def get_problem(self, *args, **kwargs):
url = 'http://poj.org/problem?id=' + str(kwargs['pid'])
problem = Problem()
try:
res = self.request.get(url=url)
website_data = res.text
problem.remote_id = kwargs['pid']
problem.remote_url = url
problem.remote_oj = 'POJ'
# print('probid', problem.remote_id)
problem.title = re.search(r'ptt" lang="en-US">([\s\S]*?)</div>', website_data).group(1)
problem.time_limit = re.search(r'(\d*MS)', website_data).group(1)
problem.memory_limit = re.search(r'Memory Limit:</b> ([\s\S]*?)</td>', website_data).group(1)
problem.special_judge = re.search(r'red;">Special Judge</td>', website_data) is not None
problem.description = re.search(r'>Description</p>[\s\S]*?lang="en-US">([\s\S]*?)</div>',
website_data).group(1)
problem.input = re.search(r'>Input</p>[\s\S]*?lang="en-US">([\s\S]*?)</div>', website_data).group(1)
problem.output = re.search(r'>Output</p>[\s\S]*?lang="en-US">([\s\S]*?)</div>', website_data).group(1)
match_group = re.search(r'>Sample Input</p>([\s\S]*?)<p class', website_data)
input_data = ''
if match_group:
input_data = re.search('"sio">([\s\S]*?)</pre>', match_group.group(1)).group(1)
output_data = ''
match_group = re.search(r'>Sample Output</p>([\s\S]*?)<p class', website_data)
if match_group:
output_data = re.search('"sio">([\s\S]*?)</pre>', match_group.group(1)).group(1)
problem.sample = [
{'input': input_data,
'output': output_data}]
# match_group = re.search(r'>Author</div>[\s\S]*?panel_content>([\s\S]*?)</div>', website_data)
# if match_group:
# problem.author = match_group.group(1)
match_group = re.search(r'>Hint</p>[\s\S]*?"en-US">([\s\S]*?)</div>', website_data)
if match_group:
problem.hint = match_group.group(1)
match_group = re.search(r'>Source</p>[\s\S]*?"en-US">([\s\S]*?)</div>', website_data)
if match_group:
problem.source = match_group.group(1)
return problem
except:
pass
return None
def get_problem(self, *args, **kwargs):
url = 'http://acm.hdu.edu.cn/showproblem.php?pid=' + str(kwargs['pid'])
problem = Problem()
try:
website_data = self.request.get(url)
self.cookies = website_data.cookies
problem.remote_id = kwargs['pid']
problem.remote_url = url
problem.remote_oj = 'HDU'
problem.title = re.search(r'color:#1A5CC8\'>([\s\S]*?)</h1>', website_data.text).group(1)
problem.time_limit = re.search(r'(\d* MS)', website_data.text).group(1)
problem.memory_limit = re.search(r'/(\d* K)', website_data.text).group(1)
problem.special_judge = re.search(r'color=red>Special Judge</font>', website_data.text) is not None
problem.description = re.search(r'>Problem Description</div>[\s\S]*?panel_content>([\s\S]*?)</div>',
website_data.text).group(1)
problem.input = re.search(r'>Input</div>[\s\S]*?panel_content>([\s\S]*?)</div>', website_data.text).group(1)
problem.output = re.search(r'>Output</div>[\s\S]*?panel_content>([\s\S]*?)</div>', website_data.text).group(
1)
match_group = re.search(r'>Sample Input</div>[\s\S]*?panel_content>([\s\S]*?)</div', website_data.text)
input_data = ''
if match_group:
input_data = re.search(r'(<pre><div[\s\S]*?>)?([\s\S]*)', match_group.group(1)).group(2)
output_data = ''
match_group = re.search(r'>Sample Output</div>[\s\S]*?panel_content>([\s\S]*?)</div', website_data.text)
if match_group:
output_data = re.search(r'(<pre><div[\s\S]*?>)?([\s\S]*)', match_group.group(1)).group(2)
if re.search('<div', output_data):
output_data = re.search(r'([\s\S]*?)<div', output_data).group(1)
problem.sample = [
{'input': input_data,
'output': output_data}]
match_group = re.search(r'>Author</div>[\s\S]*?panel_content>([\s\S]*?)</div>', website_data.text)
if match_group:
problem.author = match_group.group(1)
match_group = re.search(r'<i>Hint</i>[\s\S]*?/div>[\s]*([\s\S]+?)</div>', website_data.text)
if match_group:
problem.hint = match_group.group(1)
except:
return None
return problem