).replace(
'org/en', 'com')).replace('subb', 'sub')
if entry.getElementsByTagName('Movie'):
_Movie = entry.getElementsByTagName('Movie')[0]
#sub['MovieName'] = _Movie.getElementsByTagName('MovieName')[0].firstChild.data
sub['MovieID'] = {'MovieID': _Movie.getElementsByTagName('MovieName')[0].getAttribute('MovieID'),
'Link': _Movie.getElementsByTagName('MovieName')[0].getAttribute('Link'),
}
for section in _Movie.getElementsByTagName('section'):
if section.getAttribute('type') == u"about":
for info in section.getElementsByTagName("info"):
if info.getElementsByTagName("web_url")[0].firstChild.data == u"http://www.imdb.com":
sub['MovieID']['LinkImdb'] = info.getElementsByTagName(
"link_detail")[0].firstChild.data
if entry.getElementsByTagName('FullName') and entry.getElementsByTagName('FullName')[0].firstChild:
sub['FullName'] = entry.getElementsByTagName(
'FullName')[0].firstChild.data
if entry.getElementsByTagName('ReportLink') and entry.getElementsByTagName('ReportLink')[0].firstChild:
sub['ReportLink'] = entry.getElementsByTagName(
'ReportLink')[0].firstChild.data
# just a shortcut
sub['DownloadLink'] = sub['SubtitleFile']['File']['SubActualCD']['DownloadLink']
Link().OneLink(OnlyLink)
if sub:
subtitle_entries.append(sub)
return (subtitle_entries, sub_obj)
def translators_get():
from subdownloader.languages.language import Language
return (Translator('Sylvestre Ledru', '*****@*****.**',
(Language.from_xx('fr'), )), )
