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_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_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_title(self):
self.url = self.url.replace(plugin_server, plugin_url)
self.title = gutils.trim(self.page, '<title>', '</title>')
if self.title.find('(') > -1:
self.title = gutils.before(self.title, '(')
if self.title.find('/') > -1:
self.title = gutils.before(self.title, '/')
def get_image(self):
self.image_url = string.replace(
string.replace(gutils.trim(self.page, '"picture":', ','), '"', ''),
'\\', '')
if not self.image_url:
tmpdata = gutils.regextrim(self.page, '<div class="cover-area">',
'</div>')
if tmpdata:
# video page
tmpdata = re.search(
'(http[:][/][/][^/]+[/]flbilder[/][^"\']+)', tmpdata)
if tmpdata:
self.image_url = tmpdata.group(1)
else:
# kino page
tmpdata = gutils.before(self.page,
'<span style="line-height: 15px;">')
if tmpdata:
tmpparts = re.split('http://images.kino.de/s/', tmpdata)
if len(tmpparts) > 2:
self.image_url = 'http://images.kino.de/s/' + gutils.before(
tmpparts[2], '"')
elif len(tmpparts) > 1:
self.image_url = 'http://images.kino.de/s/' + gutils.before(
tmpparts[1], '"')
if not self.image_url and self.videopage:
tmpdata = gutils.regextrim(self.videopage,
'<div class="cover-area">',
'</div>')
if tmpdata:
# video page
tmpdata = re.search(
'(http[:][/][/][^/]+[/]flbilder[/][^"\']+)', tmpdata)
if tmpdata:
self.image_url = tmpdata.group(1)
def get_image(self):
self.image_url = string.replace(string.replace(gutils.trim(self.page, '"picture":', ','), '"', ''), '\\', '')
if not self.image_url:
tmpdata = gutils.regextrim(self.page, '<div class="cover-area">', '</div>')
if tmpdata:
# video page
tmpdata = re.search('(http[:][/][/][^/]+[/]flbilder[/][^"\']+)', tmpdata)
if tmpdata:
self.image_url = tmpdata.group(1)
else:
# kino page
tmpdata = gutils.before(self.page, '<span style="line-height: 15px;">')
if tmpdata:
tmpparts = re.split('http://images.kino.de/s/', tmpdata)
if len(tmpparts) > 2:
self.image_url = 'http://images.kino.de/s/' + gutils.before(tmpparts[2], '"')
elif len(tmpparts) > 1:
self.image_url = 'http://images.kino.de/s/' + gutils.before(tmpparts[1], '"')
if not self.image_url and self.videopage:
tmpdata = gutils.regextrim(self.videopage, '<div class="cover-area">', '</div>')
if tmpdata:
# video page
tmpdata = re.search('(http[:][/][/][^/]+[/]flbilder[/][^"\']+)', tmpdata)
if tmpdata:
self.image_url = tmpdata.group(1)
def get_title(self):
self.url = self.url.replace(plugin_server, plugin_url)
self.title = gutils.trim(self.page, '<title>', '</title>')
if self.title.find('(') > -1:
self.title = gutils.before(self.title, '(')
if self.title.find('/') > -1:
self.title = gutils.before(self.title, '/')
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_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 get_searches(self):
elements_tmp = string.split(self.page,"kinofilm.php4")
if (elements_tmp[0]<>self.page):
elements = string.split(self.page,"headline3\"><A HREF=\"/kinofilm.php4?nr=")
if (elements[0]<>''):
elements[0] = ''
for element in elements:
if (element <> ''):
self.ids.append("K_" + gutils.before(element,"&"))
self.titles.append(gutils.strip_tags(
gutils.trim(element,">","</A>") + " " +
gutils.trim(element, "<span CLASS=\"standardsmall\"><br>", "</SPAN>") + " (" +
string.replace(
gutils.trim(element, "<span class=\"standardsmall\"><b>", "</span>"), "<b>", ", ")
+ ")"))
else:
elements_tmp2 = string.split(self.page, "videofilm.php4")
if (elements_tmp2[0]<>self.page):
elements = string.split(self.page,"headline3\"><A HREF=\"/videofilm.php4?nr=")
if (elements[0]<>''):
elements[0] = ''
for element in elements:
if (element <> ''):
self.ids.append("V_" + gutils.before(element,"&"))
self.titles.append(gutils.strip_tags(
gutils.trim(element,">","</A>") + " " +
gutils.trim(element, "<span CLASS=\"standardsmall\"><br>", "</SPAN>") + " (" +
string.replace(
gutils.trim(element, "<span class=\"standardsmall\"><b>", "</span>"), "<b>", ", ") + ")"))
def get_plot(self):
self.plot = gutils.before(gutils.after(gutils.trim(self.page, 'name="description"', '/>'), 'content="'), '"')
germanplotelements = string.split(self.plot_page, 'class="plotSummary"')
if len(germanplotelements) > 1:
self.plot = self.plot + '\n\n'
germanplotelements[0] = ''
for element in germanplotelements:
if element <> '':
self.plot = self.plot + gutils.strip_tags(gutils.before(gutils.after(element, '>'), '</a>')) + '\n\n'
if self.plot == '':
# nothing in german found, try original
self.plot = gutils.before(gutils.after(gutils.trim(self.imdb_page, 'name="description"', '/>'), 'content="'), '"')
elements = string.split(self.imdb_plot_page, 'class="plotSummary"')
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(gutils.after(element, '>'), '</a>')) + '\n\n'
plotlist = string.split(gutils.trim(self.plot_page, 'id="plot-summaries-content">', '</ul>'), '<li')
plotcompilation = ''
for listelement in plotlist:
if 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
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_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 initialize(self): self.tmp_page = gutils.before(self.page, 'kinode_navi1') self.url = self.url_to_use + string.replace(str(self.movie_id), '/', '/credits/') self.open_page(self.parent_window) self.tmp_creditspage = gutils.before(self.page, 'kinode_navi1') self.url = self.url_to_use + string.replace(str(self.movie_id), "/", "/features/") self.open_page(self.parent_window) self.tmp_dvdfeaturespage = gutils.before(self.page, 'kinode_navi1')
def get_director(self):
self.director = gutils.trim(self.page, '<BR>Re\xbfyseria: ', '<BR>')
if string.find(self.director, '-->') <> -1:
self.director = gutils.after(self.director, '-->')
self.director = gutils.before(self.director,"<!--")
else:
self.director = gutils.after(self.director, '<B>')
self.director = gutils.before(self.director, '</B>')
def get_image(self):
urls = re.split('<img[ \t]+src=[\'"]', gutils.trim(self.page, '<div class="poster">', '</div>'))
for url in urls[1:]:
url = gutils.before(url, '"')
url = gutils.before(url, '\'')
if string.find(url, '.jpg') >= 0:
self.image_url = url
break
def initialize(self):
self.tmp_page = gutils.before(self.page, "<!-- PRINT-CONTENT-ENDE-->")
self.url = self.url_to_use + string.replace(str(self.movie_id), "/", "/credits/")
self.open_page(self.parent_window)
self.tmp_creditspage = gutils.before(self.page, "<!-- PRINT-CONTENT-ENDE-->")
self.url = self.url_to_use + string.replace(str(self.movie_id), "/", "/features/")
self.open_page(self.parent_window)
self.tmp_dvdfeaturespage = gutils.before(self.page, "<!-- PRINT-CONTENT-ENDE-->")
def director(self): self.director = gutils.trim(self.page,"<BR>Re¿yseria: ","<BR>") if string.find(self.director,"-->") <> -1: self.director = gutils.after(self.director,"-->") self.director = gutils.before(self.director,"<!--") else: self.director = gutils.after(self.director,"<B>") self.director = gutils.before(self.director,"</B>")
def get_o_title(self):
self.url = self.url.replace(plugin_server, plugin_url)
self.o_title = gutils.trim(self.page, '<h2 class=origTitle>', '</h2>')
self.o_title = gutils.after(self.o_title, '</span>')
if self.o_title == '':
self.o_title = gutils.trim(self.page, '<title>', '</title>')
if self.o_title.find('(') > -1:
self.o_title = gutils.before(self.o_title, '(')
if self.o_title.find('/') > -1:
self.o_title = gutils.before(self.o_title, '/')
def get_o_title(self):
self.url = self.url.replace(plugin_server, plugin_url)
self.o_title = gutils.trim(self.page, '<h2 class=origTitle>', '</h2>')
self.o_title = gutils.after(self.o_title, '</span>')
if self.o_title == '':
self.o_title = gutils.trim(self.page, '<title>', '</title>')
if self.o_title.find('(') > -1:
self.o_title = gutils.before(self.o_title, '(')
if self.o_title.find('/') > -1:
self.o_title = gutils.before(self.o_title, '/')
def get_image(self):
self.image_url = ''
tmpdata = self.regextrim(self.tmp_page, '(PRINT[-]CONTENT[-]START|<td class="content">)', '(Dieser Film wurde |>FOTOSHOW<|>KRITIK<)')
tmpdatasplit = re.split('src="http://images.kino.de/flbilder', tmpdata)
if len(tmpdatasplit) > 2:
tmpdata = gutils.before(tmpdatasplit[2], '.jpg')
if tmpdata <> '':
self.image_url = 'http://images.kino.de/flbilder' + tmpdata + '.jpg'
elif len(tmpdatasplit) > 1:
tmpdata = gutils.before(tmpdatasplit[1], '.jpg')
if tmpdata <> '':
self.image_url = 'http://images.kino.de/flbilder' + tmpdata + '.jpg'
def get_searches(self):
elements = string.split(self.page, '<a href="/filmes/')
self.number_results = elements[-1]
if len(elements[0]):
for element in elements:
id = gutils.digits_only(gutils.before(element, '"'))
title = gutils.clean(re.sub('</div>.*', '', string.replace(gutils.before(gutils.after(element, '>'), '</small>'), '<small>', ' / ')))
if id and title and title[0] != '<':
self.ids.append(id)
self.titles.append(gutils.convert_entities(title))
else:
self.number_results = 0
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_searches(self):
elements1 = re.split('headline3"[^>]*>[ \t\r\n]*<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(
"Kino: "
+ 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"[^>]*>[ \t\r\n]*<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(
"Video: "
+ string.replace(
string.replace(
gutils.strip_tags(
gutils.trim(element, ">", "</a>")
+ " ("
+ string.replace(
gutils.trim(element, '<span class="standardsmall">', "</span>"), "<br />", " - "
)
+ ")"
),
"( - (",
"(",
),
"))",
")",
)
)
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_nextpage_url(self):
match = re.search('(siguientes >|siguientes >)', self.page)
if match:
start = string.rfind(self.page, '<a href="', 0, match.start())
if start >= 0:
return 'http://www.filmaffinity.com/es/' + gutils.before(self.page[start + 9:match.start()], '"')
return None
def search(self, parent_window):
if not self.open_search(parent_window):
return None
# used for looking for subpages
tmp_page = gutils.trim(self.page, 'class="pages"', '</div>')
elements = string.split(tmp_page, 'href="')
# first results
tmp_page = gutils.trim(self.page, 'class="category-products"',
'class="toolbar-bottom"')
# look for subpages
i = 1
while i < len(elements):
element = elements[i]
i = i + 1
p1 = string.find(element, 'title="Nächste"')
if p1 >= 0:
continue
element = gutils.before(element, '"')
if element:
self.title = ''
self.o_title = ''
self.url = element
if self.open_search(parent_window):
tmp_page2 = gutils.trim(self.page,
'class="category-products"',
'class="toolbar-bottom"')
tmp_page = tmp_page + tmp_page2
self.page = tmp_page
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 search(self, parent_window):
if not self.open_search(parent_window):
return None
# used for looking for subpages
tmp_page = gutils.trim(self.page, '<span class="trefferliste">',
'</span>')
elements = string.split(tmp_page, 'cp=')
# first results
tmp_page = gutils.after(
gutils.trim(self.page, 'Alle Treffer aus der Kategorie',
'<span class="trefferliste">'), "Titel:")
# look for subpages
for element in elements:
element = gutils.before(element, '"')
try:
tmp_element = int(element)
except:
tmp_element = 1
if tmp_element != 1:
self.url = 'http://www.zweitausendeins.de/filmlexikon/?sucheNach=Titel&cp=' + str(
tmp_element) + "&wert="
if self.open_search(parent_window):
tmp_page2 = gutils.trim(self.page,
'Alle Treffer aus der Kategorie',
'<span class="trefferliste">')
tmp_page = tmp_page + tmp_page2
self.page = tmp_page
return self.page
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_trailer(self):
self.trailer = ''
tmp = string.find(self.page, u'(trailers)')
if tmp >= 0:
index = string.rfind(self.page[:tmp], u'<a href="')
if index >= 0:
self.trailer = gutils.before(self.page[index + 9:], '"')
def get_o_site(self):
self.o_site = ''
tmp = string.find(self.page, u'(site oficial)')
if tmp >= 0:
index = string.rfind(self.page[:tmp], u'<a href="')
if index >= 0:
self.o_site = gutils.before(self.page[index + 9:], '"')
def search(self, parent_window):
if not self.open_search(parent_window):
return None
# used for looking for subpages
tmp_page = gutils.trim(self.page, '<li>Treffer', '</div>')
elements = string.split(tmp_page, 'cp=')
# first results
tmp_page = gutils.trim(self.page, '<ul class=\'film-liste\'>', '</ul>')
# look for subpages
for element in elements:
element = gutils.before(element, '\'')
try:
tmp_element = int(element)
except:
tmp_element = 1
if tmp_element != 1:
self.url = 'http://www.zweitausendeins.de/filmlexikon/?sucheNach=filmtitel&cp=' + str(
tmp_element) + "&wert="
if self.open_search(parent_window):
tmp_page2 = gutils.trim(self.page,
'<ul class=\'film-liste\'>',
'</ul>')
tmp_page = tmp_page + tmp_page2
self.page = tmp_page
return self.page
def get_o_site(self):
self.o_site = ''
offsindex = string.find(self.page, '>Official Site</a>')
if offsindex >= 0:
offsindex = string.rfind(self.page[:offsindex], 'href="')
if offsindex >= 0:
self.o_site = gutils.before(self.page[offsindex + 6:], '"')
def get_image(self):
tmp = re.search('pics[0-9]*.filmaffinity.com/', self.page)
if not tmp:
self.image_url = ''
else:
self.image_url = 'http://' + gutils.before(self.page[tmp.start():],
'"')
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 search(self, parent_window):
if not self.open_search(parent_window):
return None
# 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)
if 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 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_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_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 get_title(self):
self.title = gutils.trim(self.page, '<b>Tytu\xB3 polski:</b>', "\t\t</div><div")
if self.title == '':
self.title = gutils.before(self.page, '</h1>')
pos = string.find(self.title, '(')
if pos > -1:
self.title = self.title[:pos]
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 running_time(self):
self.running_time = gutils.trim(self.page,"<div class=\"sitem\">Czas trwania: <b>\n\t\t","\n</b>")
if self.running_time.find("?") != -1:
self.running_time = ''
else:
self.running_time = gutils.after(self.running_time, "×")
self.running_time = gutils.before(self.running_time, " min")
def get_image(self):
urls = re.split('<img[ \t]+src=[\'"]', self.page)
for index in range(1, len(urls), 1):
url = gutils.before(urls[index], '"')
if string.find(url, '.jpg') >= 0:
self.image_url = url
break
def get_searches(self):
elements = string.split(self.page, '<h4><a href="/film/fichefilm_gen_cfilm=')
if (elements[0]<>''):
for index in range(1, len(elements), 1):
element = elements[index]
self.ids.append(gutils.before(element, '.'))
self.titles.append(gutils.strip_tags(gutils.convert_entities(gutils.trim(element, '>', '</a>'))))
def get_title(self):
self.title = gutils.trim(self.page, u'<b>Tytuł polski:</b>',
"\t\t</div><div")
if self.title == '':
self.title = gutils.before(self.page, '</h1>')
pos = string.find(self.title, '(')
if pos > -1:
self.title = self.title[:pos]
def get_nextpage_url(self):
match = re.search('(siguientes >|siguientes >)', self.page)
if match:
start = string.rfind(self.page, '<a href="', 0, match.start())
if start >= 0:
return 'http://www.filmaffinity.com/es/' + gutils.before(
self.page[start + 9:match.start()], '"')
return None
def get_searches(self):
elements = string.split(self.page, '<a href="/filmes/')
self.number_results = elements[-1]
if len(elements[0]):
for element in elements:
id = gutils.digits_only(gutils.before(element, '"'))
title = gutils.clean(
re.sub(
'</div>.*', '',
string.replace(
gutils.before(gutils.after(element, '>'),
'</small>'), '<small>', ' / ')))
if id and title and title[0] != '<':
self.ids.append(id)
self.titles.append(gutils.convert_entities(title))
else:
self.number_results = 0
def get_director(self):
self.director = gutils.trim(self.cast_page,'>Directed by', '</table>')
tmpelements = re.split('href="', self.director)
delimiter = ''
self.director = ''
for index in range(1, len(tmpelements), 1):
tmpelement = gutils.before(gutils.after(tmpelements[index], '>'), '<')
self.director = self.director + tmpelement + delimiter
delimiter =', '
def get_title(self):
self.title = gutils.trim(self.page, '<h1>', '<span')
elements = string.split(gutils.regextrim(self.page, '<h5>(Alternativ|Auch bekannt als):', '</div>'), '<i class="transl"')
if len(elements) > 1:
for element in elements:
tmp = gutils.before(gutils.trim(element, '>', '[de]'), '(')
if tmp <> '':
self.title = tmp
break
def search(self, parent_window):
if not self.open_search(parent_window):
return None
tmp = string.find(self.page, '<h1>Wyniki wyszukiwania dla')
if tmp == -1: # already a movie page
self.page = ''
else: # multiple matches
self.page = gutils.before(self.page[tmp:], '>Mapa strony</h3>')
return self.page
def get_runtime(self):
self.runtime = gutils.trim(
self.page, "<div class=\"sitem\">Czas trwania: <b>\n\t\t",
'\n</b>')
if self.runtime.find('?') != -1:
self.runtime = ''
else:
self.runtime = gutils.after(self.runtime, '×')
self.runtime = gutils.before(self.runtime, ' min')
def get_runtime(self):
self.runtime = ''
tmp = gutils.strip_tags(gutils.trim(self.page, 'Length', '<br'))
#1 hrs. 59 mins.
try:
self.runtime = int(gutils.before(tmp, 'hrs')) * 60 + int(
gutils.trim(tmp, '.', 'mins'))
except:
self.runtime = ''
def get_searches(self):
elements = string.split(self.page,
"href='ficha_filme_if.cdv?numero_filme=")
for element in elements[1:]:
id = gutils.before(element, "'")
title = gutils.trim(element, '>', '</a>')
if id and title:
self.ids.append(id)
self.titles.append(title)
