def fetchBankList(self): banks = []; baseUrl = "http://creditcard.pingan.com/cms-tmplt/creditcard/searchPreferentialActivity.do?type=&city=shenzhen¤tPage=%d"; for page in range(1, self.getPageRange()): url = baseUrl % page; soup = self.getSoup(url); if not soup: break; lis = soup.find_all("tr", class_="item"); if len(lis) == 0: break; for l in lis: b = Bank(); a = l.find("a"); title = a["title"].encode("utf-8"); m = re.match(r"\[(.*)\]", title); if m: b.city = m.group(1); b.title = re.sub(r"【.*】|\[.*\]", "", title); b.url = "http://creditcard.pingan.com" + a["href"].encode("utf-8"); ds = l.contents[-2].string.encode("utf-8"); b.endDate = date_parser.parseDashLineStyle(ds); banks.append(b); return banks;
def fetchBankList(self): prefUrls = [ "http://creditcard.hxb.com.cn/hotnews/index.jsp?cid=12347700871250001", "http://creditcard.hxb.com.cn/hotnews/index.jsp?cid=12347701281290003" ] banks = [] for prefUrl in prefUrls: for page in range(0, self.getPageRange()): url = prefUrl + "&page_count=30&page_start=%d" % (page * 5) soup = self.getSoup(url) if not self.isValidSoup(soup): break lis = soup.find_all("div", id="rm_lcd") for l in lis: b = Bank() a = l.find("a") b.url = "http://creditcard.hxb.com.cn/hotnews/" + a[ "href"].encode("utf-8") b.title = a["title"].encode("utf-8").strip() h6 = l.find("h6").string if h6 != None: m = re.match("\[.*至(.*)\]", h6.encode("utf-8")) if m != None: b.endDate = date_parser.parseDashLineStyle( m.group(1)) banks.append(b) return banks
def fetchBankList(self): banks = [] baseUrl = "http://creditcard.pingan.com/cms-tmplt/creditcard/searchPreferentialActivity.do?type=&city=shenzhen¤tPage=%d" for page in range(1, self.getPageRange()): url = baseUrl % page soup = self.getSoup(url) if not soup: break lis = soup.find_all("tr", class_="item") if len(lis) == 0: break for l in lis: b = Bank() a = l.find("a") title = a["title"].encode("utf-8") m = re.match(r"\[(.*)\]", title) if m: b.city = m.group(1) b.title = re.sub(r"【.*】|\[.*\]", "", title) b.url = "http://creditcard.pingan.com" + a["href"].encode( "utf-8") ds = l.contents[-2].string.encode("utf-8") b.endDate = date_parser.parseDashLineStyle(ds) banks.append(b) return banks
def fetchBankList(self): prefUrls = ["http://creditcard.hxb.com.cn/hotnews/index.jsp?cid=12347700871250001", "http://creditcard.hxb.com.cn/hotnews/index.jsp?cid=12347701281290003"]; banks = []; for prefUrl in prefUrls: for page in range(0, self.getPageRange()): url = prefUrl + "&page_count=30&page_start=%d" % (page*5); soup = self.getSoup(url); if not self.isValidSoup(soup): break; lis = soup.find_all("div", id="rm_lcd"); for l in lis: b = Bank(); a = l.find("a"); b.url = "http://creditcard.hxb.com.cn/hotnews/" + a["href"].encode("utf-8"); b.title = a["title"].encode("utf-8").strip(); h6 = l.find("h6").string; if h6 != None: m = re.match("\[.*至(.*)\]", h6.encode("utf-8")); if m != None: b.endDate = date_parser.parseDashLineStyle(m.group(1)); banks.append(b); return banks;
def fetchBankList(self): banks = []; url = "http://www.srcb.com/cardActivity/index.shtml"; soup = self.getSoup(url); if not soup: return banks; for ul in soup.find("div", class_="active_list").find_all("ul"): b = Bank(); a = ul.find("a"); b.url = a["href"].encode("utf-8"); b.title = a["title"].encode("utf-8"); ds = ul.find("span").string.encode("utf-8"); m = re.match(r"至\s+(.*)", ds); if m: b.endTime = date_parser.parseDashLineStyle(m.group(1)); banks.append(b); return banks;