def parse(self, response):
html = response.body.\
replace('<=', ' ≤ ').\
replace(' < ', ' < ').\
replace(' > ', ' > ').\
replace('>=', ' ≥ ')
sel = Selector(text=html)
item = ProblemItem()
item['origin_oj'] = 'poj'
item['problem_id'] = self.problem_id
item['problem_url'] = response.url
item['title'] = sel.css('.ptt').xpath('./text()').extract()[0]
item['description'] = sel.css('.ptx').extract()[0]
item['input'] = sel.css('.ptx').extract()[1]
item['output'] = sel.css('.ptx').extract()[2]
try:
item['time_limit'] = sel.css('.plm').re(
'Case\sT[\S*\s]*MS')[0][21:]
except:
item['time_limit'] = sel.css('.plm').re('T[\S*\s]*MS')[0][16:]
item['memory_limit'] = sel.css('.plm').re('Me[\S*\s]*K')[0][18:]
item['sample_input'] = sel.css('.sio').extract()[0]
item['sample_output'] = sel.css('.sio').extract()[1]
item['update_time'] = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
return item
def parse(self, response):
html = response.body.\
replace(' <= ', ' ≤ ').\
replace(' < ', ' < ').\
replace(' > ', ' > ').\
replace(' >= ', ' ≥ ').\
replace(' << ', ' << ').\
replace(' >> ', ' >> ')
sel = Selector(text=html)
item = ProblemItem()
item['origin_oj'] = 'fzu'
item['problem_id'] = self.problem_id
item['problem_url'] = response.url
item['title'] = sel.xpath(\
'//div[contains(@class,\
"problem_title")]/b/text()' ).extract()[0][14:].rstrip()
item['description'] = \
sel.css('.pro_desc').extract()[0][22:-6].\
replace('<div class="data">', '<pre>').\
replace('</div>', '</pre>')
try:
item['input'] = sel.css('.pro_desc').extract()[1]
except:
item['input'] = []
try:
item['output'] = sel.css('.pro_desc').extract()[2]
except:
item['output'] = []
item['time_limit'] = sel.css('.problem_desc').re('T[\S*\s]*c')[0][12:]
item['memory_limit'] = sel.css('.problem_desc').re(
'M[\S*\s]*B')[0][15:]
item['accept'] = sel.css('.problem_desc').re('Accept:*\s[0-9]+')[0][8:]
item['submit'] = sel.css('.problem_desc').re('Submit:*\s[0-9]+')[0][8:]
item['sample_input'] = \
sel.css('.data').extract()[-2].\
replace('<div class="data">', '<pre>').\
replace('</div>', '</pre>')
item['sample_output'] = \
sel.css('.data').extract()[-1].\
replace('<div class="data">', '<pre>').\
replace('</div>', '</pre>')
item['update_time'] = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
return item
def parse(self, response):
sel = Selector(response)
item = ProblemItem()
item['origin_oj'] = 'sdut'
item['problem_id'] = self.problem_id
item['problem_url'] = response.url
item['title'] = sel.xpath('//center/h2/text()').extract()[0]
item['description'] = sel.css('.pro_desc').extract()[0]
item['input'] = sel.css('.pro_desc').extract()[1]
item['output'] = sel.css('.pro_desc').extract()[2]
item['time_limit'] = sel.xpath('//a/h5/text()').re('T[\S*\s]*s')[0][12:]
item['memory_limit'] = \
sel.xpath('//a/h5/text()').re('M[\S*\s]*K')[0][14:]
item['sample_input'] = sel.xpath('//div[@class="data"]/pre').extract()[0]
item['sample_output'] = sel.xpath('//div[@class="data"]/pre').extract()[1]
item['update_time'] = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
return item
def parse(self, response):
sel = Selector(response)
item = ProblemItem()
item['origin_oj'] = 'hdu'
item['problem_id'] = self.problem_id
item['problem_url'] = response.url
item['title'] = sel.xpath('//h1/text()').extract()[0]
item['description'] = sel.css('.panel_content').extract()[0]
item['input'] = sel.css('.panel_content').extract()[1]
item['output'] = sel.css('.panel_content').extract()[2]
item['time_limit'] = \
sel.xpath('//b/span/text()').re('T[\S*\s]*S')[0][12:]
item['memory_limit'] = \
sel.xpath('//b/span/text()').re('Me[\S*\s]*K')[0][14:]
item['sample_input'] = sel.xpath('//pre').extract()[0]
item['sample_output'] = sel.xpath('//pre').extract()[1]
item['update_time'] = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
return item