def get_country(self):
self.country = gutils.trim(self.page, u'<b>PAÍS</b></td>', '</td>')
tmp = gutils.trim(self.country, 'alt="', '"')
if tmp == '':
self.country = gutils.trim(self.country, 'title="', '"')
else:
self.country = tmp
def get_genre(self):
self.genre = gutils.trim(self.page, 'Genres:</td>', '</td>')
if self.genre == '':
self.genre = gutils.trim(self.page, 'Genre:</td>', '</td>')
self.genre = self.genre.replace('\t', '')
self.genre = self.genre.replace('\n', '')
self.genre = self.genre.replace('\r', '')
def get_director(self): if (gutils.trim(self.url, "typ=", "&") <> "credits"): self.url = self.url_to_use + "typ=credits&nr=" + str(self.movie_id) self.open_page(self.parent_window) self.director = gutils.trim(self.page,"Regie","</a>") self.director = gutils.after(self.director,"mitwirk.php4") self.director = gutils.after(self.director,">")
def get_studio(self):
self.studio = gutils.strip_tags(gutils.trim(self.detail_page, 'alt="Produktion"', ' '))
if self.studio == '':
self.studio = gutils.trim(self.detail_page, 'alt="Produktion"', '</TABLE>')
self.studio = gutils.after(self.studio, '>')
self.studio = self.studio.replace('\n', ', ')
self.studio = re.sub('((^, )|(, $))', '', self.studio)
def get_searches(self):
elements = string.split(self.page, '<td><b>')
if (elements[0]<>''):
for element in elements:
self.ids.append(gutils.trim(element, 'ver.php?art=',"'"))
self.titles.append(gutils.strip_tags(gutils.convert_entities(gutils.trim(element, "target='_top'>", '</a>'))))
def get_notes(self):
self.notes = ''
tmp_page = gutils.trim(self.page, '<h3>Features</h3>', '</p>')
tmp_page = tmp_page.replace('<br>', '\n')
tmp_page = tmp_page.replace('<br />', '\n')
tmp_page = gutils.strip_tags(tmp_page)
if tmp_page <> '':
self.notes = self.notes + 'Features:\n' + tmp_page + '\n\n'
tmp_page = gutils.trim(self.page, 'Video</strong>', '<strong>')
tmp_page = tmp_page.replace('\r\n', '')
tmp_page = re.sub('[ \t]+', ' ', tmp_page)
tmp_page = tmp_page.replace('<br>', '\n')
tmp_page = tmp_page.replace('<br />', '\n')
tmp_page = gutils.strip_tags(tmp_page)
if tmp_page <> '':
self.notes = self.notes + 'Video:' + tmp_page
tmp_page = gutils.trim(self.page, 'Audio</strong>', '</div>')
tmp_page = tmp_page.replace('\r\n', '')
tmp_page = re.sub('[ \t]+', ' ', tmp_page)
tmp_page = tmp_page.replace('<br>', '\n')
tmp_page = tmp_page.replace('<br />', '\n')
tmp_page = tmp_page.replace('(more info)', '\n')
tmp_page = gutils.strip_tags(tmp_page)
if tmp_page <> '':
self.notes = self.notes + 'Audio:' + tmp_page
def get_plot(self):
text = re.search(r"\?text=([\d]*)", self.page)
if text:
page_content = self.open_page(url=self.url+"?text="+text.group(1))
self.plot = gutils.strip_tags(gutils.trim(page_content,"Obsah:"," <b><i>("))
else:
self.plot = gutils.strip_tags(gutils.trim(self.page,"Obsah:"," <b><i>("))
def search(self,parent_window): self.open_search(parent_window) tmp_page = gutils.trim(self.page, 'Matchning', 'Hittade') if tmp_page == '': tmp_page = gutils.trim(self.page, 'Matchning', 'Visa fler') self.page = tmp_page return self.page
def get_studio(self):
self.studio = gutils.strip_tags(gutils.trim(self.detail_page, 'alt="Produktion"', " "))
if self.studio == "":
self.studio = gutils.trim(self.detail_page, 'alt="Produktion"', "</TABLE>")
self.studio = gutils.after(self.studio, ">")
self.studio = self.studio.replace("\n", ", ")
self.studio = re.sub("((^, )|(, $))", "", self.studio)
def get_searches(self):
elements = string.split(self.page, '<li>')
if (elements[0]<>''):
for element in elements:
self.ids.append(gutils.trim(element, '/title/tt','/?fr='))
self.titles.append(gutils.strip_tags(gutils.convert_entities(gutils.trim(element, ';fm=1">', '</li>'))))
def get_notes(self):
self.notes = ""
tmp_page = gutils.trim(self.page, "Features:", "<b>")
tmp_page = tmp_page.replace("<br>", "\n")
tmp_page = tmp_page.replace("<br />", "\n")
tmp_page = gutils.strip_tags(tmp_page)
if tmp_page <> "":
tmp_page = re.sub("[\r\n]+", "\n", tmp_page)
self.notes = self.notes + "\nFeatures:" + tmp_page + "\n"
tmp_page = gutils.trim(self.page, "Video:", "<b>")
tmp_page = tmp_page.replace("<br>", "\n")
tmp_page = tmp_page.replace("<br />", "\n")
tmp_page = gutils.strip_tags(tmp_page)
if tmp_page <> "":
tmp_page = re.sub("[\r\n]+", "\n", tmp_page)
self.notes = self.notes + "\nVideo:" + tmp_page + "\n"
tmp_page = gutils.trim(self.page, "Audio:", "<b>")
tmp_page = tmp_page.replace("<br>", "\n")
tmp_page = tmp_page.replace("<br />", "\n")
tmp_page = gutils.strip_tags(tmp_page)
if tmp_page <> "":
tmp_page = re.sub("[\r\n]+", "\n", tmp_page)
self.notes = self.notes + "\nAudio:" + tmp_page
tmp_page = gutils.trim(self.page, "Subtitles:", "<b>")
tmp_page = gutils.strip_tags(tmp_page)
if tmp_page <> "":
tmp_page = re.sub("[\r\n]+", "\n", tmp_page)
self.notes = self.notes + "\nSubtitles:\n" + tmp_page + "\n"
def get_notes(self):
self.notes = ""
tmp_notes = re.sub('^[ \t]+', '',
gutils.strip_tags(
re.sub('(<br>|<br />)', '\r\n',
re.sub('[\r\n]+', '',
re.sub('[ \t][ \t\r\n]+', ' ',
gutils.trim(self.page, 'Bildformat(e)', '</TR>')))))
)
if (tmp_notes != ""):
self.notes = self.notes + "Bildformat(e):\n" + tmp_notes + "\n"
tmp_notes = re.sub('^[ \t]+', '',
gutils.strip_tags(
re.sub('(<br>|<br />)', '\r\n',
re.sub('[\r\n]+', '',
re.sub('[ \t][ \t\r\n]+', ' ',
gutils.trim(self.page, 'Tonformat(e)', '</TR>')))))
)
if (tmp_notes != ""):
self.notes = self.notes + "Tonformat(e):\n" + tmp_notes + "\n\n"
tmp_notes = re.sub('^[ \t]+', '',
gutils.strip_tags(
re.sub('(<br>|<br />)', '\r\n',
re.sub('[\r\n]+', '',
re.sub('[ \t][ \t\r\n]+', ' ',
gutils.trim(self.page, 'Untertitel', '</TR>')))))
)
if (tmp_notes != ""):
self.notes = self.notes + "Untertitel:" + tmp_notes + "\n\n"
def get_country(self):
self.country = gutils.trim(self.page, u'<h5>País:</h5>', '</div>')
if self.country == '':
self.country = gutils.trim(self.page, '<h5>País:</h5>', '</a>')
self.country = self.__before_more(self.country)
self.country = re.sub('[\n]+', '', self.country)
self.country = re.sub('[ ]+', ' ', self.country)
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 search(self,parent_window):
self.open_search(parent_window)
# short the content
tmp_page = gutils.trim(self.page,'<select name="sort"', 'Click Here to make a Suggestion</a>')
#
# try to get all result pages (not so nice, but it works)
#
tmp_pagecount = gutils.trim(self.page, '<div id="Search_Container" name="Search_Container">', '</table>')
tmp_pagecountintuse = 1
elements = tmp_pagecount.split("&page=")
for element in elements:
try:
tmp_pagecountint = int(gutils.before(element, '\''))
except:
tmp_pagecountint = 0
if tmp_pagecountint > tmp_pagecountintuse:
tmp_pagecountintuse = tmp_pagecountint
tmp_pagecountintcurrent = 1
while tmp_pagecountintuse > tmp_pagecountintcurrent and tmp_pagecountintuse < 4:
tmp_pagecountintcurrent = tmp_pagecountintcurrent + 1
self.url = "http://www.dvdempire.com/Exec/v1_search_all.asp?&site_media_id=0&pp=&search_refined=32&used=0&page=" + str(tmp_pagecountintcurrent) + "&string="
self.open_search(parent_window)
tmp_page2 = gutils.trim(self.page,'<select name="sort"', 'Click Here to make a Suggestion</a>')
tmp_page = tmp_page + tmp_page2
self.page = tmp_page
return self.page
def get_image(self):
self.image_url = gutils.trim(self.page, 'class="moviePosterTable"', '</td>');
self.image_url = gutils.trim(self.image_url,' src="',"\"\n")
if self.image_url.endswith('no_picture.png'):
self.image_url = ''
else:
self.image_url = "http://fdb.pl%s" % self.image_url
def get_o_title(self):
self.o_title = gutils.trim(self.tmp_page,"span class=\"standardsmall\"><br />(",")<")
if self.o_title == "":
if self.url_type == "V":
self.o_title = gutils.after(gutils.trim(self.tmp_page,"\"headline2\"><a href=\"/videofilm", "</a>"), ">")
else:
self.o_title = gutils.after(gutils.trim(self.tmp_page,"\"headline2\"><a href=\"/kinofilm", "</a>"), ">")
def get_searches(self):
elements1 = re.split('headline3"><a href="(http://www.kino.de)*/kinofilm/', self.page)
elements1[0] = None
for element in elements1:
if element <> None:
self.ids.append("K_" + re.sub('[?].*', '', gutils.before(element,'"')))
self.titles.append(string.replace(string.replace(
gutils.strip_tags(
gutils.trim(element,'>','</a>') + ' (' +
string.replace(
gutils.trim(element, '<span class="standardsmall">', "</span>"),
'<br />', ' - ')
+ ')'
),
'( - (', '('), '))', ')')
)
elements2 = re.split('headline3"><a href="(http://www.kino.de)*/videofilm/', self.page)
elements2[0] = None
for element in elements2:
if element <> None:
self.ids.append("V_" + re.sub('[?].*', '', gutils.before(element,'"')))
self.titles.append(string.replace(string.replace(
gutils.strip_tags(
gutils.trim(element,'>','</a>') + ' (' +
string.replace(
gutils.trim(element, '<span class="standardsmall">', '</span>'),
'<br />', ' - ')
+ ')'
),
'( - (', '('), '))', ')')
)
def search(self, parent_window):
self.open_search(parent_window)
tmp_page = gutils.trim(self.page, "Matchning", "Hittade")
if tmp_page == "":
tmp_page = gutils.trim(self.page, "Matchning", "Visa fler")
self.page = tmp_page
return self.page
def get_notes(self):
self.notes = ''
tmp_page = gutils.trim(self.page, 'Features:', '<b>')
tmp_page = tmp_page.replace('<br>', '\n')
tmp_page = tmp_page.replace('<br />', '\n')
tmp_page = gutils.strip_tags(tmp_page)
if tmp_page <> '':
tmp_page = re.sub('[\r\n]+', '\n', tmp_page)
self.notes = self.notes + '\nFeatures:' + tmp_page + '\n'
tmp_page = gutils.trim(self.page, 'Video:', '<b>')
tmp_page = tmp_page.replace('<br>', '\n')
tmp_page = tmp_page.replace('<br />', '\n')
tmp_page = gutils.strip_tags(tmp_page)
if tmp_page <> '':
tmp_page = re.sub('[\r\n]+', '\n', tmp_page)
self.notes = self.notes + '\nVideo:' + tmp_page + '\n'
tmp_page = gutils.trim(self.page, 'Audio:', '<b>')
tmp_page = tmp_page.replace('<br>', '\n')
tmp_page = tmp_page.replace('<br />', '\n')
tmp_page = tmp_page.replace('(more info)', '\n')
tmp_page = gutils.strip_tags(tmp_page)
if tmp_page <> '':
tmp_page = re.sub('[\r\n]+', '\n', tmp_page)
self.notes = self.notes + '\nAudio:' + tmp_page
tmp_page = gutils.trim(self.page, 'Subtitles:', '<b>')
tmp_page = gutils.strip_tags(tmp_page)
if tmp_page <> '':
tmp_page = re.sub('[\r\n]+', '\n', tmp_page)
self.notes = self.notes + '\nSubtitles:\n' + tmp_page + '\n'
def get_searches(self):
if self.page is None: # movie page
self.ids.append(self.url)
self.titles.append(gutils.convert_entities(self.title))
elif self.page is False: # no movie found
self.number_results = 0
else: # multiple matches
elements = self.page.split('<li ')
self.number_results = elements[-1]
if elements != '':
for element in elements:
if (element == ''):
continue
element = gutils.after(element, 'href="')
self.ids.append('http://' + plugin_url_other + gutils.before(element, '"'))
element_title = gutils.trim(element, '">', '</a>')
element_title = element_title.replace('\t', '')
element = gutils.after(element, 'class=searchResultDetails')
element_year = gutils.trim(element, '>', '|')
element_year = element_year.replace(" ", '')
element_year = gutils.strip_tags(element_year)
element_country = ''
pos_country = element.find('countryIds')
if pos_country != -1:
element_country = gutils.trim(element[pos_country:], '">', '</a>')
element = element_title.strip()
if element_year:
element += ' (' + element_year.strip() + ')'
if element_country:
element += ' - ' + element_country.strip()
element = gutils.convert_entities(element)
element = gutils.strip_tags(element)
self.titles.append(element)
else:
self.number_results = 0
def picture(self): self.page = gutils.trim(self.page,"<table width=\"100%\" cellpadding=\"0\" cellspacing=\"0\" border=\"0\">","<script ") # should go to sub_page function! if string.find(self.page,"http://film.wp.pl/f/no.gif") > -1: self.picture_url = "" else: self.picture_url = gutils.trim(self.page,"http://film.wp.pl/f/prev/","\" width=") self.picture_url = 'http://film.wp.pl/f/prev/' + self.picture_url
def get_searches(self): elements = string.split(self.page,"<br>") if (elements[0]<>''): for element in elements: self.ids.append(gutils.trim(element,"<a href='view.php?page=film&fid=","'>")) self.titles.append(gutils.trim(element,">","</a>"))
def get_notes(self):
self.notes = ''
language = gutils.trim(self.page, '<h5>Language:</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>Color:</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>Sound Mix:</h5>', '</div>')
sound = gutils.strip_tags(sound)
sound = re.sub('[\n]+', '', sound)
sound = re.sub('[ ]+', ' ', sound)
sound = sound.rstrip()
tagline = gutils.trim(self.page, '<h5>Tagline:</h5>', '</div>')
tagline = self.__before_more(tagline)
tagline = gutils.strip_tags(tagline)
tagline = re.sub('[\n]+', '', tagline)
tagline = re.sub('[ ]+', ' ', tagline)
tagline = tagline.rstrip()
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_plot(self):
self.plot = gutils.trim(self.page, '<b class="ch">Resumen', '<a href="/rg/title-tease/plot')
self.plot = gutils.after(self.plot, ':</b> ')
self.plot = gutils.trim(self.page, '<h5>Trama:</h5>', '</div>')
self.plot = self.__before_more(self.plot)
tmp = gutils.trim(self.plot_page, '<div id="swiki.2.1">', '</div>')
if tmp:
self.plot = tmp
elements = string.split(self.plot_page, '<p class="plotpar">')
if len(elements) > 1:
self.plot = self.plot + '\n\n'
elements[0] = ''
for element in elements:
if element != '':
self.plot = self.plot + gutils.strip_tags(gutils.before(element, '</a>')) + '\n'
if not self.plot:
# nothing in spanish found, try original
self.plot = gutils.regextrim(self.imdb_page, '<h5>Plot:</h5>', '(</div>|<a href.*)')
self.plot = self.__before_more(self.plot)
elements = string.split(self.imdb_plot_page, '<p class="plotpar">')
if len(elements) > 1:
self.plot = self.plot + '\n\n'
elements[0] = ''
for element in elements:
if element <> '':
self.plot = self.plot + gutils.strip_tags(gutils.before(element, '</a>')) + '\n\n'
def get_notes(self):
self.notes = ""
self.url = self.url_to_use + "typ=features&nr=" + str(self.movie_id)
self.open_page(self.parent_window)
self.tmp_page = gutils.trim(self.page, "<!-- PRINT-CONTENT-START-->", "<!-- PRINT-CONTENT-ENDE-->")
tmp_notes = string.replace(
gutils.strip_tags(gutils.trim(self.tmp_page, "<b>Sprache</b>", "</TD></TR>")), " ", ""
)
if tmp_notes != "":
self.notes = self.notes + "Sprachen:\n" + tmp_notes + "\n\n"
tmp_notes = string.replace(
gutils.strip_tags(gutils.trim(self.tmp_page, "<b>Untertitel</b>", "</TD></TR>")), " ", ""
)
if tmp_notes != "":
self.notes = self.notes + "Untertitel:\n" + tmp_notes + "\n\n"
tmp_notes = string.replace(
gutils.strip_tags(gutils.trim(self.tmp_page, "<b>Mehrkanalton</b>", "</TD></TR>")), " ", ""
)
if tmp_notes != "":
self.notes = self.notes + "Mehrkanalton:\n" + tmp_notes + "\n\n"
tmp_notes = string.replace(
gutils.strip_tags(gutils.trim(self.tmp_page, "<b>EAN</b>", "</TD></TR>")), " ", ""
)
if tmp_notes != "":
self.notes = self.notes + "EAN:\n" + tmp_notes + "\n\n"
def get_rating(self):
self.rating = gutils.trim(self.page, '<div class=rates>', '</div>')
self.rating = gutils.trim(self.rating, '<span property="v:average">', '</span>')
if self.rating != '':
self.rating = self.rating.replace(' ', '')
self.rating = self.rating.replace(',', '.')
self.rating = str(float(self.rating.strip()))
def get_image(self): tmp = gutils.trim(self.page, 'plakat.php?', '\'') if tmp: page_image = self.open_page(url='http://www.filmdb.de/plakat.php?' + tmp) tmp = gutils.trim(self.page, 'bilder.filmdb.de', '\'') if tmp: self.image_url = 'http://bilder.filmdb.de' + tmp
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_o_title(self):
self.url = self.url.replace(plugin_server, plugin_url)
self.o_title = gutils.trim(self.page, '<title>', '</title>')
if self.o_title.find('/') > -1:
self.o_title = gutils.trim(self.o_title, '/', '(')
if self.o_title.find('(') > -1:
self.o_title = gutils.before(self.o_title, '(')
def search(self, parent_window):
if not self.open_search(parent_window):
return None
tmp = string.find(self.page, "<table class=\"animelist strippedlist\"")
if tmp == -1: # only one match!
self.page = ''
else: # multiple matches
self.page = gutils.trim(self.page,
"<table class=\"animelist strippedlist\"",
"</tbody>")
self.page = gutils.after(self.page, "<tbody>")
return self.page
def get_searches(self):
elements = string.split(self.page, "<h3 style=\"margin:0px;\">")
self.number_results = len(elements) - 1
if self.number_results > 0:
i = 1
while i < len(elements):
element = gutils.trim(elements[i], "<a", "</a>")
# print "******* elemento "+str(i)+" **********\n\n\n\n\n"+element+"\n******fine*******\n\n\n\n\n\n"
# print "id = "+gutils.trim(element,"recensione.asp?id=","\"")
# print "title = "+gutils.convert_entities(gutils.strip_tags(gutils.trim(element,'" title="', '"')))
self.ids.append(
gutils.trim(element, "recensione.asp?id=", "\""))
self.titles.append(
gutils.convert_entities(
gutils.strip_tags(
gutils.trim(element, '" title="', '"'))))
i += 1
else:
self.number_results = 0
def get_searches(self):
elements = re.split('class="card-link', self.page)
elements[0] = None
for element in elements:
if element <> None:
element = gutils.trim(element, 'href="', '</a>')
url = gutils.before(element, '"')
if url[0] == '/':
url = "https:" + url
title = gutils.after(element, '>')
self.ids.append(url)
self.titles.append(title)
def get_cast(self):
self.cast = ''
elements = string.split(gutils.before(self.castpage, 'Filmmakers</div>'), '<div class="linkblu"')
i = 3
while i < len(elements):
actorandrole = gutils.after(gutils.trim(elements[i], '<div', '</div>'), '>')
actorandrole = string.replace(actorandrole, '</a>', _(' as '))
actorandrole = gutils.clean(actorandrole)
actorandrole = re.sub('(\n|\r)', '', actorandrole)
actorandrole = re.sub('[ \t]+', ' ', actorandrole)
self.cast = self.cast + actorandrole + '\n'
i += 1
def get_studio(self): # OK v0.1
self.studio = ''
tmp = gutils.regextrim(self.comp_page,
'Sociétés de Production<[^>]+',
'</ul>')
tmp = string.split(tmp, 'href="')
for entry in tmp:
entry = gutils.trim(entry, '>', '<')
if entry:
self.studio = self.studio + entry + ', '
if self.studio:
self.studio = self.studio[:-2]
def get_rating(self):
self.rating = gutils.trim(self.page, '<h5>Nutzer-Bewertung:</h5>',
'/10')
if self.rating:
try:
tmp = re.findall('[0-9.,]+', gutils.clean(self.rating))
if tmp and len(tmp) > 0:
self.rating = round(float(tmp[0].replace(',', '.')))
except:
self.rating = 0
else:
self.rating = 0
def get_year(self):
self.year = ''
tmp = gutils.trim(self.page, '<div class="description">', '</div>')
if tmp:
searchyearandcountry = re.search('([0-9]{4})<br', tmp)
if searchyearandcountry:
self.year = searchyearandcountry.group(1)
if not self.year:
tmp = gutils.trim(self.page, '<span class="standardsmall"><strong>', '<br')
if tmp:
tmp = gutils.trim(tmp, '<strong>', '</strong>')
if tmp:
srchyear = re.search('([0-9]{4})', tmp)
if srchyear:
self.year = srchyear.group(1)
if not self.year and self.videopage:
tmp = gutils.trim(self.videopage, '<div class="description">', '</div>')
if tmp:
searchyearandcountry = re.search('([0-9]{4})<br', tmp)
if searchyearandcountry:
self.year = searchyearandcountry.group(1)
def get_rating(self):
self.rating = gutils.trim(self.page,
'Unsere User haben diesen Film mit ',
' bewertet.')
self.rating = self.rating.replace('%', '')
self.rating = gutils.strip_tags(self.rating)
elements = self.rating.split('.')
try:
tmprating = int(elements[0])
self.rating = str(tmprating / 10)
except:
self.rating = '0'
def get_studio(self):
self.studio = ''
tmp = gutils.regextrim(self.comp_page, 'name="production"', '</ul>')
tmp = string.split(tmp, 'href="')
if len(tmp) > 1:
for entry in tmp[1:]:
entry = string.strip(
string.replace(gutils.trim(entry, '>', '<'), '\n', ''))
if entry:
self.studio = self.studio + entry + ', '
if self.studio:
self.studio = self.studio[:-2]
def search(self,parent_window):
self.url = self.real_url_search # compatibility pre 0.13.1
self.open_search(parent_window)
print self.url
pagemovie = self.page
#
# Sub Pages
#
pagesarea = gutils.trim(pagemovie, 'class="pagination-list"', '</ol>')
pagelements = re.split('href="', pagesarea)
self.title = ''
self.o_title = ''
for index in range(1, len(pagelements), 1):
pagelement = pagelements[index]
self.url = gutils.before(pagelement, '"')
self.open_search(parent_window)
if self.page:
pagemovie = pagemovie + gutils.after(gutils.trim(self.page, 'class="search-result-list figure"', '</ol>'), '>')
self.page = pagemovie
return self.page
def get_plot(self):
plotlist = string.split(gutils.trim(self.plot_page, 'id="plot-summaries-content">', '</ul>'), '<li')
plotcompilation = ''
for listelement in plotlist:
if listelement <> '' and not 'It looks like we don\'t have any Plot Summaries for this title yet.' in listelement:
plotcompilation = plotcompilation + gutils.trim(listelement, '<p>', '</p>') + '\n'
plotcompilation = plotcompilation + re.sub('<[^<]+?>', '', gutils.trim(listelement, '<div class="author-container">', '</div>').replace('\n','').lstrip()) + '\n\n'
if plotcompilation <> '':
self.plot = plotcompilation
else:
self.plot = gutils.regextrim(self.page, 'itemprop="description"', '<')
self.plot = gutils.after(self.plot, '>')
elements = string.split(self.plot_page, '<p class="plotpar">')
if len(elements) < 2:
elements = re.split('<li class="(?:odd|even)">', self.plot_page)
if len(elements) > 1:
self.plot = self.plot + '\n\n'
elements[0] = ''
for element in elements[1:]:
if element <> '':
self.plot = self.plot + gutils.strip_tags(gutils.before(element, '</a>')) + '\n\n'
def get_notes(self):
self.notes = ''
language = gutils.trim(self.page, '<h5>Sprache:</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>Farbe:</h5>', '</div>')
color = gutils.strip_tags(color)
color = re.sub('[\n]+', '', color)
color = re.sub('[ ]+', ' ', color)
color = re.sub('[ ]+$', '', color)
color = color.rstrip()
sound = gutils.trim(self.page, '<h5>Tonverfahren:</h5>', '</div>')
sound = gutils.strip_tags(sound)
sound = re.sub('[\n]+', '', sound)
sound = re.sub('[ ]+', ' ', sound)
sound = sound.rstrip()
soundsplit = sound.split(' | ')
if len(soundsplit) > 1:
soundsplit.sort()
sound = ''
for elem in soundsplit:
sound += elem + ' | '
sound = sound[0:len(sound) - 3]
tagline = gutils.trim(self.page, '<h5>Werbezeile:</h5>', '</div>')
tagline = self.__before_more(tagline)
tagline = gutils.strip_tags(tagline)
tagline = re.sub('[\n]+', '', tagline)
tagline = re.sub('[ ]+', ' ', tagline)
tagline = tagline.rstrip()
if len(language) > 0:
self.notes = "%s: %s\n" % (_('Language').encode('utf8'), language)
if len(sound) > 0:
self.notes += "%s: %s\n" % (gutils.strip_tags(
_('<b>Audio</b>').encode('utf8')), sound)
if len(color) > 0:
self.notes += "%s: %s\n" % (_('Color').encode('utf8'), color)
if len(tagline) > 0:
self.notes += "%s: %s\n" % ('Tagline', tagline)
def get_searches(self):
elements = string.split(self.page, "<td width=100% height=18")
self.number_results = elements[-1]
if (elements[0] != ''):
for element in elements:
print(
gutils.trim(element,
"align=center valign=top><a href=\"filme_",
"_"))
self.ids.append(
gutils.trim(element,
"align=center valign=top><a href=\"filme_",
"_"))
print(
gutils.strip_tags(
gutils.trim(
element,
"<font color=#FFFFFF face=Verdana size=2>",
"</font></a></b></td>") + ' - ' +
gutils.trim(element, "Ano de Lançamento:", "<br>")))
self.titles.append(
gutils.strip_tags(
gutils.trim(
element,
"<font color=#FFFFFF face=Verdana size=2>",
"</font></a></b></td>") + ' - ' +
gutils.trim(element, "Ano de Lançamento:", "<br>")))
else:
self.number_results = 0
def get_notes(self):
self.notes = "Czas trwania: " + gutils.trim(
self.page, "<div class=\"sitem\">Czas trwania: <b>\n\t\t",
"\n</b>") + '\n'
t = self.page.find("<tr><th scope=\"row\">Autor:</th>")
if t != -1:
self.notes += "Autor: %s\n" % gutils.trim(self.page[t:], "<td>\n",
"\t</td>")
t = self.page.find("<th scope=\"row\">Projekt:</th>")
if t != -1:
self.notes += "Projekt: %s\n" % gutils.trim(
self.page[t:], "<td>\n", "\t</td>")
t = self.page.find("<tr><th scope=\"row\">Scenariusz:</th>")
if t != -1:
self.notes += "Scenariusz: %s\n" % gutils.trim(
self.page[t:], "<td>\n", "\t</td>")
t = self.page.find("<th scope=\"row\">Muzyka:</th>")
if t != -1:
self.notes += "Muzyka: %s\n" % gutils.trim(self.page[t:], "<td>\n",
"\t</td>")
self.notes += "\n%s" % gutils.trim(
self.page, "<p class=\"dwazdania\">\n\t\t", "\n</p>")
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_searches(self):
if string.find(self.page, '>Films<') < 0:
self.ids.append(gutils.regextrim(self.page, '="/db/movies/view[.]mhtml[?]id=', '([&"])'))
self.titles.append('')
else:
elements = string.split(self.page, '<a href="/db/movies/view.mhtml?id=')
elements[0] = ''
for element in elements:
if element <> '' and string.find(element, 'display_set=eng') > -1:
id = gutils.before(gutils.before(element, '"'), '&')
if id <> '':
self.ids.append(id)
self.titles.append(gutils.trim(element, '>', '</a>'))
def get_cameraman(self):
self.cameraman = ''
tmp = gutils.regextrim(self.cast_page, '>Cinematography by',
'</table>')
tmp = string.split(tmp, 'href="')
if len(tmp) > 1:
for entry in tmp[1:]:
entry = string.strip(
string.replace(gutils.trim(entry, '>', '<'), '\n', ''))
if entry:
self.cameraman = self.cameraman + entry + ', '
if self.cameraman:
self.cameraman = self.cameraman[:-2]
def _find_actor(self, type, delimiter):
elements = string.split(self.castpage, '<div class="linkblu"')
result = ''
i = 1
while i < len(elements):
actorandrole = gutils.after(gutils.trim(elements[i], '<div', '</div>'), '>')
if string.find(actorandrole, type) > 0:
result = result + gutils.before(actorandrole, '</a>') + delimiter
i += 1
if result:
result = result[:-len(delimiter)]
result = re.sub('[\n\r\t ]+', ' ', result)
return result
def get_notes(self):
self.notes = ""
tmp_notes = re.sub(
'^[ \t]+', '',
gutils.strip_tags(
re.sub(
'(<br>|<br />)', '\r\n',
re.sub(
'[\r\n]+', '',
re.sub(
'[ \t][ \t\r\n]+', ' ',
gutils.trim(self.page, 'Bildformat(e)',
'</TR>'))))))
if (tmp_notes != ""):
self.notes = self.notes + "Bildformat(e):\n" + tmp_notes + "\n"
tmp_notes = re.sub(
'^[ \t]+', '',
gutils.strip_tags(
re.sub(
'(<br>|<br />)', '\r\n',
re.sub(
'[\r\n]+', '',
re.sub('[ \t][ \t\r\n]+', ' ',
gutils.trim(self.page, 'Tonformat(e)',
'</TR>'))))))
if (tmp_notes != ""):
self.notes = self.notes + "Tonformat(e):\n" + tmp_notes + "\n\n"
tmp_notes = re.sub(
'^[ \t]+', '',
gutils.strip_tags(
re.sub(
'(<br>|<br />)', '\r\n',
re.sub(
'[\r\n]+', '',
re.sub('[ \t][ \t\r\n]+', ' ',
gutils.trim(self.page, 'Untertitel',
'</TR>'))))))
if (tmp_notes != ""):
self.notes = self.notes + "Untertitel:" + tmp_notes + "\n\n"
def search(self, parent_window):
if not self.open_search(parent_window):
return None
tmp_page = gutils.trim(self.page, 'Titres Populaires', '</table>')
if not tmp_page:
has_results = re.search(
'[(]Affichant [1-9][0-9]* Résultats[)]', self.page)
if not has_results:
# nothing or one result found, try another url which looks deeper in the imdb database
# example: Adventures of Falcon -> one result, jumps directly to the movie page
# which isn't supported by this plugin
self.url = 'http://www.imdb.fr/find?more=tt&q='
if not self.open_search(parent_window):
return None
self.page = gutils.trim(self.page, '(Affichant',
'>Suggestions pour améliorer')
else:
self.page = tmp_page
self.page = self.page.decode('iso-8859-1')
# correction of all &#xxx entities
self.page = gutils.convert_entities(self.page)
return self.page
def get_searches(self):
elements = re.split('(?:href=["]*filmanzeige[.]php[?]filmid=)',
self.page)
elements[0] = ''
for element in elements:
if element <> '':
idmatch = re.search('([>]|["])', element)
if idmatch:
self.ids.append(element[:idmatch.end() - 1])
# I don't know what <wbr> means but it breaks the result list
element = string.replace(element, '<wbr>', '')
element = string.replace(element, '<wbr />', '')
# line breaks sometimes within the title
element = string.replace(element, '<wbr>', '')
element = string.replace(element, '<wbr />', '')
self.titles.append(
string.replace(
gutils.trim(element, '>', '<') + ' (' +
gutils.trim(gutils.after(element, '<td>'), '<td>',
'</td>') + ', ' +
gutils.trim(gutils.after(element, '</a>'), '<td>',
'</td>') + ')', '\n', ' - '))
def get_searches(self):
# Try to find both id and film title for each search result
elements = string.split(self.page, "<li>")
self.number_results = elements[-1]
if (elements[0] != ''):
for element in elements:
id = gutils.trim(element, "?codice=", "\">")
if id <> '':
self.ids.append(id)
title = self.capwords(
gutils.convert_entities(
gutils.trim(element, "<b>", "</b>")))
year = re.search('([[][0-9]{4}[]])', element)
if year:
year = year.group(0)
if year:
self.titles.append(title + ' ' + year)
else:
self.titles.append(title)
else:
self.number_results = 0
def get_screenplay(self):
# Find the screenplay
self.screenplay = gutils.trim(
self.page, '>Sceneggiatura</font></td>',
'<td class="bd_scheda_td"><font class="fontViolaB">Fotografia</font></td>'
)
# beautification
self.screenplay = string.replace(self.screenplay, '<a href',
',<a href')
self.screenplay = gutils.clean(self.screenplay)
self.screenplay = self.screenplay[1:]
self.screenplay = re.sub('[ ]*,', ', ', self.screenplay)
self.screenplay = re.sub('[ ]+', ' ', self.screenplay)
def get_cameraman(self):
self.cameraman = ''
tmp = gutils.regextrim(gutils.trim(self.page, 'id="person-collection"', '</section>'), 'Kamera[^<]*[<][/]h3[>]', '<h3')
tmpelements = re.split('href="', tmp)
delimiter = ''
for index in range(1, len(tmpelements), 1):
tmpelement = gutils.before(gutils.after(gutils.after(tmpelements[index], '"'), '>'), '<')
tmpelement = re.sub('<small[^>]*>[^<]*</small>', '', tmpelement)
tmpelement = gutils.strip_tags(tmpelement)
tmpelement = string.replace(tmpelement, '\n', '')
tmpelement = re.sub('[ \t]+', ' ', tmpelement)
self.cameraman = self.cameraman + tmpelement + delimiter
delimiter = ', '
def get_o_title(self):
self.o_title = gutils.clean(
gutils.after(
gutils.regextrim(self.page, 'class="text_ergebniss_faz_3"',
'[ \t]+[(]Originaltitel[)]'), '</a>'))
p1 = string.rfind(self.o_title, ',')
if p1 > 0:
self.o_title = self.o_title[p1 + 1:]
self.o_title = string.capwords(self.o_title)
if self.o_title == '':
self.o_title = gutils.after(
gutils.trim(self.page, 'class="text_ergebniss_faz_3"', '</a>'),
'>')
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):
if self.page is None: # movie page
self.ids.append(self.url)
self.titles.append(gutils.convert_entities(self.title))
elif self.page is False: # no movie found
self.number_results = 0
else: # multiple matches
elements = self.page.split('<li ')
self.number_results = elements[-1]
if elements != '':
for element in elements:
if (element == ''):
continue
element = gutils.after(element, 'href="')
self.ids.append('http://' + plugin_url_other +
gutils.before(element, '"'))
element_title = gutils.trim(element, '">', '</a>')
element_title = element_title.replace('\t', '')
element = gutils.after(element,
'class=searchResultDetails')
element_year = gutils.trim(element, '>', '|')
element_year = element_year.replace(" ", '')
element_year = gutils.strip_tags(element_year)
element_country = ''
pos_country = element.find('countryIds')
if pos_country != -1:
element_country = gutils.trim(element[pos_country:],
'">', '</a>')
element = element_title.strip()
if element_year:
element += ' (' + element_year.strip() + ')'
if element_country:
element += ' - ' + element_country.strip()
element = gutils.convert_entities(element)
element = gutils.strip_tags(element)
self.titles.append(element)
else:
self.number_results = 0
def search(self, parent_window):
if not self.open_search(parent_window):
return None
tmp_page = gutils.trim(self.page, 'Here are the', '</TABLE>')
if not tmp_page:
has_results = re.match('[(]Displaying [1-9][0-7]* Result[s]*[)]',
self.page)
if not has_results:
# nothing or one result found, try another url which looks deeper in the imdb database
# example: Adventures of Falcon -> one result, jumps directly to the movie page
# which isn't supported by this plugin
self.url = 'http://www.imdb.com/find?more=tt;q='
if not self.open_search(parent_window):
return None
self.page = gutils.trim(
self.page, '(Displaying',
'>Suggestions For Improving Your Results<')
else:
self.page = tmp_page
self.page = self.page.decode('iso-8859-1')
# correction of all &#xxx entities
self.page = gutils.convert_entities(self.page)
return self.page
def search(self, parent_window):
if not self.open_search(parent_window):
return None
tmp_page = gutils.trim(self.page, 'Titoli popolari', '</table>')
if not tmp_page:
has_results = re.match(
'[(]Visualizza [1-9][0-7]* risultat[io]*[)]', self.page)
if not has_results:
# nothing or one result found, try another url which looks deeper in the imdb database
# example: Adventures of Falcon -> one result, jumps directly to the movie page
# which isn't supported by this plugin
self.url = 'http://italian.imdb.com/find?more=tt;q='
if not self.open_search(parent_window):
return None
self.page = gutils.trim(
self.page, '(Visualizza',
'>Suggerimenti per migliorare i tuoi risultati<')
else:
self.page = tmp_page
self.page = self.page.decode('iso-8859-1')
# correction of all &#xxx entities
self.page = gutils.convert_entities(self.page)
return self.page
def get_cast(self): # OK v1.5
# Find the actors. Try to make it comma separated.
self.cast = gutils.trim(
self.page, '>Attori</font></td>',
'<td class="bd_scheda_td"><font class="fontViolaB">Soggetto</font></td>'
)
# beautification
self.cast = string.replace(self.cast, '<a href', '---<a href')
self.cast = gutils.clean(self.cast)
self.cast = self.cast[3:]
self.cast = re.sub('[ ]*---', '\n', self.cast)
self.cast = re.sub('[ ]+', ' ', self.cast)
self.cast = string.replace(self.cast, '( ', '(')
self.cast = string.replace(self.cast, ' )', ')')
