def start_requests(self): links = service.get_links(self.get_domain(), 0) time_str1 = '%s-%s' % (time.localtime().tm_year, time.localtime().tm_mon) time_str2 = '%s-%s' % (time.localtime().tm_year, time.localtime().tm_mon + 1) links.extend(['http://career.ruc.edu.cn/index.asp?date=%s' % time_str1, 'http://career.ruc.edu.cn/index.asp?date=%s' % time_str2]) for link in links: yield self._create_request(link)
def start_requests(self): links = service.get_links(self.get_domain(), 0) base_url = 'http://job.ustb.edu.cn/accms/sites/jobc/zhaopinhuixinxi-list.jsp?fromDate=%s&F_FL1=校内&F_FL2=' week_day = time.localtime().tm_wday time_str1 = '%4d%2.2d%2.2d' % (time.localtime(time.time() - 60 * 60 * 24 * week_day).tm_year, time.localtime(time.time() - 60 * 60 * 24 * week_day).tm_mon, time.localtime(time.time() - 60 * 60 * 24 * week_day).tm_mday) time_str2 = '%4d%2.2d%2.2d' % (time.localtime(time.time() - 60 * 60 * 24 * (week_day - 7)).tm_year, time.localtime(time.time() - 60 * 60 * 24 * (week_day - 7)).tm_mon, time.localtime(time.time() - 60 * 60 * 24 * (week_day - 7)).tm_mday) time_str3 = '%4d%2.2d%2.2d' % (time.localtime(time.time() - 60 * 60 * 24 * (week_day - 14)).tm_year, time.localtime(time.time() - 60 * 60 * 24 * (week_day - 14)).tm_mon, time.localtime(time.time() - 60 * 60 * 24 * (week_day - 14)).tm_mday) time_str4 = '%4d%2.2d%2.2d' % (time.localtime(time.time() - 60 * 60 * 24 * (week_day - 21)).tm_year, time.localtime(time.time() - 60 * 60 * 24 * (week_day - 21)).tm_mon, time.localtime(time.time() - 60 * 60 * 24 * (week_day - 21)).tm_mday) links.extend([base_url % time_str1, base_url % time_str2, base_url % time_str3, base_url % time_str4, ]) for link in links: yield self._create_request(link)
def start_requests(self): links = service.get_links(self.get_domain(), 0) # links = ['http://career.buaa.edu.cn/website/zphxx/388e7d9b013d7bfc3c715f88.h'] # http://scc.pku.edu.cn/zpxx/zphd/34590.htm for link in links: yield self._create_request(link)