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_o_title(self):
self.o_title = gutils.trim(self.tmp_page, 'span class="standardsmall">(', ')<')
if self.o_title == '':
if self.url_type == 'V':
self.o_title = gutils.after(self.regextrim(self.tmp_page, 'headline2"[^>]*>[ \t\r\n]*<a href="/videofilm', '</a>'), '>')
else:
self.o_title = gutils.after(self.regextrim(self.tmp_page, 'headline2"[^>]*>[ \t\r\n]*<a href="/kinofilm', '</a>'), '>')
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_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):
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_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_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 = string.split(self.page, '<li ')
self.number_results = elements[-1]
if (elements[0] <> ''):
for element in elements:
element = gutils.after(element, '<a href="')
self.ids.append('http://' + plugin_server + gutils.before(element, '"'))
element_title = gutils.trim(element, 'class="searchResultTitle"', '</a>')
element_title = gutils.after(element_title, '">')
element_title = string.replace(element_title, "\t", '')
element = gutils.after(element, 'class="searchResultDetails"')
element_year = gutils.trim(element, '>', '|')
element_year = string.replace(element_year, " ", '')
element_year = gutils.strip_tags(element_year)
element_country = gutils.trim(element, '">', '</a>')
element = string.strip(element_title)
if (element_year <> ''):
element = element + ' (' + string.strip(element_year) + ')'
if (element_country <> ''):
element = element + ' - ' + string.strip(element_country)
element = gutils.convert_entities(element)
element = gutils.strip_tags(element)
self.titles.append(element)
else:
self.number_results = 0
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 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 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_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_plot(self):
self.plot = gutils.trim(self.page, u'<b>GÉNERO Y CRÍTICA</b>', '</tr>')
if self.plot == '':
self.plot = gutils.trim(self.page, '<b>GÉNERO Y CRÍTICA</b>', '</tr>')
self.plot = gutils.after(self.plot, '<td valign="top">')
self.plot = gutils.after(self.plot, 'SINOPSIS:')
self.plot = string.replace(self.plot, ' (FILMAFFINITY)', '')
self.plot = string.replace(self.plot, '(FILMAFFINITY)', '')
def get_searches(self): elements = string.split(self.page,'class="dvdtitle">') elements[0] = '' for element in elements: element = gutils.trim( element, '<a href="', '<br/>' ) if element != '': self.ids.append( gutils.after( gutils.trim( element, 'movie/','/main') , '/' ) ) self.titles.append( string.replace( gutils.after( element, '">' ), '</a></span>', '' ) )
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_title(self):
if self.url_type == "V":
self.title = gutils.after(
self.regextrim(self.tmp_page, 'headline2"[^>]*>[ \t\r\n]*<a href="/videofilm', "</a>"), ">"
)
else:
self.title = gutils.after(
self.regextrim(self.tmp_page, 'headline2"[^>]*>[ \t\r\n]*<a href="/kinofilm', "</a>"), ">"
)
def get_searches(self): elements = string.split(self.page, "<!--") elements[0] = '' for element in elements: if element <> '': self.ids.append(gutils.trim(element, "filmid=", ">")) self.titles.append(gutils.trim( gutils.after(element, "filmid="), ">", "<") + " - " + gutils.trim(gutils.after(element, "</a>"), "<td>", "</td>") + " - " + gutils.trim(gutils.after(gutils.after(element, "<td>"), "<td>"), "<td>", "</td>"))
def get_plot(self):
self.plot = gutils.trim(self.page,'<h2 id="o-filmie-header" class="replace">','</div>')
self.plot = gutils.after(self.plot, '<p>')
url = gutils.trim(self.plot,"\t...","</a>")
url = gutils.trim(url, 'href="','"')
self.plot = gutils.strip_tags(self.plot)
if url != '':
plot_page = self.open_page(url=url)
self.plot = gutils.trim(plot_page, '<div class="filmContent">', '</ul>')
self.plot = gutils.after(self.plot, 'zgłoś poprawkę')
def get_o_title(self):
self.o_title = gutils.trim(self.tmp_page, 'span class="standardsmall">(', ")<")
if self.o_title == "":
if self.url_type == "V":
self.o_title = gutils.after(
self.regextrim(self.tmp_page, 'headline2"[^>]*>[ \t\r\n]*<a href="/videofilm', "</a>"), ">"
)
else:
self.o_title = gutils.after(
self.regextrim(self.tmp_page, 'headline2"[^>]*>[ \t\r\n]*<a href="/kinofilm', "</a>"), ">"
)
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])
self.titles.append(gutils.trim(element, '>', '<') + ' - ' +
gutils.trim(gutils.after(element, '</a>'), '<td>', '</td>') + ' - ' +
gutils.trim(gutils.after(element, '<td>'), '<td>', '</td>'))
def get_searches(self):
elements = string.split(self.page, '<tr')
self.number_results = elements[-1]
if (elements[0]<>''):
for element in elements:
self.ids.append(gutils.trim(element, 'IDfilm=', '"'))
title = gutils.convert_entities(gutils.strip_tags(gutils.after(gutils.trim(element, 'IDfilm=', '</a>'), '>')))
year = gutils.after(gutils.trim(element, '<td valign="bottom"', '</td>'), '>')
self.titles.append(title + ' (' + year + ')')
else:
self.number_results = 0
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_plot(self): # little steps to perfect plot (I hope ... it's a terrible structured content ... ) self.plot = gutils.trim(self.tmp_page, '<span style="line-height:', '</spa') if self.plot == '': self.plot = gutils.trim(self.tmp_page,"Kurzinfo", "</td></tr><tr><td></td>") if (self.plot == ''): self.plot = gutils.trim(self.tmp_page,"Kurzinfo", '<script ') self.plot = gutils.after(self.plot, '>') while len(self.plot) and string.find(self.plot, '</A>') > -1: self.plot = gutils.after(self.plot, '</A>'); self.plot = gutils.after(gutils.after(self.plot, '</table>'), '>') else: self.plot = gutils.after(self.plot, '>')
def get_plot(self):
if gutils.trim(self.url, "typ=", "&") <> "film":
self.url = self.url_to_use + "typ=film&nr=" + str(self.movie_id)
self.open_page(self.parent_window)
self.tmp_page = gutils.trim(self.page, "<!-- PRINT-CONTENT-START-->", "<!-- PRINT-CONTENT-ENDE-->")
if self.url_type == "V":
self.plot = gutils.after(self.tmp_page, 'IMG SRC="/pix/MBBILDER/VIDEO')
self.plot = gutils.trim(self.plot, "</TABLE>", "</TD>")
else:
self.plot = gutils.after(self.tmp_page, 'IMG SRC="/pix/MBBILDER/KINOPLAK')
self.plot = gutils.trim(self.plot, "</TABLE>", "</TD>")
if self.plot == "":
self.plot = gutils.trim(self.tmp_page, 'BORDER="0" align="left" ><TR><TD>', "</TD>")
def get_searches(self):
elements = string.split(self.page,"\n <a href=\"filmsuche.cfm?wert=")
if (elements[0]<>''):
elements[0] = ''
for element in elements:
if (element <> ''):
self.ids.append(gutils.before(element,"&"))
self.titles.append(gutils.strip_tags(
gutils.trim(element,">","</a>") + " (" +
string.capwords(gutils.trim(element, "\n ", "(Orginaltitel)")) + ", " +
gutils.after(gutils.trim(element, "sucheNach=produktionsland", "</a>"), ">") + ", " +
gutils.after(gutils.trim(element, "sucheNach=produktionsjahr", "</a>"), ">") +
")"))
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):
elements = string.split(self.page, '<div class="text_ergebniss_faz_3"')
i = 1
while i < len(elements):
element = elements[i]
i = i + 1
self.ids.append(gutils.trim(element, 'filmlexikon/?wert=', '&'))
self.titles.append(string.strip(gutils.clean(
gutils.trim(element, '>', '</a>') + ' (' +
string.capwords(gutils.trim(element, '</a>', '(Originaltitel)')) + ', ' +
gutils.after(gutils.trim(element, 'sucheNach=produktionsland', '</a>'), '>') + ', ' +
gutils.after(gutils.trim(element, 'sucheNach=produktionsjahr', '</a>'), '>') +
')')))
def get_plot(self): if (gutils.trim(self.url, "typ=", "&") <> "film"): self.url = self.url_to_use + "typ=film&nr=" + str(self.movie_id) self.open_page(self.parent_window) self.tmp_page = gutils.trim(self.page, "<!-- PRINT-CONTENT-START-->", "<!-- PRINT-CONTENT-ENDE-->") if (self.url_type == "V"): self.plot = gutils.after(self.tmp_page,"IMG SRC=\"/pix/MBBILDER/VIDEO") self.plot = gutils.trim(self.plot,"</TABLE>", "</TD>") else: self.plot = gutils.after(self.tmp_page,"IMG SRC=\"/pix/MBBILDER/KINOPLAK") self.plot = gutils.trim(self.plot,"</TABLE>", "</TD>") if self.plot == '': self.plot = gutils.trim(self.tmp_page, "BORDER=\"0\" align=\"left\" ><TR><TD>", "</TD>")
def get_searches(self):
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 element in elements[:-1]:
self.ids.append(gutils.trim(element, '<b><a href="/es/film','.html'))
title = gutils.after(element, '<b><a href="/es/film')
self.titles.append(gutils.strip_tags(gutils.convert_entities(gutils.after(title, '>'))))
def get_studio(self):
self.studio = ''
tmp = gutils.trim(self.page, '<div class="description">', '</div>')
if tmp:
tmp = gutils.trim(tmp, 'Regie:', '</p>')
if tmp:
self.studio = string.replace(gutils.after(tmp, '<br/>'), 'Verleih: ', '')
if not self.studio:
self.studio = gutils.trim(self.page, 'Verleih: ', '<')
if not self.studio and self.videopage:
tmp = gutils.trim(self.videopage, '<div class="description">', '</div>')
if tmp:
tmp = gutils.trim(tmp, 'Regie:', '</p>')
if tmp:
self.studio = string.replace(gutils.after(tmp, '<br/>'), 'Verleih: ', '')
def get_plot(self):
if gutils.trim(self.url, "typ=", "&") <> "film":
self.url = self.url_to_use + "typ=film&nr=" + str(self.movie_id)
self.open_page(self.parent_window)
self.tmp_page = gutils.trim(self.page, "<!-- PRINT-CONTENT-START-->", "<!-- PRINT-CONTENT-ENDE-->")
# little steps to perfect plot (I hope ... it's a terrible structured content ... )
self.plot = gutils.trim(self.tmp_page, "Kurzinfo", "</TD></TR><tr><td></td></tr><TR>")
if self.plot == "":
self.plot = gutils.trim(self.tmp_page, "Kurzinfo", '<script language="JavaScript">')
self.plot = gutils.after(self.plot, "Fotoshow</A>")
self.plot = gutils.after(self.plot, "Filmpreise</A>")
self.plot = gutils.after(self.plot, "Games zum Film</A>")
self.plot = gutils.after(self.plot, " Crew</A>")
self.plot = gutils.before(self.plot, "FOTOSHOW</SPAN>")
self.plot = gutils.after(self.plot, "</TABLE>")
def get_searches(self):
elements = string.split(self.page,'class="text_ergebniss_titel"')
i = 0
while i < len(elements) - 1:
id_part = elements[i]
i = i + 1
text_part = elements[i]
i = i + 1
self.ids.append(gutils.trim(id_part, 'filmsuche.cfm?wert=', '&'))
self.titles.append(gutils.strip_tags(
gutils.trim(text_part, '>', '</a>') + ' (' +
string.capwords(gutils.trim(text_part, '</a>', '(Originaltitel)')) + ', ' +
gutils.after(gutils.trim(text_part, 'sucheNach=produktionsland', '</a>'), '>') + ', ' +
gutils.after(gutils.trim(text_part, 'sucheNach=produktionsjahr', '</a>'), '>') +
')'))
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_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_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_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 search(self, parent_window):
if not self.open_search(parent_window):
return None
self.page = gutils.trim(self.page, '>Wynik wyszukiwania<',
'<TABLE border=0 cellpadding=0')
self.page = gutils.after(self.page, '</SPAN></DIV><BR>')
return self.page
def get_cast(self):
self.cast = gutils.trim(self.cast_page, '<h2>OBSADA:</h2>', '<div class="b')
self.cast = gutils.after(self.cast, '<div class="clr"></div>')
self.cast = string.replace(self.cast, '\t', '')
self.cast = gutils.strip_tags(self.cast)
self.cast = string.replace(self.cast, '\n\n ', _(' as '))
self.cast = string.replace(self.cast, "%s\n" % _(' as '), "\n")
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_site(self):
"""Find the film's imdb details page"""
self.site = gutils.trim(self.page, \
"/imagens/bf_siteoficial.gif' WIDTH=89 HEIGHT=18 BORDER=0 ALT=''>", \
"' TARGET=_blank><IMG SRC='/imagens/bf_imdb.gif'")
self.site = gutils.after(self.site, "<A HREF='")
self.site = string.replace(self.site, "'", "")
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_site(self): """Find the film's imdb details page""" self.site = gutils.trim(self.page, \ "/imagens/bf_siteoficial.gif' WIDTH=89 HEIGHT=18 BORDER=0 ALT=''>", \ "' TARGET=_blank><IMG SRC='/imagens/bf_imdb.gif'") self.site = gutils.after(self.site, "<A HREF='") self.site = string.replace(self.site, "'", "")
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_year(self):
self.year = gutils.trim(self.page, '<a href="/year/', '</a>')
self.year = gutils.after(self.year, '>')
if not self.year:
tmp = gutils.trim(self.page, '<title>', '</title>')
tmp = re.search('([0-9]{4})[)]', tmp)
if tmp:
self.year = tmp.group(0)
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_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_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 initialize(self):
try:
self.jsondata = json.loads(
gutils.trim(gutils.after(self.page, '<body'),
'<script type="application/ld+json">',
'</script>'))
except:
self.jsondata = {}
def get_o_title(self):
self.o_title = gutils.trim(self.page,
u'<th>TÍTULO ORIGINAL</th>',
'</strong></td>')
self.o_title = gutils.after(self.o_title, '<strong>')
self.o_title = re.sub('[ ]+', ' ', self.o_title)
self.o_title = re.sub('([(]Serie de TV[)]|[(]TV[)]|[(]TV Series[)])',
'', self.o_title)
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_plot(self):
self.plot = gutils.after(gutils.trim(self.page, 'class="movie-plot-synopsis"', '</section>'), '>')
start = string.find(self.plot, '<script')
end = string.find(self.plot, '</script>', start)
while start > -1 and end > -1:
self.plot = self.plot[:start]+self.plot[end:]
start = string.find(self.plot, '<script')
end = string.find(self.plot, '</script>', start)
self.plot = string.replace(self.plot, '\n', '')
def get_studio(self):
self.studio = gutils.trim(self.detail_page, 'alt="Produktion"', '<img')
if self.studio == '':
self.studio = gutils.trim(self.detail_page, 'alt="Produktion"',
'</TABLE>')
self.studio = gutils.after(self.studio, '>')
self.studio = self.studio.replace('<tr>', ', ')
self.studio = gutils.strip_tags(self.studio)
self.studio = re.sub('((^, )|(, $))', '', self.studio)
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_rating(self):
self.rating = gutils.after(gutils.trim(self.page,">Note: <","</span>"), '>')
if self.rating == '':
self.rating = "0"
if self.rating:
try:
self.rating = round(float(self.rating), 0)
except Exception, e:
self.rating = 0
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_cast(self):
self.cast = ''
tmp = self.page.split('itemprop="actor"')
for element in tmp[1:]:
actor = gutils.trim(element, '>', '</span>')
role = gutils.after(gutils.trim(element, u'Rôle', '</span>'), ': ')
if role:
self.cast = self.cast + actor + _(' as ') + role + '\n'
else:
self.cast = self.cast + actor + '\n'
def get_searches(self):
elements = string.split(self.page, 'class="product-name"')
i = 1
while i < len(elements):
element = elements[i]
i = i + 1
self.ids.append(gutils.trim(element, 'href="', '"'))
self.titles.append(
re.sub('Zweitausendeins Edition.*', '',
gutils.trim(gutils.after(element, '>'), '>', '<')))
def get_rating(self):
"""Find the film's rating. From 0 to 10.
Convert if needed when assigning."""
tmp_rating = gutils.trim(self.page, "<br><b>Cota", " (")
tmp_rating = gutils.after(tmp_rating, "</b>")
if tmp_rating <> "":
tmp_rating = string.replace(tmp_rating, ',', '.')
self.rating = str(float(string.strip(tmp_rating)))
else:
self.rating = ""
