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_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_o_title(self):
self.o_title = gutils.regextrim(self.page, 'class="title-extra"[^>]*>', '<')
if not self.o_title:
self.o_title = gutils.regextrim(self.page, '<h1>', '([ ]|[&][#][0-9]+[;])<span')
if not self.o_title:
self.o_title = re.sub(' [(].*', '', gutils.trim(self.page, '<title>', '</title>'))
self.o_title = re.sub('"', '', self.o_title)
def get_o_title(self):
self.o_title = gutils.regextrim(self.page, 'class="title-extra"[^>]*>', '<')
if not self.o_title:
self.o_title = gutils.regextrim(self.page, '<h1>', '([ ]|[&][#][0-9]+[;])<span')
if not self.o_title:
self.o_title = re.sub(' [(].*', '', gutils.trim(self.page, '<title>', '</title>'))
self.o_title = re.sub('"', '', self.o_title)
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_o_title(self):
self.o_title = gutils.regextrim(self.page, 'class="title-extra"[^>]*>', "<")
if not self.o_title:
self.o_title = gutils.regextrim(self.page, "<h1>", "([ ]|[&][#][0-9]+[;])<span")
if not self.o_title:
self.o_title = re.sub(" [(].*", "", gutils.trim(self.page, "<title>", "</title>"))
self.o_title = re.sub('"', "", self.o_title)
def get_country(self):
self.country = gutils.regextrim(self.tmp_page, 'span class="standardsmall"[^>]*><strong>((DVD|VHS|Laser Disc|Video CD|Blue-ray Disc)</strong>[ \t]-[ \t]<strong>)*', '</span>')
if self.country <> None:
self.country = gutils.regextrim(self.country, '-[ \t]<strong>', '</strong>')
self.country = re.sub('[0-9]+$', '', self.country)
else:
self.country = ''
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(gutils.regextrim(self.tmp_page, 'headline2"[^>]*>[ \t\r\n]*<a href="/videofilm', '</a>'), '>')
else:
self.o_title = gutils.after(gutils.regextrim(self.tmp_page, 'headline2"[^>]*>[ \t\r\n]*<a href="/kinofilm', '</a>'), '>')
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):
tmp = gutils.regextrim(self.page, 'plakat.php[?]', '["\']')
if tmp:
page_image = self.open_page(url='http://www.filmdb.de/plakat.php?' + tmp)
tmp = gutils.regextrim(self.page, 'bilder.filmdb.de', '["\']')
if tmp:
self.image_url = 'http://bilder.filmdb.de' + tmp
def get_classification(self):
self.classification = string.replace(
gutils.trim(self.page, '"fsk":', ','), '"', '')
if not self.classification:
self.classification = gutils.regextrim(self.page, 'FSK: ', '<')
if not self.classification and self.videopage:
self.classification = gutils.regextrim(self.videopage, 'FSK: ',
'<')
def get_image(self):
tmp = gutils.regextrim(self.page, 'plakat.php[?]', '["\']')
if tmp:
page_image = self.open_page(
url='http://www.filmdb.de/plakat.php?' + tmp)
tmp = gutils.regextrim(self.page, 'bilder.filmdb.de', '["\']')
if tmp:
self.image_url = 'http://bilder.filmdb.de' + tmp
def get_notes(self):
self.notes = ''
critica = gutils.clean(string.replace(gutils.regextrim(self.page, 'Critica</font>', "(</td>|\n|Note<)"), '<br>', '\n'))
if critica:
self.notes = 'Critica:\n\n' + critica + '\n\n'
note = gutils.clean(string.replace(gutils.regextrim(self.page, 'Note</font>', "(</td>|\n|Critica<)"), '<br>', '--BR--'))
if note:
# string.capwords removes line breaks, preventing them with placeholder --BR--
note = self.capwords(note)
self.notes = self.notes + 'Note:\n\n' + string.replace(note, '--br--', '\n')
def get_classification(self):
# until we can find a way to locate the user, we have to use the US-classification
self.classification = gutils.trim(self.page, '<meta itemprop="contentRating" content="', '"')
if not self.classification:
classificationList = gutils.regextrim(self.cert_page,'id="certifications-list"','<\/ul>')
if classificationList:
self.classification = gutils.regextrim(classificationList,'>United States:','<')
else: # the old way
self.classification = gutils.trim(self.cert_page, '>Certification:<', '</div>')
self.classification = gutils.trim(self.classification, '>USA:', '<')
def get_o_title(self):
self.o_title = gutils.regextrim(self.page, '(<p>Originaltitel[:] |Originaltitel<[^>]+>)', '(</tr>|</p>)')
if not self.o_title:
self.o_title = gutils.trim(self.page, '<h1(', ')')
if not self.o_title:
self.o_title = gutils.trim(self.page, '<div class="teaser">', '</')
if not self.o_title:
if self.videopage:
self.o_title = gutils.trim(self.videopage, '<p>Originaltitel: ', '</p>')
if not self.o_title:
self.o_title = gutils.regextrim(self.page, '<h1>', '(</h1>|</span>)')
def get_searches(self):
if string.find(self.page, '<title>Suche') > 0:
elements = string.split(self.page, "hit.php3?hit=")
elements[0] = ''
for element in elements:
if element <> '':
id = gutils.trim(element, 'movie-', '-')
if id <> '':
self.ids.append(id)
self.titles.append(gutils.strip_tags(string.replace(gutils.regextrim(element, '>', '</[Aa]>'), '<br />', ' - ')))
else:
id = gutils.regextrim(self.page, 'index[.]php3[?]id=', '("|;|\')')
self.ids.append(id)
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_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_plot(self):
self.plot = ''
storyid = gutils.regextrim(self.page, '<a href="plot/', '(">|[&])')
if not storyid is None:
story_page = self.open_page(url="https://ssl.ofdb.de/plot/%s" % (storyid.encode('utf8')))
if story_page:
self.plot = gutils.trim(story_page, "</b><br><br>","</")
def get_plot(self):
self.plot = ''
storyid = gutils.regextrim(self.page, '<a href="plot/', '(">|[&])')
if not storyid is None:
story_page = self.open_page(url="http://www.ofdb.de/plot/%s" % (storyid.encode('utf8')))
if story_page:
self.plot = gutils.trim(story_page, "</b><br><br>","</")
def get_cast(self):
self.cast = gutils.regextrim(self.page, '[(]Darsteller[)]', '(<[pP]>|<br><span[^>]+>)')
self.cast = gutils.clean(self.cast)
self.cast = self.cast.replace(' als ', _(' as '))
self.cast = re.sub('( \t|\t|\r|\n)', '', self.cast)
self.cast = self.cast.replace(', ', '\n')
self.cast = self.cast.replace(',', '')
def get_year(self):
self.year = ''
tmp = gutils.regextrim(self.tmp_page, 'span class="standardsmall"[^>]*><strong>', '</span>')
if tmp <> None:
srchresult = re.search('[0-9][0-9][0-9][0-9]</strong>', tmp)
if srchresult <> None:
self.year = srchresult.string[srchresult.start():srchresult.end()]
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_image(self):
# Find the film's poster image
tmp_poster = gutils.regextrim(self.page, "../images_locandine/%s/" % self.movie_id, ".(JPG|jpg)\"")
if tmp_poster != "":
self.image_url = "http://www.cinematografo.it/bancadati/images_locandine/%s/%s.jpg" % (self.movie_id, tmp_poster)
else:
self.image_url = ""
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_plot(self):
self.plot = re.sub(
'[0-9 ]+Views', '',
re.sub(
'[]', '-',
re.sub(
'[\x93]', '"', gutils.regextrim(self.page, 'showcover.php[^>]*>', '</td>'))))
def get_cast(self):
self.cast = gutils.regextrim(self.page, '[(]Darsteller[)]',
'(</td>|<br><span[^>]+>)')
self.cast = gutils.clean(self.cast)
self.cast = self.cast.replace(' als ', _(' as '))
self.cast = re.sub('( \t|\t|\r|\n)', '', self.cast)
self.cast = self.cast.replace(',', '\n')
def get_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_searches(self):
if string.find(self.page, '<title>Suche') > 0:
elements = string.split(self.page, "hit.php3?hit=")
elements[0] = ''
for element in elements:
if element <> '':
id = gutils.trim(element, 'movie-', '-')
if id <> '':
self.ids.append(id)
self.titles.append(
gutils.strip_tags(
string.replace(
gutils.regextrim(element, '>', '</[Aa]>'),
'<br />', ' - ')))
else:
id = gutils.regextrim(self.page, 'index[.]php3[?]id=', '("|;|\')')
self.ids.append(id)
def get_o_title(self):
self.o_title = gutils.regextrim(
self.page, '(<p>Originaltitel[:] |Originaltitel<[^>]+>)',
'(</tr>|</p>)')
if not self.o_title:
self.o_title = gutils.trim(self.page, '<h1(', ')')
if not self.o_title:
self.o_title = gutils.trim(self.page, '<div class="teaser">',
'</')
if not self.o_title:
if self.videopage:
self.o_title = gutils.trim(self.videopage,
'<p>Originaltitel: ',
'</p>')
if not self.o_title:
self.o_title = gutils.regextrim(
self.page, '<h1>', '(</h1>|</span>)')
def get_o_title(self):
self.o_title = gutils.trim(self.page, '<p>Originaltitel: ', '</p>')
if not self.o_title:
self.o_title = gutils.trim(self.page, '<span class="standardsmall">(', ')')
if not self.o_title:
self.o_title = gutils.trim(self.page, '<div class="teaser">', '</')
if not self.o_title:
self.o_title = gutils.regextrim(self.page, '<title>', '([|]|</title>)')
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_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_o_title(self):
self.o_title = gutils.trim(self.o_page, '<span class="title-extra">',
'<i>(original title)</i>')
if self.o_title == '':
self.o_title = gutils.regextrim(self.o_page, '<h1>',
'([ ]|[&][#][0-9]+[;])<span')
if self.o_title == '':
self.o_title = re.sub(
'[(].*', '', gutils.trim(self.o_page, '<title>', '</title>'))
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 get_runtime(self):
self.runtime = gutils.strip_tags(
gutils.regextrim(self.page, 'Runtime<[^>]+>', 'min<'))
tmp = string.split(self.runtime, 'h ')
if len(tmp) > 1:
try:
self.runtime = int(tmp[0]) * 60 + int(tmp[1])
except:
None
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):
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 get_studio(self):
self.studio = ''
tmp = gutils.regextrim(self.comp_page, 'Production Companies<[^>]+', '</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_cameraman(self):
self.cameraman = ''
tmp = gutils.regextrim(self.cast_page, 'Cinematography by<[^>]+', '</table>')
tmp = string.split(tmp, 'href="')
for entry in tmp:
entry = gutils.trim(entry, '>', '<')
if entry:
self.cameraman = self.cameraman + entry + ', '
if self.cameraman:
self.cameraman = self.cameraman[:-2]
def get_studio(self):
self.studio = ''
tmp = gutils.regextrim(self.page, '>Production Company<', '(<B>|</TABLE>)')
elements = re.split('(href|HREF)="/db/companies', tmp)
for element in elements:
element = gutils.clean(gutils.trim(element, '>', '<'))
if element:
self.studio = self.studio + element + ', '
if self.studio:
self.studio = self.studio[:-2]
def get_plot(self):
self.plot = gutils.regextrim(self.page, '<h5>Plot:</h5>', '(</div>|<a href.*)')
self.plot = self.__before_more(self.plot)
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\n'
def get_screenplay(self):
self.screenplay = gutils.regextrim(self.page, '<th>Buch:', '<th>')
if not self.screenplay:
self.screenplay= gutils.trim(self.creditspage, 'Drehbuch: ', '</tr>')
if not self.screenplay:
elements = re.split('<h3>Drehbuch</h3>', self.page)
delimiter = ''
for element in elements[1:]:
self.screenplay = self.screenplay + delimiter + gutils.trim(element, 'itemprop="name">', '<')
delimiter = ', '
def get_cameraman(self):
self.cameraman = gutils.regextrim(self.page, '<th>Kamera:', '(<th>|</table>)')
if not self.cameraman:
self.cameraman= gutils.trim(self.creditspage, 'Kamera ', '</tr>')
if not self.cameraman:
elements = re.split('"function-title">Kamera</span>', self.page)
delimiter = ''
for element in elements[1:]:
self.cameraman = self.cameraman + delimiter + gutils.trim(element, 'itemprop="name">', '<')
delimiter = ', '
def get_cameraman(self): # OK v0.1
self.cameraman = ''
tmp = gutils.regextrim(self.cast_page, 'Image<[^>]+', '</table>')
tmp = string.split(tmp, 'href="')
for entry in tmp:
entry = gutils.trim(entry, '>', '<')
if entry:
self.cameraman = self.cameraman + entry + ', '
if self.cameraman:
self.cameraman = self.cameraman[:-2]
def get_studio(self):
self.studio = ''
tmp = gutils.regextrim(self.comp_page, 'Production Companies<[^>]+',
'</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_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 get_o_title(self):
# it seems, that films coming from the German branch can have their German title in the h1-name-tag;
# in this case (only?), IMDB renders an additional "originalTitle"-tag.
self.o_title = gutils.trim(self.page, '<div class="originalTitle">', '<span')
if not self.o_title:
self.o_title = gutils.regextrim(self.page, '<h1 itemprop="name"[^>]*>', ' ')
if not self.o_title:
self.o_title = gutils.trim(self.page, 'og:title\' content="', '"')
if not self.o_title:
self.o_title = re.sub(' [(].*', '', gutils.trim(self.page, '<title>', '</title>'))
self.o_title = gutils.clean(re.sub('"', '', self.o_title))
def get_o_title(self):
self.o_title = gutils.trim(self.page, '<p>Originaltitel: ', '</p>')
if not self.o_title:
self.o_title = gutils.trim(self.page, '<h1(', ')')
if not self.o_title:
self.o_title = gutils.trim(self.page, '<div class="teaser">', '</')
if not self.o_title:
if self.videopage:
self.o_title = gutils.trim(self.videopage, '<p>Originaltitel: ', '</p>')
if not self.o_title:
self.o_title = gutils.regextrim(self.page, '<h1>', '</h1>')
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 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 get_cast(self):
# Find the actors. Try to make it comma separated.
self.cast = gutils.regextrim(self.page, ">Attori</font>", '(<font class="fontViolaB">|\n)')
self.cast = string.replace(self.cast, "target='_self'>", "\n>")
self.cast = string.replace(self.cast, "<a>", _(" as ").encode('utf8'))
self.cast = string.replace(self.cast, "</tr><tr>", '\n')
self.cast = string.replace(self.cast, "...vedi il resto del cast", '')
self.cast = gutils.clean(self.cast)
self.cast = string.replace(self.cast, " ", ' ')
self.cast = re.sub('[ ]+', ' ', self.cast)
self.cast = re.sub('\n[ ]+', '\n', self.cast)
def get_o_title(self): # OK v0.1
#~ self.o_title = gutils.trim(self.page, 'class="title-extra">', '<')
self.o_title = gutils.trim(
gutils.trim(self.page, '<h5>Alias:</h5><div class="info-content">',
'</div>'), '"', '"')
if not self.o_title: # same conditions as title
self.o_title = gutils.regextrim(self.page, '<h1>',
'([ ]|[&][#][0-9]+[;])<span')
if not self.o_title:
self.o_title = re.sub(
' [(].*', '', gutils.trim(self.page, '<title>', '</title>'))
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 get_plot(self):
self.plot = gutils.regextrim(self.page, '<h5>Plot:</h5>',
'(</div>|<a href.*)')
self.plot = self.__before_more(self.plot)
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\n'
