def get_searches(self):
elements1 = re.split('href="/kinofilm/', self.page)
elements1[0] = None
for element in elements1:
if element <> None:
title = gutils.clean(gutils.trim(element,'>','</a>')) + string.replace(' (' +
gutils.clean(gutils.trim(element, '<p>', "<br />")) + ')', '()', '')
if title != ' ':
self.ids.append("K_" + re.sub('[?].*', '', gutils.before(element,'"')))
self.titles.append('Kino: ' + title)
elements2 = re.split('href="http://www.video.de/videofilm/', self.page)
elements2[0] = None
for element in elements2:
if element <> None:
title = gutils.clean(gutils.trim(element,'>','</a>')) + string.replace(' (' +
gutils.clean(gutils.trim(gutils.before(element, '</li>'), '<p>', "<br />")) + ')', '()', '')
if title != ' ':
id = re.sub('[?].*', '', gutils.before(element,'"'))
self.ids.append("V_" + id)
type = ''
if 'blu-ray-disc-kauf' in id:
type = ' (Bluray-Kauf)'
if 'blu-ray-disc-leih' in id:
type = ' (Bluray-Verleih)'
if 'dvd-leih' in id:
type = ' (DVD-Verleih)'
if 'dvd-kauf' in id:
type = ' (DVD-Kauf)'
self.titles.append('Video: ' + title + type)
def get_searches(self):
elements1 = re.split('href="/kinofilm/', self.page)
elements1[0] = None
for element in elements1:
if element <> None:
title = gutils.clean(gutils.trim(element,'>','</a>')) + string.replace(' (' +
gutils.clean(gutils.trim(element, '<p>', "<br />")) + ')', '()', '')
if title != ' ':
self.ids.append("K_" + re.sub('[?].*', '', gutils.before(element,'"')))
self.titles.append('Kino: ' + title)
elements2 = re.split('href="http://www.video.de/videofilm/', self.page)
elements2[0] = None
for element in elements2:
if element <> None:
title = gutils.clean(gutils.trim(element,'>','</a>')) + string.replace(' (' +
gutils.clean(gutils.trim(element, '<p>', "<br />")) + ')', '()', '')
if title != ' ':
id = re.sub('[?].*', '', gutils.before(element,'"'))
self.ids.append("V_" + id)
type = ''
if 'blu-ray-disc-kauf' in id:
type = ' (Bluray-Kauf)'
if 'blu-ray-disc-leih' in id:
type = ' (Bluray-Verleih)'
if 'dvd-leih' in id:
type = ' (DVD-Verleih)'
if 'dvd-kauf' in id:
type = ' (DVD-Kauf)'
self.titles.append('Video: ' + title + type)
def get_cast(self):
self.cast = ""
casts = gutils.trim(self.page_cast, 'Acteurs', '</table>')
parts = string.split(casts, '<td ')
for index in range(1, len(parts) - 1, 2):
character = gutils.after(parts[index], '>')
actor = gutils.after(parts[index + 1], '>')
self.cast = self.cast + gutils.clean(actor) + _(' as ') + gutils.clean(character) + '\n'
def get_cast(self):
self.cast = ""
casts = gutils.trim(self.page_cast, "Acteurs", "</table>")
parts = string.split(casts, "<td ")
for index in range(1, len(parts) - 1, 3):
character = gutils.after(parts[index + 1], ">")
actor = gutils.after(parts[index + 2], ">")
self.cast = self.cast + gutils.clean(actor) + _(" as ") + gutils.clean(character) + "\n"
def parse_movie(self):
try:
fields = list(self.fields_to_fetch) # make a copy
self.initialize()
if 'year' in fields:
self.get_year()
self.year = gutils.digits_only(self.year, 2100)
fields.pop(fields.index('year'))
if 'runtime' in fields:
self.get_runtime()
self.runtime = gutils.digits_only(self.runtime)
fields.pop(fields.index('runtime'))
if 'rating' in fields:
self.get_rating()
self.rating = gutils.digits_only(self.rating, 10)
fields.pop(fields.index('rating'))
if 'cast' in fields:
self.get_cast()
self.cast = gutils.clean(self.cast)
if not isinstance(self.cast, unicode):
self.cast = gutils.gdecode(self.cast, self.encode)
fields.pop(fields.index('cast'))
if 'plot' in fields:
self.get_plot()
self.plot = gutils.clean(self.plot)
if not isinstance(self.plot, unicode):
self.plot = gutils.gdecode(self.plot, self.encode)
fields.pop(fields.index('plot'))
if 'notes' in fields:
self.get_notes()
self.notes = gutils.clean(self.notes)
if not isinstance(self.notes, unicode):
self.notes = gutils.gdecode(self.notes, self.encode)
fields.pop(fields.index('notes'))
if 'image' in fields:
self.get_image()
self.fetch_picture()
fields.pop(fields.index('image'))
for i in fields:
getattr(self, "get_%s" % i)()
self[i] = gutils.clean(self[i])
if not isinstance(self[i], unicode):
self[i] = gutils.gdecode(self[i], self.encode)
if 'o_title' in self.fields_to_fetch and self.o_title is not None:
if self.o_title[:4] == u'The ':
self.o_title = self.o_title[4:] + u', The'
if 'title' in self.fields_to_fetch and self.title is not None:
if self.title[:4] == u'The ':
self.title = self.title[4:] + u', The'
except:
log.exception('')
finally:
# close the progress dialog which was opened in get_movie
self.progress.hide()
def parse_movie(self):
try:
fields = list(self.fields_to_fetch) # make a copy
self.initialize()
if 'year' in fields:
self.get_year()
self.year = gutils.digits_only(self.year, 2100)
fields.pop(fields.index('year'))
if 'runtime' in fields:
self.get_runtime()
self.runtime = gutils.digits_only(self.runtime)
fields.pop(fields.index('runtime'))
if 'rating' in fields:
self.get_rating()
self.rating = gutils.digits_only(self.rating, 10)
fields.pop(fields.index('rating'))
if 'cast' in fields:
self.get_cast()
self.cast = gutils.clean(self.cast)
if not isinstance(self.cast, unicode):
self.cast = gutils.gdecode(self.cast, self.encode)
fields.pop(fields.index('cast'))
if 'plot' in fields:
self.get_plot()
self.plot = gutils.clean(self.plot)
if not isinstance(self.plot, unicode):
self.plot = gutils.gdecode(self.plot, self.encode)
fields.pop(fields.index('plot'))
if 'notes' in fields:
self.get_notes()
self.notes = gutils.clean(self.notes)
if not isinstance(self.notes, unicode):
self.notes = gutils.gdecode(self.notes, self.encode)
fields.pop(fields.index('notes'))
if 'image' in fields:
self.get_image()
self.fetch_picture()
fields.pop(fields.index('image'))
for i in fields:
getattr(self, "get_%s" % i)()
self[i] = gutils.clean(self[i])
if not isinstance(self[i], unicode):
self[i] = gutils.gdecode(self[i], self.encode)
if 'o_title' in self.fields_to_fetch and self.o_title is not None:
if self.o_title[:4] == u'The ':
self.o_title = self.o_title[4:] + u', The'
if 'title' in self.fields_to_fetch and self.title is not None:
if self.title[:4] == u'The ':
self.title = self.title[4:] + u', The'
except:
log.exception('')
finally:
# close the progress dialog which was opened in get_movie
self.progress.hide()
def parse_movie(self):
try:
fields = list(self.fields_to_fetch) # make a copy
self.initialize()
if "year" in fields:
self.get_year()
self.year = gutils.digits_only(self.year, 2100)
fields.pop(fields.index("year"))
if "runtime" in fields:
self.get_runtime()
self.runtime = gutils.digits_only(self.runtime)
fields.pop(fields.index("runtime"))
if "rating" in fields:
self.get_rating()
self.rating = gutils.digits_only(self.rating, 10)
fields.pop(fields.index("rating"))
if "cast" in fields:
self.get_cast()
self.cast = gutils.clean(self.cast)
if not isinstance(self.cast, unicode):
self.cast = gutils.gdecode(self.cast, self.encode)
fields.pop(fields.index("cast"))
if "plot" in fields:
self.get_plot()
self.plot = gutils.clean(self.plot)
if not isinstance(self.plot, unicode):
self.plot = gutils.gdecode(self.plot, self.encode)
fields.pop(fields.index("plot"))
if "notes" in fields:
self.get_notes()
self.notes = gutils.clean(self.notes)
if not isinstance(self.notes, unicode):
self.notes = gutils.gdecode(self.notes, self.encode)
fields.pop(fields.index("notes"))
if "image" in fields:
self.get_image()
self.fetch_picture()
fields.pop(fields.index("image"))
for i in fields:
getattr(self, "get_%s" % i)()
self[i] = gutils.clean(self[i])
if not isinstance(self[i], unicode):
self[i] = gutils.gdecode(self[i], self.encode)
if "o_title" in self.fields_to_fetch and self.o_title is not None:
if self.o_title[:4] == u"The ":
self.o_title = self.o_title[4:] + u", The"
if "title" in self.fields_to_fetch and self.title is not None:
if self.title[:4] == u"The ":
self.title = self.title[4:] + u", The"
finally:
# close the progress dialog which was opened in get_movie
self.progress.hide()
def get_notes(self):
self.notes = ''
critica = gutils.clean(string.replace(gutils.regextrim(self.page, 'Critica</font>', "(</td>|\n|Note<)"), '<br>', '\n'))
if critica:
self.notes = 'Critica:\n\n' + critica + '\n\n'
note = gutils.clean(string.replace(gutils.regextrim(self.page, 'Note</font>', "(</td>|\n|Critica<)"), '<br>', '--BR--'))
if note:
# string.capwords removes line breaks, preventing them with placeholder --BR--
note = self.capwords(note)
self.notes = self.notes + 'Note:\n\n' + string.replace(note, '--br--', '\n')
def get_searches(self):
elements = re.split('<tr>', self.page)
for index in range(1, len(elements), 1):
element = elements[index]
titleandid = gutils.trim(element, '<td class="title">', '</td>')
title = gutils.clean(titleandid)
id = gutils.trim(titleandid, 'href="', '"')
idstart = string.rfind(id, '/')
id = id[idstart + 1:]
year = gutils.trim(element, '<td class="year">', '</td>')
self.ids.append(id)
self.titles.append(title + ' (' + gutils.clean(year)+ ')')
def get_cast(self):
self.cast = ''
tmp = gutils.trim(self.page, '>Cast<', '</TABLE>')
elements = re.split('(href|HREF)="/db/people', tmp)
for element in elements:
actor = gutils.clean(gutils.trim(element, '>', '<'))
if actor:
role = gutils.clean(gutils.trim(element, '>...', '</TR>'))
if role:
self.cast = self.cast + actor + _(' as ') + role + '\n'
else:
self.cast = self.cast + actor + '\n'
def get_cast(self):
self.cast = ''
tmp = gutils.trim(self.page, '>Cast<', '</TABLE>')
elements = re.split('(href|HREF)="/db/people', tmp)
for element in elements:
actor = gutils.clean(gutils.trim(element, '>', '<'))
if actor:
role = gutils.clean(gutils.trim(element, '>...', '</TR>'))
if role:
self.cast = self.cast + actor + _(' as ') + role + '\n'
else:
self.cast = self.cast + actor + '\n'
def get_notes(self): self.notes = '' # ...type atype = gutils.trim(self.page, '"field">Type', '</td>') atype = gutils.clean(atype) if atype != '': self.notes += "Type: %s\n" % atype # ...number of episodes episodes = gutils.trim(self.page, '"field">Episodes', '</td>') episodes = gutils.clean(episodes) if episodes != '': self.notes += "Episodes: %s\n" % episodes
def get_searches(self):
elements = string.split(self.page, '<a href=\'/film/fichefilm_gen_cfilm=')
if (elements[0] <> ''):
for index in range(1, len(elements), 1):
element = elements[index]
title = gutils.clean(gutils.convert_entities(gutils.trim(element, '>', '</a>')))
year = gutils.clean(gutils.trim(element, '<span class="fs11">', '<br'))
if title:
self.ids.append(gutils.before(element, '.'))
if year:
self.titles.append(title + ' (' + year + ')')
else:
self.titles.append(title)
def parse_movie(self):
from copy import deepcopy
fields = deepcopy(self.fields_to_fetch)
self.initialize()
if "year" in fields:
self.get_year()
self.year = gutils.digits_only(self.year, 2100)
fields.pop(fields.index("year"))
if "runtime" in fields:
self.get_runtime()
self.runtime = gutils.digits_only(self.runtime)
fields.pop(fields.index("runtime"))
if "rating" in fields:
self.get_rating()
self.rating = gutils.digits_only(self.rating, 10)
fields.pop(fields.index("rating"))
if "cast" in fields:
self.get_cast()
self.cast = gutils.clean(self.cast)
self.cast = gutils.gdecode(self.cast, self.encode)
fields.pop(fields.index("cast"))
if "plot" in fields:
self.get_plot()
self.plot = gutils.clean(self.plot)
self.plot = gutils.gdecode(self.plot, self.encode)
fields.pop(fields.index("plot"))
if "notes" in fields:
self.get_notes()
self.notes = gutils.clean(self.notes)
self.notes = gutils.gdecode(self.notes, self.encode)
fields.pop(fields.index("notes"))
if "image" in fields:
self.get_image()
self.fetch_picture()
fields.pop(fields.index("image"))
for i in fields:
getattr(self, "get_%s" % i)()
self[i] = gutils.clean(self[i])
self[i] = gutils.gdecode(self[i], self.encode)
if "o_title" in self.fields_to_fetch and self.o_title is not None:
if self.o_title[:4] == "The ":
self.o_title = self.o_title[4:] + ", The"
if "title" in self.fields_to_fetch and self.title is not None:
if self.title[:4] == "The ":
self.title = self.title[4:] + ", The"
def get_cast(self):
self.cast = ""
casts = gutils.trim(self.page_cast, 'Acteurs, rôles, personnages', '<h2>')
parts = string.split(casts, 'href="/personne/fichepersonne_gen_cpersonne=')
for index in range(1, len(parts), 1):
character = gutils.clean(gutils.trim(parts[index], 'Rôle :', '<'))
if not character:
character = gutils.clean(gutils.trim(parts[index - 1], '<td>', '</td>'))
actor = gutils.clean(gutils.trim(parts[index], '>', '<'))
if actor:
if character:
self.cast = self.cast + actor + _(' as ') + character + '\n'
else:
self.cast = self.cast + actor + '\n'
def parse_movie(self):
from copy import deepcopy
fields = deepcopy(self.fields_to_fetch)
self.initialize()
if 'year' in fields:
self.get_year()
self.year = gutils.digits_only(self.year, 2100)
fields.pop(fields.index('year'))
if 'runtime' in fields:
self.get_runtime()
self.runtime = gutils.digits_only(self.runtime)
fields.pop(fields.index('runtime'))
if 'rating' in fields:
self.get_rating()
self.rating = gutils.digits_only(self.rating, 10)
fields.pop(fields.index('rating'))
if 'cast' in fields:
self.get_cast()
self.cast = gutils.clean(self.cast)
self.cast = gutils.gdecode(self.cast, self.encode)
fields.pop(fields.index('cast'))
if 'plot' in fields:
self.get_plot()
self.plot = gutils.clean(self.plot)
self.plot = gutils.gdecode(self.plot, self.encode)
fields.pop(fields.index('plot'))
if 'notes' in fields:
self.get_notes()
self.notes = gutils.clean(self.notes)
self.notes = gutils.gdecode(self.notes, self.encode)
fields.pop(fields.index('notes'))
if 'image' in fields:
self.get_image()
self.fetch_picture()
fields.pop(fields.index('image'))
for i in fields:
getattr(self, "get_%s" % i)()
self[i] = gutils.clean(self[i])
self[i] = gutils.gdecode(self[i], self.encode)
if 'o_title' in self.fields_to_fetch and self.o_title is not None:
if self.o_title[:4] == 'The ':
self.o_title = self.o_title[4:] + ', The'
if 'title' in self.fields_to_fetch and self.title is not None:
if self.title[:4] == 'The ':
self.title = self.title[4:] + ', The'
def search(self, parent_window):
self.open_search(parent_window)
tmp_pagemovie = self.page
#
# try to get all result pages (not so nice, but it works)
#
tmp_pagecount = gutils.clean(gutils.trim(tmp_pagemovie, ">von", "</a>"))
try:
tmp_pagecountint = int(tmp_pagecount)
except:
tmp_pagecountint = 1
tmp_pagecountintcurrent = 1
while tmp_pagecountint > tmp_pagecountintcurrent and tmp_pagecountintcurrent < 5:
tmp_pagecountintcurrent = tmp_pagecountintcurrent + 1
self.url = (
"http://www.kino.de/search.php?mode=megaSearch&searchCategory=film&page="
+ str(tmp_pagecountintcurrent)
+ "&inputSearch="
)
self.open_search(parent_window)
tmp_pagemovie = tmp_pagemovie + self.page
#
# Look for DVD and VHS
#
self.url = "http://www.kino.de/search.php?mode=megaSearch&searchCategory=video&inputSearch="
self.open_search(parent_window)
tmp_pagevideo = tmp_pagemovie + self.page
#
# try to get all result pages (not so nice, but it works)
#
tmp_pagecount = gutils.clean(gutils.trim(self.page, ">von", "</a>"))
try:
tmp_pagecountint = int(tmp_pagecount)
except:
tmp_pagecountint = 1
tmp_pagecountintcurrent = 1
while tmp_pagecountint > tmp_pagecountintcurrent and tmp_pagecountintcurrent < 5:
tmp_pagecountintcurrent = tmp_pagecountintcurrent + 1
self.url = (
"http://www.kino.de/search.php?mode=megaSearch&searchCategory=video&page="
+ str(tmp_pagecountintcurrent)
+ "&inputSearch="
)
self.open_search(parent_window)
tmp_pagevideo = tmp_pagevideo + self.page
self.page = tmp_pagevideo
return self.page
def get_rating(self): self.rating = gutils.trim(self.page, '<h5>Nutzer-Bewertung:</h5>', '/10') if self.rating: try: self.rating = str(float(gutils.clean(self.rating))) except: self.rating = ''
def get_cast(self):
self.cast = gutils.regextrim(self.page, '[(]Darsteller[)]',
'(</td>|<br><span[^>]+>)')
self.cast = gutils.clean(self.cast)
self.cast = self.cast.replace(' als ', _(' as '))
self.cast = re.sub('( \t|\t|\r|\n)', '', self.cast)
self.cast = self.cast.replace(',', '\n')
def get_notes(self):
self.notes = ''
language = gutils.regextrim(self.page, 'Language:<[^>]+>', '</div>')
language = gutils.strip_tags(language)
language = re.sub('[\n]+', '', language)
language = re.sub('[ ]+', ' ', language)
language = language.strip()
color = gutils.regextrim(self.page, 'Color:<[^>]+>', '</div>')
color = gutils.strip_tags(color)
color = re.sub('[\n]+', '', color)
color = re.sub('[ ]+', ' ', color)
color = color.strip()
sound = gutils.regextrim(self.page, 'Sound Mix:<[^>]+>', '</div>')
sound = gutils.strip_tags(sound)
sound = re.sub('[\n]+', '', sound)
sound = re.sub('[ ]+', ' ', sound)
sound = sound.strip()
tagline = gutils.regextrim(self.tagl_page, '>Taglines', '>See also')
taglines = re.split('<div[^>]+class="soda[^>]*>', tagline)
tagline = ''
if len(taglines)>1:
for entry in taglines[1:]:
entry = gutils.clean(gutils.before(entry, '</div>'))
if entry:
tagline = tagline + entry + '\n'
if len(language)>0:
self.notes = "%s: %s\n" %(_('Language'), language)
if len(sound)>0:
self.notes += "%s: %s\n" %(gutils.strip_tags(_('<b>Audio</b>')), sound)
if len(color)>0:
self.notes += "%s: %s\n" %(_('Color'), color)
if len(tagline)>0:
self.notes += "%s: %s\n" %('Tagline', tagline)
def get_notes(self):
self.notes = ''
language = gutils.regextrim(self.page, 'Language:<[^>]+>', '</div>')
language = gutils.strip_tags(language)
language = re.sub('[\n]+', '', language)
language = re.sub('[ ]+', ' ', language)
language = language.strip()
color = gutils.regextrim(self.page, 'Color:<[^>]+>', '</div>')
color = gutils.strip_tags(color)
color = re.sub('[\n]+', '', color)
color = re.sub('[ ]+', ' ', color)
color = color.strip()
sound = gutils.regextrim(self.page, 'Sound Mix:<[^>]+>', '</div>')
sound = gutils.strip_tags(sound)
sound = re.sub('[\n]+', '', sound)
sound = re.sub('[ ]+', ' ', sound)
sound = sound.strip()
tagline = gutils.regextrim(self.tagl_page, '>Taglines', '>See also')
taglines = re.split('<div[^>]+class="soda[^>]*>', tagline)
tagline = ''
if len(taglines) > 1:
for entry in taglines[1:]:
entry = gutils.clean(gutils.before(entry, '</div>'))
if entry:
tagline = tagline + entry + '\n'
if len(language) > 0:
self.notes = "%s: %s\n" % (_('Language'), language)
if len(sound) > 0:
self.notes += "%s: %s\n" % (gutils.strip_tags(
_('<b>Audio</b>')), sound)
if len(color) > 0:
self.notes += "%s: %s\n" % (_('Color'), color)
if len(tagline) > 0:
self.notes += "%s: %s\n" % ('Tagline', tagline)
def get_director(self):
self.director = gutils.trim(self.creditspage, u"reżyseria: <", "</tr>")
self.director = gutils.after(self.director, ">")
self.director = self.director.replace("<br />", ", ")
self.director = gutils.clean(self.director)
if self.director.endswith(","):
self.director = self.director[:-1]
def get_screenplay(self):
self.screenplay = gutils.trim(self.creditspage, u"scenariusz: <", "</tr>")
self.screenplay = gutils.after(self.screenplay, ">")
self.screenplay = self.screenplay.replace("<br />", ", ")
self.screenplay = gutils.clean(self.screenplay)
if self.screenplay.endswith(","):
self.screenplay = self.screenplay[:-1]
def get_plot(self):
self.plot = gutils.trim(self.page, '<div class="yui-content">',
'<div class="footer">')
if not self.plot:
# kino page
self.plot = gutils.after(
gutils.trim(self.page, 'Filmhandlung & Hintergrund', '</div>'),
'</h2>')
if not self.plot and self.videopage:
self.plot = gutils.trim(self.videopage,
'<div class="yui-content">',
'<div class="footer">')
if self.plot:
# video page
self.plot = re.sub('<script type="text/javascript">[^<]+</script>',
'', self.plot)
self.plot = string.replace(self.plot, '>Großansicht</a>', '>')
self.plot = string.replace(self.plot, '>Schließen</a>', '>')
self.plot = string.replace(self.plot, '>zurück </a>', '>')
self.plot = string.replace(self.plot, '>1</a>', '>')
self.plot = string.replace(self.plot, '> weiter</a>', '>')
self.plot = string.replace(self.plot, '</h4>', '\n')
self.plot = gutils.clean(self.plot)
compiledmultiline = re.compile(r'^[^(]+[(]Foto[:][^)]+[)][ ]*$',
re.MULTILINE)
self.plot = compiledmultiline.sub('', self.plot)
compiledmultiline = re.compile(r"(^\s+$|^\s*//\s*$)", re.MULTILINE)
self.plot = compiledmultiline.sub('', self.plot)
compiledmultiline = re.compile("^[\n]+$", re.MULTILINE)
self.plot = compiledmultiline.sub("\n", self.plot)
def get_searches(self):
if not self.page:
return
if len(self.page) < 20: # immidietly redirection to movie page
self.number_results = 1
self.ids.append(self.page)
self.titles.append(self.url)
else: # multiple matches
elements = string.split(self.page, '</a></b>')
if (elements[0] <> ''):
for index in range(0, len(elements) - 1, 1):
element = elements[index]
nextelement = elements[index + 1]
id = gutils.trim(element, '<b><a href="/es/film', '.html')
if id:
self.ids.append(id)
title = gutils.clean(
gutils.after(element,
'<b><a href="/es/film')).replace(
"\n", "")
title = gutils.strip_tags(
gutils.convert_entities(gutils.after(
title, '>'))) + ' ' + string.strip(
gutils.before(nextelement, '<'))
self.titles.append(title)
def get_notes(self):
self.notes = ''
language = gutils.trim(self.page, '<h5>Lingua:</h5>', '</div>')
language = gutils.strip_tags(language)
language = re.sub('[\n]+', '', language)
language = re.sub('[ ]+', ' ', language)
language = language.rstrip()
color = gutils.trim(self.page, '<h5>Colore:</h5>', '</div>')
color = gutils.strip_tags(color)
color = re.sub('[\n]+', '', color)
color = re.sub('[ ]+', ' ', color)
color = color.rstrip()
sound = gutils.trim(self.page, '<h5>Sonoro:</h5>', '</div>')
sound = gutils.strip_tags(sound)
sound = re.sub('[\n]+', '', sound)
sound = re.sub('[ ]+', ' ', sound)
sound = sound.rstrip()
date = gutils.trim(self.page, '<h5>Data di uscita:</h5>',
'<a class="tn15more inline"')
date = re.sub('[\n]+', '', date)
date = re.sub('[ ]+', ' ', date)
date = gutils.clean(date)
if len(language) > 0:
self.notes = "%s: %s\n" % (_('Language'), language)
if len(sound) > 0:
self.notes += "%s: %s\n" % (gutils.strip_tags(
_('<b>Audio</b>')), sound)
if len(color) > 0:
self.notes += "%s: %s\n" % (_('Color'), color)
if len(date) > 0:
self.notes += "%s: %s\n" % (_('Data di uscita'), date)
def get_searches(self):
elements = re.split(' <a title="[^"]+" href="(/datenbank/medien/dvd/|/datenbank/medien/blu-ray/)', self.page)
elements[0] = None
for index in range(1, len(elements), 2):
element = elements[index + 1]
if element <> None:
if elements[index] == '/datenbank/medien/blu-ray/':
medium = 'Blu-Ray'
self.ids.append('blu-ray/' + gutils.before(element,'"'))
else:
medium = 'DVD'
self.ids.append('dvd/' + gutils.before(element,'"'))
self.titles.append(
gutils.trim(element, '>', '</a>') +
gutils.clean(
'(' + medium + ' - ' +
re.sub('[ \t\n]+', ' ',
string.replace(
string.replace(
gutils.regextrim(element, '<div [^>]*>', '</div>'),
'<br>', ' - '),
' ', ''))
+ ')'
)
)
def get_genre(self):
self.genre = gutils.trim(self.page,"Genre(s):","</table>")
self.genre = string.replace(self.genre, "<br>", ", ")
self.genre = gutils.strip_tags(self.genre)
self.genre = string.replace(self.genre, "/", ", ")
self.genre = gutils.clean(self.genre)
self.genre = self.genre[0:-1]
def get_genre(self):
self.genre = ''
tmp = gutils.trim(self.page, '<th>GÉNERO</th>', '</tr>')
tmp = gutils.after(tmp, '<td>')
if tmp:
self.genre = gutils.clean(string.replace(tmp, ' | ', '. '))
self.genre = re.sub('[.][ \t]+', '. ', self.genre)
def get_searches(self):
elements = re.split(' <a title="[^"]+" href="(/datenbank/medien/dvd/|/datenbank/medien/blu-ray/)', self.page)
elements[0] = None
for index in range(1, len(elements), 2):
element = elements[index + 1]
if element <> None:
if elements[index] == '/datenbank/medien/blu-ray/':
medium = 'Blu-Ray'
self.ids.append('blu-ray/' + gutils.before(element,'"'))
else:
medium = 'DVD'
self.ids.append('dvd/' + gutils.before(element,'"'))
self.titles.append(
gutils.trim(element, '>', '</a>') +
gutils.clean(
'(' + medium + ' - ' +
re.sub('[ \t\n]+', ' ',
string.replace(
string.replace(
gutils.regextrim(element, '<div [^>]*>', '</div>'),
'<br>', ' - '),
' ', ''))
+ ')'
)
)
def get_cameraman(self):
self.cameraman = gutils.regextrim(self.creditspage, u"zdjęcia: <", "(</tr>|<tr>)")
self.cameraman = gutils.after(self.cameraman, ">")
self.cameraman = self.cameraman.replace("<br />", ", ")
self.cameraman = gutils.clean(self.cameraman)
if self.cameraman.endswith(","):
self.cameraman = self.cameraman[:-1]
def get_notes(self):
self.notes = ''
language = gutils.trim(self.page, '<h5>Lingua:</h5>', '</div>')
language = gutils.strip_tags(language)
language = re.sub('[\n]+', '', language)
language = re.sub('[ ]+', ' ', language)
language = language.rstrip()
color = gutils.trim(self.page, '<h5>Colore:</h5>', '</div>')
color = gutils.strip_tags(color)
color = re.sub('[\n]+', '', color)
color = re.sub('[ ]+', ' ', color)
color = color.rstrip()
sound = gutils.trim(self.page, '<h5>Sonoro:</h5>', '</div>')
sound = gutils.strip_tags(sound)
sound = re.sub('[\n]+', '', sound)
sound = re.sub('[ ]+', ' ', sound)
sound = sound.rstrip()
date = gutils.trim(self.page, '<h5>Data di uscita:</h5>', '<a class="tn15more inline"')
date = re.sub('[\n]+', '', date)
date = re.sub('[ ]+', ' ', date)
date = gutils.clean(date)
if len(language)>0:
self.notes = "%s: %s\n" %(_('Language'), language)
if len(sound)>0:
self.notes += "%s: %s\n" %(gutils.strip_tags(_('<b>Audio</b>')), sound)
if len(color)>0:
self.notes += "%s: %s\n" %(_('Color'), color)
if len(date)>0:
self.notes += "%s: %s\n" %(_('Data di uscita'), date)
def get_rating(self):
self.rating = gutils.clean(gutils.after(gutils.trim(self.page, '<span class="rating', '</a>'), '>'))
if self.rating:
try:
self.rating = str(round(float(self.rating)))
except:
self.rating = ''
def get_genre(self):
self.genre = ''
tmp = gutils.trim(self.page, '<th>GÉNERO</th>', '</tr>')
tmp = gutils.after(tmp, '<td>')
if tmp:
self.genre = gutils.clean(string.replace(tmp, ' | ', '. '))
self.genre = re.sub('[.][ \t]+', '. ', self.genre)
def get_rating(self):
self.rating = gutils.trim(self.page, "<b>Nutzer-Bewertung:</b>", "/10")
if self.rating:
try:
self.rating = str(float(gutils.clean(self.rating)))
except:
self.rating = ""
def get_notes(self):
self.notes = ""
language = gutils.regextrim(self.page, "Language:<[^>]+>", "</div>")
language = gutils.strip_tags(language)
language = re.sub("[\n]+", "", language)
language = re.sub("[ ]+", " ", language)
language = language.strip()
color = gutils.regextrim(self.page, "Color:<[^>]+>", "</div>")
color = gutils.strip_tags(color)
color = re.sub("[\n]+", "", color)
color = re.sub("[ ]+", " ", color)
color = color.strip()
sound = gutils.regextrim(self.page, "Sound Mix:<[^>]+>", "</div>")
sound = gutils.strip_tags(sound)
sound = re.sub("[\n]+", "", sound)
sound = re.sub("[ ]+", " ", sound)
sound = sound.strip()
tagline = gutils.regextrim(self.tagl_page, ">Taglines", ">See also")
taglines = re.split('<div[^>]+class="soda[^>]*>', tagline)
tagline = ""
if len(taglines) > 1:
for entry in taglines[1:]:
entry = gutils.clean(gutils.before(entry, "</div>"))
if entry:
tagline = tagline + entry + "\n"
if len(language) > 0:
self.notes = "%s: %s\n" % (_("Language"), language)
if len(sound) > 0:
self.notes += "%s: %s\n" % (gutils.strip_tags(_("<b>Audio</b>")), sound)
if len(color) > 0:
self.notes += "%s: %s\n" % (_("Color"), color)
if len(tagline) > 0:
self.notes += "%s: %s\n" % ("Tagline", tagline)
def get_cast(self):
self.cast = gutils.regextrim(self.page, '[(]Darsteller[)]', '(<[pP]>|<br><span[^>]+>)')
self.cast = gutils.clean(self.cast)
self.cast = self.cast.replace(' als ', _(' as '))
self.cast = re.sub('( \t|\t|\r|\n)', '', self.cast)
self.cast = self.cast.replace(', ', '\n')
self.cast = self.cast.replace(',', '')
def get_genre(self):
self.genre = gutils.trim(self.page,"Genre(s):","</table>")
self.genre = string.replace(self.genre, "<br>", ", ")
self.genre = gutils.strip_tags(self.genre)
self.genre = string.replace(self.genre, "/", ", ")
self.genre = gutils.clean(self.genre)
self.genre = self.genre[0:-1]
def get_screenplay(self):
self.screenplay = ''
tmp = gutils.trim(self.page_cast, '<h2>crew</h2>', '</dl>')
elements = string.split(tmp, '<dt>')
for element in elements:
if string.find(element, 'Screenwriter') > 0:
self.screenplay = gutils.clean(gutils.before(element, '</a>'))
def get_cameraman(self):
self.cameraman = ''
tmp = gutils.trim(self.page_cast, '<h2>crew</h2>', '</dl>')
elements = string.split(tmp, '<dt>')
for element in elements:
if string.find(element, 'Cinematographer') > 0:
self.cameraman = gutils.clean(gutils.before(element, '</a>'))
def capwords(
self, name
): # Does not work with accented letters => discarded in titles
tmp = gutils.clean(name)
if tmp == string.upper(tmp):
return string.capwords(name)
return name
def get_director(self):
self.director = gutils.trim(self.creditspage, u'reżyseria: <', '</tr>')
self.director = gutils.after(self.director, '>')
self.director = self.director.replace('<br />', ', ')
self.director = gutils.clean(self.director)
if self.director.endswith(','):
self.director = self.director[:-1]
def get_runtime(self):
self.runtime = gutils.clean(gutils.trim(self.page, u'Durée : ', '</span>'))
if self.runtime:
if self.runtime.find('H') > 0:
self.runtime = str (int(gutils.before(self.runtime,'H'))*60 + int(gutils.after(self.runtime,'H')))
else:
self.runtime = gutils.before(self.runtime,' mn')
def get_director(self):
self.director = gutils.trim(self.page,'<h5>Regie</h5>', '<br/>')
if self.director == '':
self.director = gutils.trim(self.page,'<h5>Regisseur:</h5>', '</div>')
self.director = self.__before_more(self.director)
self.director = self.director.replace('<br/>', ', ')
self.director = gutils.clean(self.director)
self.director = re.sub(',$', '', self.director)
def get_rating(self):
self.rating = gutils.after(
gutils.trim(self.page, 'id="movie-rat-avg"', '</div>'), '>')
if self.rating:
self.rating = str(
round(
float(gutils.clean(string.replace(self.rating, ',',
'.')))))
def get_cameraman(self):
self.cameraman = gutils.regextrim(self.creditspage, u'zdjęcia: <',
'(</tr>|<tr>)')
self.cameraman = gutils.after(self.cameraman, '>')
self.cameraman = self.cameraman.replace('<br />', ', ')
self.cameraman = gutils.clean(self.cameraman)
if self.cameraman.endswith(','):
self.cameraman = self.cameraman[:-1]
def get_cast(self):
self.cast = gutils.trim(self.page, u'<b>Elenco:</b>', u'</td>')
self.cast = string.replace(self.cast, u'<br>', u'\n')
self.cast = string.replace(self.cast, u', ', u'')
self.cast = string.replace(self.cast, u'\t', u'')
self.cast = string.replace(self.cast, u'\n ', u'\n')
self.cast = gutils.clean(self.cast)
self.cast = re.sub('[ \t]*[\n]+[ \t]*' , '\n', self.cast)
def get_rating(self):
"""Find the film's rating. From 0 to 10.
Convert if needed when assigning."""
self.rating = gutils.clean(gutils.trim(self.page, u'IMDB: ', u'</span>'))
try:
self.rating = round(float(self.rating), 0)
except Exception, e:
self.rating = 0
def get_cameraman(self):
self.cameraman = gutils.trim(self.cast_page, '>Kamera</a>', '</table>')
self.cameraman = string.replace(self.cameraman, '(Kamera)', '')
self.cameraman = string.replace(self.cameraman, '(nicht im Abspann)', '')
self.cameraman = string.replace(self.cameraman, '</a>', ', ')
self.cameraman = gutils.clean(self.cameraman)
self.cameraman = re.sub(',[ \t]*$', '', self.cameraman)
self.cameraman = re.sub('[ ]+', ' ', self.cameraman)
def get_o_title(self):
self.o_title = string.capwords(
gutils.clean(
gutils.regextrim(self.page, '<b>Originaltitel:',
'(</p>|<b>)')))
if not self.o_title:
self.o_title = gutils.after(
gutils.trim(self.page, 'class=\'film-titel\'', '</h1>'), '>')
def get_screenplay(self):
self.screenplay = gutils.trim(self.creditspage, u'scenariusz: <',
'</tr>')
self.screenplay = gutils.after(self.screenplay, '>')
self.screenplay = self.screenplay.replace('<br />', ', ')
self.screenplay = gutils.clean(self.screenplay)
if self.screenplay.endswith(','):
self.screenplay = self.screenplay[:-1]
def get_notes(self):
self.notes = ""
tmp_notes = gutils.clean(gutils.trim(self.page, "<strong>Sprachen:</strong>", "</p>"))
if tmp_notes != "":
self.notes = self.notes + "Sprachen:\n" + tmp_notes + "\n\n"
tmp_notes = gutils.clean(gutils.trim(self.page, "<strong>Untertitel:</strong>", "</p>"))
if tmp_notes != "":
self.notes = self.notes + "Untertitel:\n" + tmp_notes + "\n\n"
tmp_notes = gutils.clean(gutils.trim(self.page, "<strong>Tonformat:</strong>", "</p>"))
if tmp_notes != "":
self.notes = self.notes + "Tonformat:\n" + tmp_notes + "\n\n"
tmp_notes = gutils.clean(gutils.trim(self.page, "<strong>Bildformat:</strong>", "</p>"))
if tmp_notes != "":
self.notes = self.notes + "Bildformat:\n" + tmp_notes + "\n\n"
tmp_notes = gutils.clean(gutils.trim(self.page, "<strong>EAN</strong>", "</p>"))
if tmp_notes != "":
self.notes = self.notes + "EAN:\n" + tmp_notes + "\n\n"
def get_cameraman(self):
# Find the cameraman
self.cameraman = gutils.trim(self.page, 'Fotografia</font></td></tr><tr>', '<td colspan="2"')
self.cameraman = string.replace(self.cameraman, '<tr>', ', ')
# beautification
self.cameraman = gutils.clean(self.cameraman)
self.cameraman = string.replace(self.cameraman, ' ,', ',')
self.cameraman = re.sub('[ ]+', ' ', self.cameraman)
self.cameraman = re.sub('[,][ ]*$', '', self.cameraman)
def get_screenplay(self):
# Find the screenplay
self.screenplay = gutils.trim(self.page, 'Sceneggiatura</font></td></tr><tr>', '<td colspan="2"')
self.screenplay = string.replace(self.screenplay, '<tr>', ', ')
# beautification
self.screenplay = gutils.clean(self.screenplay)
self.screenplay = string.replace(self.screenplay, ' ,', ',')
self.screenplay = re.sub('[ ]+', ' ', self.screenplay)
self.screenplay = re.sub('[,][ ]*$', '', self.screenplay)
def get_searches(self):
elements = re.findall(
"""/film/film.asp\?fi=(\d+)"[^>]*>.*?searchTitle\s*textB">(.*?)</span>.*?"> (.*?)</span>""",
self.page)
self.number_results = len(elements)
for element in elements:
self.ids.append(element[0])
self.titles.append(gutils.clean(element[1]) + ' ' + element[2])
