def get_problem(self, *args, **kwargs):
url = 'http://acm.wust.edu.cn/problem.php?id=' + str(kwargs['pid']) + '&soj=0'
problem = Problem()
try:
website_data = Spider.get_data(url, self.code_type)
problem.remote_id = kwargs['pid']
problem.remote_url = url
problem.remote_oj = 'WUST'
problem.title = re.search(r': ([\s\S]*?)</h2>', website_data).group(1)
problem.time_limit = re.search(r'(\d* Sec)', website_data).group(1)
problem.memory_limit = re.search(r'(\d* MB)', website_data).group(1)
problem.special_judge = re.search(r'class=red>Special Judge</span>', website_data) is not None
soup = BeautifulSoup(website_data, 'lxml')
# case:problem.picture=self.parse_html("img", soup, website_data)
problem.description = self.parse_html("Description", soup, website_data)
problem.input = self.parse_html("Input", soup, website_data)
problem.output = self.parse_html("Output", soup, website_data)
input_data = self.parse_html("Sample Input", soup, website_data)
output_data = self.parse_html("Sample Output", soup, website_data)
problem.hint = self.parse_html("HINT", soup, website_data)
problem.author = self.parse_html("Author", soup, website_data)
problem.source = self.parse_html("Source", soup, website_data)
problem.sample = [
{'input': input_data,
'output': output_data}]
except:
return Problem.PROBLEM_NOT_FOUND
return problem
def get_problem(self, *args, **kwargs):
url = 'http://acm.hdu.edu.cn/showproblem.php?pid=' + str(kwargs['pid'])
problem = Problem()
try:
website_data = Spider.get_data(url, self.code_type)
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).group(1)
problem.time_limit = re.search(r'(\d* MS)', website_data).group(1)
problem.memory_limit = re.search(r'/(\d* K)',
website_data).group(1)
problem.special_judge = re.search(
r'color=red>Special Judge</font>', website_data) is not None
problem.description = re.search(
r'>Problem Description</div>[\s\S]*?panel_content>([\s\S]*?)</div>',
website_data).group(1)
problem.input = re.search(
r'>Input</div>[\s\S]*?panel_content>([\s\S]*?)</div>',
website_data).group(1)
problem.output = re.search(
r'>Output</div>[\s\S]*?panel_content>([\s\S]*?)</div>',
website_data).group(1)
match_group = re.search(
r'>Sample Input</div>[\s\S]*?panel_content>([\s\S]*?)</div',
website_data)
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)
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)
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)
if match_group:
problem.hint = match_group.group(1)
except:
return Problem.PROBLEM_NOT_FOUND
return problem
def get_problem(self, *args, **kwargs):
pid = kwargs.get('pid')
url = 'http://codeforces.com/problemset/problem/' + pid[:
-1] + '/' + pid[
-1:]
problem = Problem()
try:
website_data = self.req.get(url)
problem.remote_id = kwargs.get('pid')
problem.remote_url = url
problem.remote_oj = 'CODEFORCES'
problem.title = re.search(r'class="title">([\s\S]*?)</div>',
website_data.text).group(1)
temp_result = re.search(
r'time-limit"><div class="property-title">([\s\S]*?)</div>([\s\S]*?)</div>',
website_data.text)
problem.time_limit = temp_result.group(
1) + ': ' + temp_result.group(2)
temp_result = re.search(
r'class="memory-limit"><div class="property-title">([\s\S]*?)</div>([\s\S]*?)</div>',
website_data.text)
problem.memory_limit = temp_result.group(
1) + ': ' + temp_result.group(2)
problem.special_judge = None
problem.description = re.search(
r'class="property-title">'
'([\s\S]*?)</div>([\s\S]*?)</div>'
'([\s\S]*?)<div>([\s\S]*?)</div>', website_data.text).group(4)
problem.input = re.search(
r'class="section-title">Input</div>([\s\S]*?)</div>',
website_data.text).group(1)
problem.output = re.search(
r'class="section-title">Output</div>([\s\S]*?)</div>',
website_data.text).group(1)
input_data = ''
soup = BeautifulSoup(website_data.text, 'lxml')
lines = soup.find_all('div', attrs={'class': 'input'})
if lines:
for line in lines:
input_data += str(line.find('pre')) + '\n'
output_data = ''
lines = soup.find_all('div', attrs={'class': 'output'})
if lines:
for line in lines:
output_data += str(line.find('pre')) + '\n'
problem.sample = [{'input': input_data, 'output': output_data}]
temp_result = re.search(
r'div class="note">([\s\S]*?)</div>([\s\S]*?)</div>',
website_data.text).group(2)
problem.hint = temp_result
except:
return None
def get_problem(self, *args, **kwargs):
url = 'http://poj.org/problem?id=' + str(kwargs['pid'])
problem = Problem()
try:
res = self.req.get(url=url)
website_data = res.text
problem.remote_id = kwargs['pid']
problem.remote_url = url
problem.remote_oj = 'POJ'
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.fzu.edu.cn/problem.php?pid=' + str(kwargs['pid'])
problem = Problem()
try:
website_data = Spider.get_data(url, self.code_type)
soup = BeautifulSoup(website_data, 'lxml')
problem.remote_id = kwargs['pid']
problem.remote_url = url
problem.remote_oj = 'FZU'
problem.title = re.search(r'<b> Problem [\d]* ([\s\S]*?)</b>',
website_data).group(1)
problem.time_limit = re.search(r'(\d* mSec)',
website_data).group(1)
problem.memory_limit = re.search(r'(\d* KB)',
website_data).group(1)
problem.special_judge = re.search(
r'<font color="blue">Special Judge</font>',
website_data) is not None
pro_desc = soup.find_all(attrs={"class": 'pro_desc'})
problem.description = pro_desc[0].get_text()
if len(pro_desc) >= 2:
problem.input = pro_desc[1].get_text()
if len(pro_desc) >= 3:
problem.output = pro_desc[2].get_text()
data = soup.find_all(attrs={"class": 'data'})
if len(data) > 1:
input_data = data[0].get_text()
output_data = data[1].get_text()
problem.sample = [{'input': input_data, 'output': output_data}]
h2s = soup.find_all('h2')
for h2 in h2s[-2:]:
if (h2.get_text().strip() == 'Hint'):
problem.hint = h2.next_sibling
if (h2.get_text().strip() == 'Source'):
problem.source = h2.next_sibling
except Exception as e:
#print(e)
return Problem.PROBLEM_NOT_FOUND
return problem