def get_date(self):
string = lxml_utils.get_text_following_by_tag(self.html, 'em', "Дата")
if string is None:
return None
for f in settings.date_formats:
try:
date = time.strptime(string, f)
return datetime.fromtimestamp(time.mktime(date))
except ValueError:
continue
return None
def read(self):
with open(self.description_path, 'r', encoding='utf-8') as dfile:
data = dfile.read()
md = markdown(data)
self.html = lxml.html.fromstring(md)
# ALBUM
try:
album_title = self.html.xpath('.//h1/a/text()')[0]
album_uri = self.html.xpath('.//h1/a/@href')[0]
except:
raise Exception('Cannot read album title/uri')
# COURSE
try:
course_title = self.html.xpath('.//p/a/text()')[0]
course_uri = self.html.xpath('.//p/a/@href')[0]
except:
raise Exception('Cannot read course title/uri')
# TEACHER
teacher = lxml_utils.get_text_following_by_tag(self.html, 'em', "Преподаватель")
teacher = re.sub(r'\s', '', teacher)
if teacher not in settings.teachers_names:
raise Exception('Teacher %s is not found' % teacher)
teacher_name = settings.teachers_names[teacher]
# DATE
date = self.get_date()
if date is None:
raise Exception('Date field is empty')
# PRODUCT
content = self.get_drawings()
a = Album(type='1', title=album_title, uri=album_uri, course=course_title, course_uri=course_uri, date=date,
teacher=teacher_name, comment=None)
for p in content:
author_name, author_age, filename, product_title = p
product = self.create_product(a, author_name, author_age, filename, product_title)
product.image_original_path = os.path.join(self.dir_path, filename)
a.add_product(product)
return a
