def parse(self):
content_info = re.compile(r'<tr\s*>\s*<td class="type">(.+?)</td>\s*<td class="birth"(.+?)>.+</td>\s*</tr>',
re.S).findall(self.content)
for name, value in content_info:
if str(name).endswith('дата рождения'):
year_birth = re.compile(r'\d{4}-\d{2}-\d{2}').findall(value)
if year_birth:
self.instance.year_birth = self.prepare_str(year_birth[0])
if self.instance.id:
token = re.findall(r'xsrftoken = \'([^\']+)\'', self.content)
obj_type = re.findall(r'objType: \'([^\']+)\'', self.content)
if token and obj_type:
content = self.request.get_content(self.instance.get_url('info', token=token[0], type=obj_type[0]))
if content:
self.instance.information = content.replace(' class="trivia"', '')
self.content = html.fromstring(self.content)
person_id = re.compile(r".+/name/(\d+)/").findall(self.extract('id'))[0]
self.instance.id = self.prepare_int(person_id)
self.instance.name = self.extract('name', to_str=True)
self.instance.name_en = self.extract('name_en', to_str=True)
self.instance.gender = self.extract('gender', to_str=True)
# movies
from kinopoisk.person import Role
for element in self.extract('movies'):
type = [t.get('data-work-type') for t in element.iterancestors()][0]
self.instance.career.setdefault(type, [])
self.instance.career[type].append(Role.get_parsed('role_link', element))
self.instance.set_source('main_page')
def parse(self):
person_id = re.compile(
r"<link rel=\"canonical\" href=\"https?://www.kinopoisk.ru/name/(\d+)/\" />"
).findall(self.content)
if person_id:
self.instance.id = self.prepare_int(person_id[0])
name = re.compile(
r'<h1 class="moviename-big" itemprop="name">(.+?)</h1>').findall(
self.content)
if name:
self.instance.name = self.prepare_str(name[0])
name_en = re.compile(
r'<span itemprop="alternateName">([A-Z]\'?[- a-zA-Z]+)</span>'
).findall(self.content)
if name_en:
self.instance.name_en = self.prepare_str(name_en[0])
content_info = re.compile(
r'<tr\s*>\s*<td class="type">(.+?)</td>\s*<td[^>]*>(.+?)</td>\s*</tr>'
).findall(self.content)
for name, value in content_info:
if str(name) == 'дата рождения':
year_birth = re.compile(
r'<a href="/lists/m_act%5Bbirthday%5D%5Byear%5D/\d{4}/">(\d{4})</a>'
).findall(value)
if year_birth:
self.instance.year_birth = self.prepare_int(year_birth[0])
if self.instance.id:
token = re.findall(r'xsrftoken = \'([^\']+)\'', self.content)
obj_type = re.findall(r'objType: \'([^\']+)\'', self.content)
if token and obj_type:
response = self.request.get(self.instance.get_url(
'info', token=token[0], type=obj_type[0]),
headers=HEADERS)
response.connection.close()
if response.content:
self.instance.information = response.content.decode(
'windows-1251',
'ignore').replace(' class="trivia"', '')
# movies
from kinopoisk.person import Role
self.content = html.fromstring(self.content)
for element in self.extract('movies'):
type = [t.get('data-work-type')
for t in element.iterancestors()][0]
self.instance.career.setdefault(type, [])
self.instance.career[type].append(
Role.get_parsed('role_link', element))
self.instance.set_source('main_page')
def parse(self):
content_info = re.compile(
r'<tr\s*>\s*<td class="type">(.+?)</td>\s*<td[^>]*>(.+?)</td>\s*</tr>',
re.S).findall(self.content)
for name, value in content_info:
if str(name) == 'дата рождения':
year_birth = re.compile(
r'<a href="/lists/m_act%5Bbirthday%5D%5Byear%5D/\d{4}/">(\d{4})</a>'
).findall(value)
if year_birth:
self.instance.year_birth = self.prepare_int(year_birth[0])
if self.instance.id:
token = re.findall(r'xsrftoken = \'([^\']+)\'', self.content)
obj_type = re.findall(r'objType: \'([^\']+)\'', self.content)
if token and obj_type:
response = self.request.get(self.instance.get_url(
'info', token=token[0], type=obj_type[0]),
headers=HEADERS)
response.connection.close()
if response.content:
self.instance.information = response.content.decode(
'windows-1251',
'ignore').replace(' class="trivia"', '')
self.content = html.fromstring(self.content)
person_id = re.compile(r".+/name/(\d+)/").findall(
self.extract('id'))[0]
self.instance.id = self.prepare_int(person_id)
self.instance.name = self.extract('name', to_str=True)
self.instance.name_en = self.extract('name_en', to_str=True)
# movies
from kinopoisk.person import Role
for element in self.extract('movies'):
type = [t.get('data-work-type')
for t in element.iterancestors()][0]
self.instance.career.setdefault(type, [])
self.instance.career[type].append(
Role.get_parsed('role_link', element))
self.instance.set_source('main_page')
def parse(self):
content_info = re.compile(r'<tr\s*>\s*<td class="type">(.+?)</td>\s*<td[^>]*>(.+?)</td>\s*</tr>', re.S).findall(
self.content)
for name, value in content_info:
if str(name) == 'дата рождения':
year_birth = re.compile(r'<a href="/lists/m_act%5Bbirthday%5D%5Byear%5D/\d{4}/">(\d{4})</a>').findall(
value)
if year_birth:
self.instance.year_birth = self.prepare_int(year_birth[0])
if self.instance.id:
token = re.findall(r'xsrftoken = \'([^\']+)\'', self.content)
obj_type = re.findall(r'objType: \'([^\']+)\'', self.content)
if token and obj_type:
response = self.request.get(self.instance.get_url('info', token=token[0], type=obj_type[0]),
headers=HEADERS)
response.connection.close()
if response.content:
self.instance.information = response.content.decode('windows-1251', 'ignore').replace(
' class="trivia"', '')
self.content = html.fromstring(self.content)
person_id = re.compile(r".+/name/(\d+)/").findall(self.extract('id'))[0]
self.instance.id = self.prepare_int(person_id)
self.instance.name = self.extract('name', to_str=True)
self.instance.name_en = self.extract('name_en', to_str=True)
# movies
from kinopoisk.person import Role
for element in self.extract('movies'):
type = [t.get('data-work-type') for t in element.iterancestors()][0]
self.instance.career.setdefault(type, [])
self.instance.career[type].append(Role.get_parsed('role_link', element))
self.instance.set_source('main_page')