Python Bank.url方法代码示例

# 需要导入模块: from bank import Bank [as 别名]
# 或者: from bank.Bank import url [as 别名]
    def fetchBankList(self):
        banks = [];
        baseUrl = "http://www.psbc.com/portal/zh_CN/CreditCard/SpecialOffers/index%s.html";
        for page in range(0, self.getPageRange()): 
            if page == 0:
                url = baseUrl % ("",);
            else:
                url = baseUrl % ("_" + str(page),);
            soup = self.getSoup(url);
            if not soup:
                break;

            for a in soup.find("ul", class_="artic_list clearfix").find_all("a"):
                b = Bank();
                url =  a["href"].encode("utf-8");
                if re.match(r"http", url):
                    b.url = url; 
                else:
                    b.url = "http://www.psbc.com" + url;

                title = a.string.encode("utf-8");
                m = re.match("(.*)：(.*)", title);
                if not m:
                    b.title = title;
                else:
                    b.title = m.group(2);
                    b.city = m.group(1);

                banks.append(b);
            
	return banks;

# 需要导入模块: from bank import Bank [as 别名]
# 或者: from bank.Bank import url [as 别名]
    def fetchBankListByUrl(self, url):
        banks = [];

        f = self.openUrl(url);
        if f == None:
            return;

        soup = BeautifulSoup(f);
        lis = soup.find_all("li", class_="link");
        for l in lis:
            b = Bank();
            a = l.find("a");
            href = a["href"].encode("utf-8")
            if href.startswith("http:"): 
                b.url = href;
            else:
		b.url = "http://creditcard.cib.com.cn" + href;

            title = a.string.strip().encode("utf-8");
	    b.city = city_parser.parseBracketStyle(title);
	    if b.city in ["兴悦会", "机票随兴订",]:
		b.city = None;
	    b.title = re.sub(r"\[.*?\](.*)", r"\1", title);
            banks.append(b);
        return banks;

# 需要导入模块: from bank import Bank [as 别名]
# 或者: from bank.Bank import url [as 别名]
    def inflateBank(self, jo):
        b = Bank();
        url = jo["LinkUrl"].encode("utf-8");
        if url.find("http:") == -1:
            b.url = "http://cc.cmbchina.com" + url;
        else:
            b.url = url;

        b.title = jo["Title"].encode("utf-8");
        b.name = "招商银行";
        b.fetchTime = strftime("%Y-%m-%d %H:%M:%S", gmtime());
        return b;

# 需要导入模块: from bank import Bank [as 别名]
# 或者: from bank.Bank import url [as 别名]
    def fetchBankList(self):
        banks = [];
        baseUrl = "http://www.nbcb.com.cn/xyk/thtghd/index%s.shtml";
        for page in range(1, self.getPageRange()):
            url = None;
            if page == 1:
                url = baseUrl % "";
            else:
                url = baseUrl % "_" + str(page);

            soup = self.getSoup(url);
            if not soup:
                break;

            for a in soup.find("div", class_="newslist").find_all("a", class_=""):
                b = Bank();
                b.url = "http://www.nbcb.com.cn" + a["href"].encode("utf-8");
                title = soup_util.getStrings(a);
                m = re.match(r"\[(.*)\]", title);
                if m:
                    b.city = m.group(1);
                b.title = re.sub(r"\[(.*)\]|【(.*)】", "", title);
                banks.append(b);

	return banks;

# 需要导入模块: from bank import Bank [as 别名]
# 或者: from bank.Bank import url [as 别名]
	def fetchBankList(self):
		banks = [];
		baseUrls = ["http://xyk.cebbank.com/home/activities/category/a_region_dd/list%d.htm","http://xyk.cebbank.com/home/activities/category/a_life_cycle/list%d.htm",];
		print baseUrls;
		for bu in baseUrls:
			for page in range(1, self.getPageRange()): 
				##url = "http://xyk.cebbank.com/home/activities/category/a_life_cycle/list%d.htm" % page;
				url = bu % page;
				soup = self.getSoup(url);
				if not self.isValidSoup(soup):
					break;

				lis = soup.find("ul", class_="th_list_ul").find_all("div", class_="floatleft");
				for l in lis:
					b = Bank();
					a = l.find("a");
					b.url = "http://xyk.cebbank.com" + a["href"].encode("utf-8");
					title = a.string.encode("utf-8").strip();
					m = re.match(r"(.*?)（(.*)）", title);
					if m:
						b.title = m.group(1);
						b.city = m.group(2);
					else:
						b.title = title;
					banks.append(b);
		return banks;

# 需要导入模块: from bank import Bank [as 别名]
# 或者: from bank.Bank import url [as 别名]
    def fetchBankList(self):
        banks = [];
        baseUrl = "http://creditcard.pingan.com/cms-tmplt/creditcard/searchPreferentialActivity.do?type=&city=shenzhen&currentPage=%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;

# 需要导入模块: from bank import Bank [as 别名]
# 或者: from bank.Bank import url [as 别名]
    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;

# 需要导入模块: from bank import Bank [as 别名]
# 或者: from bank.Bank import url [as 别名]
    def fetchBankList(self):
        f = self.openUrl("http://cards.ecitic.com/youhui/shuakahuodong.shtml");
        if f == None:
            return;

        soup = BeautifulSoup(f);
        lis = soup.find_all("li", class_="emb4 item-n");
        banks = [];
        for li in lis:
            b = Bank();
            h2 = li.find_all("h2")[0];
            title = h2.string.encode("utf-8");
            b.title = re.sub(r"\[.*\]", "", title);
            m = re.match(r".*\[(.*)\].*", title);
            if m:
                b.city = m.group(1);
            b.name = self.getName();
            b.url = "http://cards.ecitic.com/youhui/" +li.find("a", class_="a-h")["href"].encode("utf-8");
            ds = li.find("span", class_="date")
            if ds and ds.string:
                ds = ds.string.encode("utf-8");
                m = re.match(r".*-(.*)", ds)
                if m: 
                    b.endDate = date_parser.parseSlashStyle(m.group(1).strip());
            banks.append(b);
        return banks;

# 需要导入模块: from bank import Bank [as 别名]
# 或者: from bank.Bank import url [as 别名]
def getBankList(whereDict, city="all"):
    conn = getConnection();
    c = conn.cursor();
    where = buildWhereClause(whereDict);
    if city and city != "all":
        where += " and ct_name = '%s'" % city;

    c.execute("SELECT * FROM " + BankTable.TABLE_NAME 
            + " LEFT OUTER JOIN " 
            + " (SELECT _id AS ct_id, name AS ct_name FROM city) "  
            + " ON ct_id == " + BankTable.COL_CITY_ID + " "
            + where + "ORDER BY _id DESC", list(whereDict.viewvalues()))

    conn.commit();

    banks = [];
    for row in c.fetchall():
        bank = Bank();
        bank.name = row[BankTable.COL_NAME];
        bank.title = row[BankTable.COL_TITLE];
        bank.fetchTime = row[BankTable.COL_FETCH_TIME];
        bank.accepted = row[BankTable.COL_ACCEPTED];
        bank.url = row[BankTable.COL_URL];
        bank.id = row[BankTable.COL_ID];
        city = row["ct_name"];
        if city:
            bank.city = city;
        banks.append(bank);
    return banks;

# 需要导入模块: from bank import Bank [as 别名]
# 或者: from bank.Bank import url [as 别名]
    def fetchBankList(self):
        banks = []
        baseUrl = "http://www.bankofshanghai.com/servlet/ServletGate?op=Forward&cur_page=MorePage&target=more&systemModule=1104&cid=110404&page=%d&menuId=&navigation=-%20%25D2%25F8%25D0%25D0%25BF%25A8%25D2%25B5%25CE%25F1%25B6%25AF%25CC%25AC"
        for p in range(1, self.getPageRange()):
            url = (
                "http://www.bankofshanghai.com/servlet/ServletGate?op=Forward&cur_page=MorePage&target=more&systemModule=1104&cid=110404&page="
                + str(p)
                + "&menuId=&navigation=-%20%25D2%25F8%25D0%25D0%25BF%25A8%25D2%25B5%25CE%25F1%25B6%25AF%25CC%25AC"
            )
            soup = self.getSoup(url)
            if not soup or self.isSoupEquals(soup, self.prevSoup):
                break

            self.prevSoup = soup
            for td in soup.find_all("td", bgcolor="#F5F5F5", width="71%"):
                b = Bank()
                a = td.find("a")
                if not a:
                    continue

                b.url = "http://www.bankofshanghai.com/" + a["href"].encode("utf-8")
                b.title = a["title"].encode("utf-8")
                banks.append(b)

        return banks

# 需要导入模块: from bank import Bank [as 别名]
# 或者: from bank.Bank import url [as 别名]
    def fetchBankList(self):

        banks = [];
        baseUrls = ["http://card.cgbchina.com.cn/Channel/11820301?currentChannelPage=%d", "http://card.cgbchina.com.cn/Channel/11820220?currentChannelPage=%d", "http://card.cgbchina.com.cn/Channel/11820139?currentChannelPage=%d"];
        for baseUrl in baseUrls:
            for page in range(1, self.getPageRange()): 
                url = baseUrl % page;
                soup = self.getSoup(url);
                if not soup: 
                    break;

                youhuiContent = soup.find("div", class_="youhui_content");
                if len(youhuiContent.contents) <= 1:
                    break;

                for a in youhuiContent.find_all("a"):
                    bank = Bank();
                    title = a.string.encode("utf-8");
                    m = re.match(r"【(.*)】(.*)", title);
                    if not m:
                        bank.title = title;
                    else:
                        bank.city = m.group(1);
                        bank.title = m.group(2);

                    url =  a["href"].encode("utf-8");
                    if url.find("http") != -1:
                        bank.url = url;
                    else:
                        bank.url = "http://card.cgbchina.com.cn" + url;

                    dateStr = a.parent.find_next_sibling("p").string
                    if dateStr:
                        dateStr = dateStr.encode("utf-8").split("-")[-1].strip();
                        try:
                            bank.endDate =  datetime.strptime(dateStr, "%Y.%m.%d");
                        except ValueError:
                            pass;

                    banks.append(bank);

        return banks;

# 需要导入模块: from bank import Bank [as 别名]
# 或者: from bank.Bank import url [as 别名]
    def parseInner(self, url):
        banks = [];
        soup = self.getSoup(url);

        for a in soup.find("table", class_="ke-zeroborder").find_all("a"):
            b = Bank();
            b.url = a["href"].encode("utf-8");
	    title = a.string.encode("utf-8");
            b.title = self.removeCity(title);
            banks.append(b);
        return banks;

# 需要导入模块: from bank import Bank [as 别名]
# 或者: from bank.Bank import url [as 别名]
    def fetchBankList(self):
        banks = [];
	soup = self.getSoup("http://creditcard.gzcb.com.cn/Activities3.html", encoding="gbk");
	if not soup:
	    return banks;

	for a in soup.find("div", class_="active_C").find("ul").find_all("a"):
	    b = Bank();
	    b.url = "http://creditcard.gzcb.com.cn/" + a["href"].encode("utf-8");
	    b.title = a.string.encode("utf-8");
	    banks.append(b);

	return banks;

# 需要导入模块: from bank import Bank [as 别名]
# 或者: from bank.Bank import url [as 别名]
    def fetchBankList(self):
        banks = [];
	for page in range(1, self.getPageRange()): 
            f = self.openUrl("http://app.cqrcb.com:81/apply/ajax/AjaxSearch?pageNo=" + str(page) + "&bianliang=0");
	    if f == None:
		break;

            root = json.loads(f.read());
            for l in root['merchantList']:
                b = Bank();
                b.url = "http://app.cqrcb.com:81/apply/ShowDetail.action?merid=" + l["merid"].encode("utf-8");
                b.title =  l["merpro"].encode("utf-8");
                banks.append(b);
	return banks;

# 需要导入模块: from bank import Bank [as 别名]
# 或者: from bank.Bank import url [as 别名]
    def fetchBankList(self):
        banks = [];
	url = "http://www.hccb.com.cn/xyk/hdgg/index.shtml#";
	soup = self.getSoup(url);
	if not soup:
	    return banks;
	for td in soup.find_all("td", class_="newstitle"):
	    b = Bank();
	    a = td.find("a");
	    b.url = "http://www.hccb.com.cn" + a["href"].encode("utf-8");
	    b.title = self.getTitle(b.url);
	    b.endTime = self.getEndTime(b.url);
	    banks.append(b);

	return banks;