def parse_factory(self):
try:
cells = self.__parse_cells()
except KeyError:
logger.error('no cells found')
except Exception as e:
logger.info(e)
else:
return [self.__wrap_cells(cell) for cell in cells]
def parse_body(self, *args, **kwargs):
"""
解析文章内容
返回:
body - 文章的内容，字符串形式，保留html标签
"""
try:
content = self.soup.find(name='div', attrs=self.CONTENT).contents
except Exception as e:
logger.error(e)
return '文章为空'
else:
return ''.join([str(c) for c in content])
def parse_tag(self, *args, **kwargs):
try:
return self.parse_author()[5:]
except Exception as e:
logger.error(e)
return '佚名'
def parse_date(self, *args, **kwargs):
try:
return str(self.soup.find(name='span', attrs=self.DATE).string)
except Exception as e:
logger.error(e)
return 'N/A'