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