def iter_movie_persons(self, movie_id, role_filter):
res = self.readurl(
'http://api.allocine.fr/rest/v3/movie?partner=YW5kcm9pZC12M3M&code=%s&profile=large&mediafmt=mp4-lc&format=json&filter=movie&striptags=synopsis,synopsisshort' % movie_id)
if res is not None:
jres = json.loads(res)
if 'movie' in jres:
jres = jres['movie']
else:
return
else:
return
if 'castMember' in jres:
for cast in jres['castMember']:
if (role_filter is None or (role_filter is not None and cast['activity']['$'].lower().strip() == role_filter.lower().strip())):
id = cast['person']['code']
name = unicode(cast['person']['name'])
short_description = unicode(cast['activity']['$'])
if 'role' in cast:
short_description += ', %s' % cast['role']
thumbnail_url = NotAvailable
if 'picture' in cast:
thumbnail_url = unicode(cast['picture']['href'])
person = Person(id, name)
person.short_description = short_description
person.real_name = NotLoaded
person.birth_place = NotLoaded
person.birth_date = NotLoaded
person.death_date = NotLoaded
person.gender = NotLoaded
person.nationality = NotLoaded
person.short_biography = NotLoaded
person.roles = NotLoaded
person.thumbnail_url = thumbnail_url
yield person
def iter_persons(self, pattern):
res = self.readurl('http://api.allocine.fr/rest/v3/search?partner=YW5kcm9pZC12M3M&filter=person&q=%s&format=json' % pattern.encode('utf-8'))
jres = json.loads(res)
if 'person' not in jres['feed']:
return
for p in jres['feed']['person']:
thumbnail_url = NotAvailable
if 'picture' in p:
thumbnail_url = unicode(p['picture']['href'])
person = Person(p['code'], unicode(p['name']))
desc = u''
if 'birthDate' in p:
desc += '(%s), ' % p['birthDate']
if 'activity' in p:
for a in p['activity']:
desc += '%s, ' % a['$']
person.real_name = NotLoaded
person.birth_place = NotLoaded
person.birth_date = NotLoaded
person.death_date = NotLoaded
person.gender = NotLoaded
person.nationality = NotLoaded
person.short_biography = NotLoaded
person.short_description = desc.strip(', ')
person.roles = NotLoaded
person.thumbnail_url = thumbnail_url
yield person
def iter_persons(self, pattern):
params = [("partner", self.PARTNER_KEY), ("q", pattern), ("format", "json"), ("filter", "person")]
res = self.__do_request("search", params)
if res is None:
return
jres = json.loads(res)
if "person" not in jres["feed"]:
return
for p in jres["feed"]["person"]:
thumbnail_url = NotAvailable
if "picture" in p:
thumbnail_url = unicode(p["picture"]["href"])
person = Person(p["code"], unicode(p["name"]))
desc = u""
if "birthDate" in p:
desc += "(%s), " % p["birthDate"]
if "activity" in p:
for a in p["activity"]:
desc += "%s, " % a["$"]
person.real_name = NotLoaded
person.birth_place = NotLoaded
person.birth_date = NotLoaded
person.death_date = NotLoaded
person.gender = NotLoaded
person.nationality = NotLoaded
person.short_biography = NotLoaded
person.short_description = desc.strip(", ")
person.roles = NotLoaded
person.thumbnail_url = thumbnail_url
yield person
def iter_persons(self, pattern):
params = [('partner', self.PARTNER_KEY),
('q', pattern.encode('utf-8')),
('format', 'json'),
('filter', 'person')]
res = self.__do_request('search', params)
if res is None:
return
jres = json.loads(res)
if 'person' not in jres['feed']:
return
for p in jres['feed']['person']:
thumbnail_url = NotAvailable
if 'picture' in p:
thumbnail_url = unicode(p['picture']['href'])
person = Person(p['code'], unicode(p['name']))
desc = u''
if 'birthDate' in p:
desc += '(%s), ' % p['birthDate']
if 'activity' in p:
for a in p['activity']:
desc += '%s, ' % a['$']
person.real_name = NotLoaded
person.birth_place = NotLoaded
person.birth_date = NotLoaded
person.death_date = NotLoaded
person.gender = NotLoaded
person.nationality = NotLoaded
person.short_biography = NotLoaded
person.short_description = desc.strip(', ')
person.roles = NotLoaded
person.thumbnail_url = thumbnail_url
yield person
def get_person(self, id):
name = NotAvailable
short_biography = NotAvailable
short_description = NotAvailable
birth_place = NotAvailable
birth_date = NotAvailable
death_date = NotAvailable
real_name = NotAvailable
gender = NotAvailable
thumbnail_url = NotAvailable
roles = {}
nationality = NotAvailable
td_overview = self.parser.select(self.document.getroot(), 'td#overview-top', 1)
descs = self.parser.select(td_overview, 'span[itemprop=description]')
if len(descs) > 0:
short_biography = unicode(descs[0].text)
rname_block = self.parser.select(td_overview, 'div.txt-block h4.inline')
if len(rname_block) > 0 and "born" in rname_block[0].text.lower():
links = self.parser.select(rname_block[0].getparent(), 'a')
for a in links:
href = a.attrib.get('href', '').strip()
if href == 'bio':
real_name = unicode(a.text.strip())
elif 'birth_place' in href:
birth_place = unicode(a.text.lower().strip())
names = self.parser.select(td_overview, 'h1[itemprop=name]')
if len(names) > 0:
name = unicode(names[0].text.strip())
times = self.parser.select(td_overview, 'time[itemprop=birthDate]')
if len(times) > 0:
time = times[0].attrib.get('datetime', '').split('-')
if len(time) == 3 and int(time[0]) >= 1900:
birth_date = datetime(int(time[0]), int(time[1]), int(time[2]))
dtimes = self.parser.select(td_overview, 'time[itemprop=deathDate]')
if len(dtimes) > 0:
dtime = dtimes[0].attrib.get('datetime', '').split('-')
if len(dtime) == 3 and int(dtime[0]) >= 1900:
death_date = datetime(int(dtime[0]), int(dtime[1]), int(dtime[2]))
img_thumbnail = self.parser.select(self.document.getroot(), 'td#img_primary img')
if len(img_thumbnail) > 0:
thumbnail_url = unicode(img_thumbnail[0].attrib.get('src', ''))
# go to the filmography page
self.browser.location('http://www.imdb.com/name/%s/filmotype' % id)
assert self.browser.is_on_page(FilmographyPage)
roles = self.browser.page.get_roles()
person = Person(id, name)
person.real_name = real_name
person.birth_date = birth_date
person.death_date = death_date
person.birth_place = birth_place
person.gender = gender
person.nationality = nationality
person.short_biography = short_biography
person.short_description = short_description
person.roles = roles
person.thumbnail_url = thumbnail_url
return person
def get_person(self, id):
name = NotAvailable
short_biography = NotAvailable
short_description = NotAvailable
birth_place = NotAvailable
birth_date = NotAvailable
death_date = NotAvailable
real_name = NotAvailable
gender = NotAvailable
thumbnail_url = NotAvailable
roles = {}
nationality = NotAvailable
td_overview = self.doc.xpath('//td[@id="overview-top"]')[0]
descs = td_overview.xpath('.//span[@itemprop="description"]')
if len(descs) > 0:
short_biography = descs[0].text
rname_block = td_overview.xpath('.//div[has-class("txt-block")]//h4[has-class("inline")]')
if len(rname_block) > 0 and "born" in rname_block[0].text.lower():
links = rname_block[0].xpath('..//a')
for a in links:
href = a.attrib.get('href', '').strip()
if href == 'bio':
real_name = a.text.strip()
elif 'birth_place' in href:
birth_place = a.text.lower().strip()
names = td_overview.xpath('.//h1//span[@itemprop="name"]')
if len(names) > 0:
name = names[0].text.strip()
times = td_overview.xpath('.//time[@itemprop="birthDate"]')
if len(times) > 0:
time = times[0].attrib.get('datetime', '').split('-')
if len(time) == 3 and int(time[0]) >= 1900:
birth_date = datetime(int(time[0]), int(time[1]), int(time[2]))
dtimes = td_overview.xpath('.//time[@itemprop="deathDate"]')
if len(dtimes) > 0:
dtime = dtimes[0].attrib.get('datetime', '').split('-')
if len(dtime) == 3 and int(dtime[0]) >= 1900:
death_date = datetime(int(dtime[0]), int(dtime[1]), int(dtime[2]))
img_thumbnail = self.doc.xpath('//td[@id="img_primary img"]')
if len(img_thumbnail) > 0:
thumbnail_url = img_thumbnail[0].attrib.get('src', '')
roles = self.get_roles()
person = Person(id, name)
person.real_name = real_name
person.birth_date = birth_date
person.death_date = death_date
person.birth_place = birth_place
person.gender = gender
person.nationality = nationality
person.short_biography = short_biography
person.short_description = short_description
person.roles = roles
person.thumbnail_url = thumbnail_url
return person
def iter_movie_persons(self, movie_id, role_filter):
params = [
("partner", self.PARTNER_KEY),
("code", movie_id),
("profile", "large"),
("mediafmt", "mp4-lc"),
("filter", "movie"),
("striptags", "synopsis,synopsisshort"),
("format", "json"),
]
res = self.__do_request("movie", params)
if res is not None:
jres = json.loads(res)
if "movie" in jres:
jres = jres["movie"]
else:
return
else:
return
if "castMember" in jres:
for cast in jres["castMember"]:
if role_filter is None or (
role_filter is not None and cast["activity"]["$"].lower().strip() == role_filter.lower().strip()
):
id = cast["person"]["code"]
name = unicode(cast["person"]["name"])
short_description = unicode(cast["activity"]["$"])
if "role" in cast:
short_description += ", %s" % cast["role"]
thumbnail_url = NotAvailable
if "picture" in cast:
thumbnail_url = unicode(cast["picture"]["href"])
person = Person(id, name)
person.short_description = short_description
person.real_name = NotLoaded
person.birth_place = NotLoaded
person.birth_date = NotLoaded
person.death_date = NotLoaded
person.gender = NotLoaded
person.nationality = NotLoaded
person.short_biography = NotLoaded
person.roles = NotLoaded
person.thumbnail_url = thumbnail_url
yield person
def iter_persons(self, pattern):
res = self.readurl('http://www.imdb.com/xml/find?json=1&nr=1&nm=on&q=%s' % pattern.encode('utf-8'))
jres = json.loads(res)
htmlparser = HTMLParser()
for cat in ['name_popular', 'name_exact', 'name_approx']:
if cat in jres:
for p in jres[cat]:
person = Person(p['id'], htmlparser.unescape(unicode(p['name'])))
person.real_name = NotLoaded
person.birth_place = NotLoaded
person.birth_date = NotLoaded
person.death_date = NotLoaded
person.gender = NotLoaded
person.nationality = NotLoaded
person.short_biography = NotLoaded
person.short_description = htmlparser.unescape(p['description'])
person.roles = NotLoaded
person.thumbnail_url = NotLoaded
yield person
def iter_movie_persons(self, movie_id, role_filter):
params = [('partner', self.PARTNER_KEY),
('code', movie_id),
('profile', 'large'),
('mediafmt', 'mp4-lc'),
('filter', 'movie'),
('striptags', 'synopsis,synopsisshort'),
('format', 'json')]
res = self.__do_request('movie', params)
if res is not None:
jres = json.loads(res)
if 'movie' in jres:
jres = jres['movie']
else:
return
else:
return
if 'castMember' in jres:
for cast in jres['castMember']:
if (role_filter is None or (role_filter is not None and cast['activity']['$'].lower().strip() == role_filter.lower().strip())):
id = cast['person']['code']
name = unicode(cast['person']['name'])
short_description = unicode(cast['activity']['$'])
if 'role' in cast:
short_description += ', %s' % cast['role']
thumbnail_url = NotAvailable
if 'picture' in cast:
thumbnail_url = unicode(cast['picture']['href'])
person = Person(id, name)
person.short_description = short_description
person.real_name = NotLoaded
person.birth_place = NotLoaded
person.birth_date = NotLoaded
person.death_date = NotLoaded
person.gender = NotLoaded
person.nationality = NotLoaded
person.short_biography = NotLoaded
person.roles = NotLoaded
person.thumbnail_url = thumbnail_url
yield person
def iter_persons(self, role_filter=None):
if (role_filter is None or (role_filter is not None and role_filter == 'actor')):
tables = self.parser.select(self.document.getroot(), 'table.cast_list')
if len(tables) > 0:
table = tables[0]
tds = self.parser.select(table, 'td.itemprop')
for td in tds:
id = td.find('a').attrib.get('href', '').strip('/').split('/')[1]
name = unicode(td.find('a').text)
char_name = unicode(self.parser.select(td.getparent(), 'td.character', 1).text_content())
person = Person(id, name)
person.short_description = char_name
person.real_name = NotLoaded
person.birth_place = NotLoaded
person.birth_date = NotLoaded
person.death_date = NotLoaded
person.gender = NotLoaded
person.nationality = NotLoaded
person.short_biography = NotLoaded
person.roles = NotLoaded
person.thumbnail_url = NotLoaded
yield person
for gloss_link in self.parser.select(self.document.getroot(), 'table[cellspacing="1"] h5 a'):
role = gloss_link.attrib.get('name', '').rstrip('s')
if (role_filter is None or (role_filter is not None and role == role_filter)):
tbody = gloss_link.getparent().getparent().getparent().getparent()
for line in self.parser.select(tbody, 'tr')[1:]:
for a in self.parser.select(line, 'a'):
role_detail = NotAvailable
href = a.attrib.get('href', '')
if '/name/nm' in href:
id = href.strip('/').split('/')[-1]
name = unicode(a.text)
if 'glossary' in href:
role_detail = unicode(a.text)
person = Person(id, name)
person.short_description = role_detail
yield person
def iter_persons(self, role_filter=None):
if (role_filter is None or (role_filter is not None and role_filter == 'actor')):
tables = self.doc.xpath('//table[has-class("cast_list")]')
if len(tables) > 0:
table = tables[0]
tds = table.xpath('.//td[has-class("itemprop")]')
for td in tds:
id = td.find('a').attrib.get('href', '').strip('/').split('/')[1]
name = td.find('a').text
char_name = td.xpath('..//td[has-class("character")]')[0].text_content()
person = Person(id, name)
person.short_description = char_name
person.real_name = NotLoaded
person.birth_place = NotLoaded
person.birth_date = NotLoaded
person.death_date = NotLoaded
person.gender = NotLoaded
person.nationality = NotLoaded
person.short_biography = NotLoaded
person.roles = NotLoaded
person.thumbnail_url = NotLoaded
yield person
for gloss_link in self.doc.xpath('//table[@cellspacing="1"]//h5//a'):
role = gloss_link.attrib.get('name', '').rstrip('s')
if (role_filter is None or (role_filter is not None and role == role_filter)):
tbody = gloss_link.getparent().getparent().getparent().getparent()
for line in tbody.xpath('.//tr')[1:]:
for a in line.xpath('.//a'):
role_detail = NotAvailable
href = a.attrib.get('href', '')
if '/name/nm' in href:
id = href.strip('/').split('/')[-1]
name = a.text
if 'glossary' in href:
role_detail = a.text
person = Person(id, name)
person.short_description = role_detail
yield person
def iter_persons(self, pattern):
res = self.readurl(
'http://www.imdb.com/xml/find?json=1&nr=1&nm=on&q=%s' %
pattern.encode('utf-8'))
jres = json.loads(res)
htmlparser = HTMLParser()
for cat in ['name_popular', 'name_exact', 'name_approx']:
if cat in jres:
for p in jres[cat]:
person = Person(p['id'],
htmlparser.unescape(unicode(p['name'])))
person.real_name = NotLoaded
person.birth_place = NotLoaded
person.birth_date = NotLoaded
person.death_date = NotLoaded
person.gender = NotLoaded
person.nationality = NotLoaded
person.short_biography = NotLoaded
person.short_description = htmlparser.unescape(
p['description'])
person.roles = NotLoaded
person.thumbnail_url = NotLoaded
yield person
def get_person(self, id):
params = [('partner', self.PARTNER_KEY),
('code', id),
('profile', 'large'),
('mediafmt', 'mp4-lc'),
('filter', 'movie'),
('striptags', 'biography,biographyshort'),
('format', 'json')]
res = self.__do_request('person', params)
if res is not None:
jres = json.loads(res)
if 'person' in jres:
jres = jres['person']
else:
return None
else:
return None
name = NotAvailable
short_biography = NotAvailable
biography = NotAvailable
short_description = NotAvailable
birth_place = NotAvailable
birth_date = NotAvailable
death_date = NotAvailable
real_name = NotAvailable
gender = NotAvailable
thumbnail_url = NotAvailable
roles = {}
nationality = NotAvailable
if 'name' in jres:
name = u''
if 'given' in jres['name']:
name += jres['name']['given']
if 'family' in jres['name']:
name += ' %s' % jres['name']['family']
if 'biographyShort' in jres:
short_biography = unicode(jres['biographyShort'])
if 'birthPlace' in jres:
birth_place = unicode(jres['birthPlace'])
if 'birthDate' in jres:
df = jres['birthDate'].split('-')
birth_date = datetime(int(df[0]), int(df[1]), int(df[2]))
if 'deathDate' in jres:
df = jres['deathDate'].split('-')
death_date = datetime(int(df[0]), int(df[1]), int(df[2]))
if 'realName' in jres:
real_name = unicode(jres['realName'])
if 'gender' in jres:
gcode = jres['gender']
if gcode == '1':
gender = u'Male'
else:
gender = u'Female'
if 'picture' in jres:
thumbnail_url = unicode(jres['picture']['href'])
if 'nationality' in jres:
nationality = u''
for n in jres['nationality']:
nationality += '%s, ' % n['$']
nationality = nationality.strip(', ')
if 'biography' in jres:
biography = unicode(jres['biography'])
if 'participation' in jres:
for m in jres['participation']:
if m['activity']['$'] not in roles:
roles[m['activity']['$']] = []
pyear = '????'
if 'productionYear' in m['movie']:
pyear = m['movie']['productionYear']
roles[m['activity']['$']].append(u'(%s) %s' % (pyear, m['movie']['originalTitle']))
person = Person(id, name)
person.real_name = real_name
person.birth_date = birth_date
person.death_date = death_date
person.birth_place = birth_place
person.gender = gender
person.nationality = nationality
person.short_biography = short_biography
person.biography = biography
person.short_description = short_description
person.roles = roles
person.thumbnail_url = thumbnail_url
return person
def get_person(self, id):
params = [('partner', self.PARTNER_KEY), ('code', id),
('profile', 'large'), ('mediafmt', 'mp4-lc'),
('filter', 'movie'),
('striptags', 'biography,biographyshort'),
('format', 'json')]
jres = self.__do_request('person', params)
if jres is not None:
if 'person' in jres:
jres = jres['person']
else:
return None
else:
return None
name = NotAvailable
short_biography = NotAvailable
biography = NotAvailable
short_description = NotAvailable
birth_place = NotAvailable
birth_date = NotAvailable
death_date = NotAvailable
real_name = NotAvailable
gender = NotAvailable
thumbnail_url = NotAvailable
roles = {}
nationality = NotAvailable
if 'name' in jres:
name = u''
if 'given' in jres['name']:
name += jres['name']['given']
if 'family' in jres['name']:
name += ' %s' % jres['name']['family']
if 'biographyShort' in jres:
short_biography = unicode(jres['biographyShort'])
if 'birthPlace' in jres:
birth_place = unicode(jres['birthPlace'])
if 'birthDate' in jres:
df = jres['birthDate'].split('-')
birth_date = datetime(int(df[0]), int(df[1]), int(df[2]))
if 'deathDate' in jres:
df = jres['deathDate'].split('-')
death_date = datetime(int(df[0]), int(df[1]), int(df[2]))
if 'realName' in jres:
real_name = unicode(jres['realName'])
if 'gender' in jres:
gcode = jres['gender']
if gcode == '1':
gender = u'Male'
else:
gender = u'Female'
if 'picture' in jres:
thumbnail_url = unicode(jres['picture']['href'])
if 'nationality' in jres:
nationality = u''
for n in jres['nationality']:
nationality += '%s, ' % n['$']
nationality = nationality.strip(', ')
if 'biography' in jres:
biography = unicode(jres['biography'])
if 'participation' in jres:
for m in jres['participation']:
if m['activity']['$'] not in roles:
roles[m['activity']['$']] = []
pyear = '????'
if 'productionYear' in m['movie']:
pyear = m['movie']['productionYear']
movie_to_append = (u'%s' % (m['movie']['code']), u'(%s) %s' %
(pyear, m['movie']['originalTitle']))
roles[m['activity']['$']].append(movie_to_append)
person = Person(id, name)
person.real_name = real_name
person.birth_date = birth_date
person.death_date = death_date
person.birth_place = birth_place
person.gender = gender
person.nationality = nationality
person.short_biography = short_biography
person.biography = biography
person.short_description = short_description
person.roles = roles
person.thumbnail_url = thumbnail_url
return person
def get_person(self, id):
res = self.readurl(
'http://api.allocine.fr/rest/v3/person?partner=YW5kcm9pZC12M3M&profile=large&code=%s&mediafmt=mp4-lc&filter=movie&format=json&striptags=biography'
% id)
if res is not None:
jres = json.loads(res)
if 'person' in jres:
jres = jres['person']
else:
return None
else:
return None
name = NotAvailable
short_biography = NotAvailable
biography = NotAvailable
short_description = NotAvailable
birth_place = NotAvailable
birth_date = NotAvailable
death_date = NotAvailable
real_name = NotAvailable
gender = NotAvailable
thumbnail_url = NotAvailable
roles = {}
nationality = NotAvailable
if 'name' in jres:
name = u''
if 'given' in jres['name']:
name += jres['name']['given']
if 'family' in jres['name']:
name += ' %s' % jres['name']['family']
if 'biographyShort' in jres:
short_biography = unicode(jres['biographyShort'])
if 'birthPlace' in jres:
birth_place = unicode(jres['birthPlace'])
if 'birthDate' in jres:
df = jres['birthDate'].split('-')
birth_date = datetime(int(df[0]), int(df[1]), int(df[2]))
if 'deathDate' in jres:
df = jres['deathDate'].split('-')
death_date = datetime(int(df[0]), int(df[1]), int(df[2]))
if 'realName' in jres:
real_name = unicode(jres['realName'])
if 'gender' in jres:
gcode = jres['gender']
if gcode == '1':
gender = u'Male'
else:
gender = u'Female'
if 'picture' in jres:
thumbnail_url = unicode(jres['picture']['href'])
if 'nationality' in jres:
nationality = u''
for n in jres['nationality']:
nationality += '%s, ' % n['$']
nationality = nationality.strip(', ')
if 'biography' in jres:
biography = unicode(jres['biography'])
if 'participation' in jres:
for m in jres['participation']:
if m['activity']['$'] not in roles:
roles[m['activity']['$']] = []
pyear = '????'
if 'productionYear' in m['movie']:
pyear = m['movie']['productionYear']
roles[m['activity']['$']].append(
u'(%s) %s' % (pyear, m['movie']['originalTitle']))
person = Person(id, name)
person.real_name = real_name
person.birth_date = birth_date
person.death_date = death_date
person.birth_place = birth_place
person.gender = gender
person.nationality = nationality
person.short_biography = short_biography
person.biography = biography
person.short_description = short_description
person.roles = roles
person.thumbnail_url = thumbnail_url
return person
def get_person(self, id):
params = [
("partner", self.PARTNER_KEY),
("code", id),
("profile", "large"),
("mediafmt", "mp4-lc"),
("filter", "movie"),
("striptags", "biography,biographyshort"),
("format", "json"),
]
res = self.__do_request("person", params)
if res is not None:
jres = json.loads(res)
if "person" in jres:
jres = jres["person"]
else:
return None
else:
return None
name = NotAvailable
short_biography = NotAvailable
biography = NotAvailable
short_description = NotAvailable
birth_place = NotAvailable
birth_date = NotAvailable
death_date = NotAvailable
real_name = NotAvailable
gender = NotAvailable
thumbnail_url = NotAvailable
roles = {}
nationality = NotAvailable
if "name" in jres:
name = u""
if "given" in jres["name"]:
name += jres["name"]["given"]
if "family" in jres["name"]:
name += " %s" % jres["name"]["family"]
if "biographyShort" in jres:
short_biography = unicode(jres["biographyShort"])
if "birthPlace" in jres:
birth_place = unicode(jres["birthPlace"])
if "birthDate" in jres:
df = jres["birthDate"].split("-")
birth_date = datetime(int(df[0]), int(df[1]), int(df[2]))
if "deathDate" in jres:
df = jres["deathDate"].split("-")
death_date = datetime(int(df[0]), int(df[1]), int(df[2]))
if "realName" in jres:
real_name = unicode(jres["realName"])
if "gender" in jres:
gcode = jres["gender"]
if gcode == "1":
gender = u"Male"
else:
gender = u"Female"
if "picture" in jres:
thumbnail_url = unicode(jres["picture"]["href"])
if "nationality" in jres:
nationality = u""
for n in jres["nationality"]:
nationality += "%s, " % n["$"]
nationality = nationality.strip(", ")
if "biography" in jres:
biography = unicode(jres["biography"])
if "participation" in jres:
for m in jres["participation"]:
if m["activity"]["$"] not in roles:
roles[m["activity"]["$"]] = []
pyear = "????"
if "productionYear" in m["movie"]:
pyear = m["movie"]["productionYear"]
movie_to_append = (u"%s" % (m["movie"]["code"]), u"(%s) %s" % (pyear, m["movie"]["originalTitle"]))
roles[m["activity"]["$"]].append(movie_to_append)
person = Person(id, name)
person.real_name = real_name
person.birth_date = birth_date
person.death_date = death_date
person.birth_place = birth_place
person.gender = gender
person.nationality = nationality
person.short_biography = short_biography
person.biography = biography
person.short_description = short_description
person.roles = roles
person.thumbnail_url = thumbnail_url
return person
def get_person(self, id):
name = NotAvailable
short_biography = NotAvailable
short_description = NotAvailable
birth_place = NotAvailable
birth_date = NotAvailable
death_date = NotAvailable
real_name = NotAvailable
gender = NotAvailable
thumbnail_url = NotAvailable
roles = {}
nationality = NotAvailable
td_overview = self.parser.select(self.document.getroot(),
'td#overview-top', 1)
descs = self.parser.select(td_overview, 'span[itemprop=description]')
if len(descs) > 0:
short_biography = unicode(descs[0].text)
rname_block = self.parser.select(td_overview,
'div.txt-block h4.inline')
if len(rname_block) > 0 and "born" in rname_block[0].text.lower():
links = self.parser.select(rname_block[0].getparent(), 'a')
for a in links:
href = a.attrib.get('href', '').strip()
if href == 'bio':
real_name = unicode(a.text.strip())
elif 'birth_place' in href:
birth_place = unicode(a.text.lower().strip())
names = self.parser.select(td_overview, 'h1[itemprop=name]')
if len(names) > 0:
name = unicode(names[0].text.strip())
times = self.parser.select(td_overview, 'time[itemprop=birthDate]')
if len(times) > 0:
time = times[0].attrib.get('datetime', '').split('-')
if len(time) == 3 and int(time[0]) >= 1900:
birth_date = datetime(int(time[0]), int(time[1]), int(time[2]))
dtimes = self.parser.select(td_overview, 'time[itemprop=deathDate]')
if len(dtimes) > 0:
dtime = dtimes[0].attrib.get('datetime', '').split('-')
if len(dtime) == 3 and int(dtime[0]) >= 1900:
death_date = datetime(int(dtime[0]), int(dtime[1]),
int(dtime[2]))
img_thumbnail = self.parser.select(self.document.getroot(),
'td#img_primary img')
if len(img_thumbnail) > 0:
thumbnail_url = unicode(img_thumbnail[0].attrib.get('src', ''))
# go to the filmography page
self.browser.location('http://www.imdb.com/name/%s/filmotype' % id)
assert self.browser.is_on_page(FilmographyPage)
roles = self.browser.page.get_roles()
person = Person(id, name)
person.real_name = real_name
person.birth_date = birth_date
person.death_date = death_date
person.birth_place = birth_place
person.gender = gender
person.nationality = nationality
person.short_biography = short_biography
person.short_description = short_description
person.roles = roles
person.thumbnail_url = thumbnail_url
return person
def get_person(self, id):
res = self.readurl(
'http://api.allocine.fr/rest/v3/person?partner=YW5kcm9pZC12M3M&profile=large&code=%s&mediafmt=mp4-lc&filter=movie&format=json&striptags=biography' % id)
if res is not None:
jres = json.loads(res)
if 'person' in jres:
jres = jres['person']
else:
return None
else:
return None
name = NotAvailable
short_biography = NotAvailable
biography = NotAvailable
short_description = NotAvailable
birth_place = NotAvailable
birth_date = NotAvailable
death_date = NotAvailable
real_name = NotAvailable
gender = NotAvailable
thumbnail_url = NotAvailable
roles = {}
nationality = NotAvailable
if 'name' in jres:
name = u''
if 'given' in jres['name']:
name += jres['name']['given']
if 'family' in jres['name']:
name += ' %s' % jres['name']['family']
if 'biographyShort' in jres:
short_biography = unicode(jres['biographyShort'])
if 'birthPlace' in jres:
birth_place = unicode(jres['birthPlace'])
if 'birthDate' in jres:
df = jres['birthDate'].split('-')
birth_date = datetime(int(df[0]), int(df[1]), int(df[2]))
if 'deathDate' in jres:
df = jres['deathDate'].split('-')
death_date = datetime(int(df[0]), int(df[1]), int(df[2]))
if 'realName' in jres:
real_name = unicode(jres['realName'])
if 'gender' in jres:
gcode = jres['gender']
if gcode == '1':
gender = u'Male'
else:
gender = u'Female'
if 'picture' in jres:
thumbnail_url = unicode(jres['picture']['href'])
if 'nationality' in jres:
nationality = u''
for n in jres['nationality']:
nationality += '%s, ' % n['$']
nationality = nationality.strip(', ')
if 'biography' in jres:
biography = unicode(jres['biography'])
if 'participation' in jres:
for m in jres['participation']:
if m['activity']['$'] not in roles:
roles[m['activity']['$']] = []
pyear = '????'
if 'productionYear' in m['movie']:
pyear = m['movie']['productionYear']
roles[m['activity']['$']].append(u'(%s) %s' % (pyear, m['movie']['originalTitle']))
person = Person(id, name)
person.real_name = real_name
person.birth_date = birth_date
person.death_date = death_date
person.birth_place = birth_place
person.gender = gender
person.nationality = nationality
person.short_biography = short_biography
person.biography = biography
person.short_description = short_description
person.roles = roles
person.thumbnail_url = thumbnail_url
return person