def parse(self, response):
# print "内部网页"
# print response.body
indatas = response.xpath('//div[@class="ebdp-pc4promote-circularcontainer"]')
print len(indatas)
for data in indatas:
item = FundsInfoItem()
item["pname"] = data.xpath('./div[@class="ebdp-pc4promote-circularcontainer-head"]/span/span/a/text()').extract()[0]
# print item["pname"]
item["pid"] = data.xpath('./div[@class="ebdp-pc4promote-circularcontainer-head"]/span/span/a/@href').extract()[0].split('(')[-1].split(',')[0].strip('\'')
temp = data.xpath('./div[@class="ebdp-pc4promote-circularcontainer-content"]/table/tbody/tr/td')
if len(temp)==5:
item["prate"] = temp[0].xpath('./div/div')[1].xpath('./text()').extract()[0]
item["pfloor"] = temp[1].xpath('./div/div')[1].xpath('./b/text()').extract()[0]+temp[1].xpath('./div/div')[1].xpath('./text()').extract()[0]
item["pperiod"] = temp[2].xpath('./div/div')[1].xpath('string(.)').extract()[0]
elif len(temp)==6:
item["prate"] = temp[1].xpath('./div/div')[1].xpath('./text()').extract()[0]
item["pfloor"] = temp[2].xpath('./div/div')[1].xpath('./b/text()').extract()[0]+temp[1].xpath('./div/div')[1].xpath('./text()').extract()[0]
item["pperiod"] = temp[3].xpath('./div/div')[1].xpath('string(.)').extract()[0]
yield item
def parsexk(self, response):
print("新客理财爬取")
xklc = response.xpath('//div[@class="xklc_con"]')
print(len(xklc))
for product in xklc:
item = FundsInfoItem()
item["pid"] = product.xpath(
'./div/div/div[@class="xklc_cptab"]/ul[@class="tb2 fl"]/li'
)[0].xpath('normalize-space(string(.))').extract()[0]
item["pname"] = product.xpath(
'./div/div/div[@class="xklc_title"]/text()').extract()[0]
try:
item["prate"] = product.xpath(
'./div/div/div[@class="xklc_sz"]/div')[0].xpath(
'normalize-space(string(.))').extract()[0]
except:
pass
try:
item["pperiod"] = product.xpath(
'./div/div/div[@class="xklc_cptab"]/ul[@class="tb2 fl"]'
)[1].xpath('./li')[1].xpath(
'normalize-space(string(.))').extract()[0]
except:
pass
try:
item["pfloor"] = product.xpath(
'./div/div/div[@class="xklc_cptab"]/ul[@class="tb2 fl"]'
)[1].xpath('./li')[0].xpath(
'normalize-space(string(.))').extract()[0]
except:
pass
yield item
def parse(self, response):
# print "内部网页"
# print response.body
indatas = response.xpath('//tbody/tr')
# print len(indatas)
for data in indatas:
item = FundsInfoItem()
try:
item["pname"] = data.xpath('./td')[0].xpath(
'./a/text()').extract()[0]
except:
item["pname"] = data.xpath('./td')[0].xpath(
'./text()').extract()[0]
item["pid"] = data.xpath('./td')[-1].xpath(
'./img/@src').extract()[0].split('lccp')[-1].split('.')[0]
item["prate"] = data.xpath('./td')[6].xpath(
'./text()').extract()[0]
item["pfloor"] = data.xpath('./td')[5].xpath(
'./text()').extract()[0]
item["pperiod"] = data.xpath('./td')[4].xpath(
'./text()').extract()[0]
yield item
def parse(self, response):
# print "打印response"
# print response.body
datas = json.loads(response.body)['content']['resultList']
# print datas[0]
for data in datas:
item = FundsInfoItem()
item["pid"] = data['prdNo']
item["pname"] = data['prdName']
item["prate"] = data['incomerate']
item["pperiod"] = data['dayDeadLine']
item["pfloor"] = data['firstAmt']
pdfUrl = 'https://etrade.citicbank.com/portalweb/findoc/' + str(
item["pid"]) + '00.html'
item["pscale"] = pdfUrl
# self.i = self.i+1
# print self.i
# yield item
try:
subResponse = Request(url=pdfUrl,
method='GET',
meta={"item": item},
callback=self.get_scale,
errback=self.errors)
yield subResponse
except:
yield item
def parsein(self, response):
# print "内部网页"
indatas = response.xpath('//tr')
item = FundsInfoItem()
for data in indatas:
if u'产品名称' in data.xpath('./th/text()').extract()[0]:
# print "产品名称"
item["pname"] = data.xpath(
'normalize-space(./td/text())').extract()[0]
if u'产品代码' in data.xpath('./th/text()').extract()[0]:
# print "产品代码"
item["pid"] = data.xpath(
'normalize-space(./td/text())').extract()[0]
if u'预计年化收益率' in data.xpath('./th/text()').extract()[0]:
# print "预计年化收益率"
item["prate"] = data.xpath(
'normalize-space(./td/text())').extract()[0]
if u'起点金额' in data.xpath('./th/text()').extract()[0]:
# print "起点金额"
item["pfloor"] = data.xpath(
'normalize-space(./td/text())').extract()[0]
if u'投资期限' in data.xpath('./th/text()').extract()[0]:
# print "投资期限"
item["pperiod"] = data.xpath(
'normalize-space(./td/text())').extract()[0]
yield item
def parse(self, response):
datas = json.loads(response.text)['rows']
# print(datas[1])
for data in datas:
item = FundsInfoItem()
item["pid"] = data['finance_no']
item["pname"] = data['finance_allname']
item["prate"] = data['finance_anticipate_rate']
item["pperiod"] = data['finance_lmttime_info']
item["pfloor"] = data['finance_indi_ipominamnt']
yield item
def parsedq(self,response):
# print "打印response"
datas = json.loads(response.body)["data"]["compFinancialProducts"]
# print len(datas)
for data in datas:
item = FundsInfoItem()
item["pid"] = data["prdCode"]
item["pname"] = data["prdName"]
item["prate"] = data["indexContent"]
item["pperiod"] = data["investTerm"]
item["pfloor"] = data["minInvestAmount"]
yield item
def parse(self, response):
# print "打印response"
datas = response.xpath('//Table')
# print len(datas)
for data in datas:
item = FundsInfoItem()
item["pid"] = data.xpath('./ProductNo/text()').extract()[0]
item["pname"] = data.xpath('./ProdName/text()').extract()[0]
item["prate"] = data.xpath('./ProdProfit/text()').extract()[0]
item["pperiod"] = data.xpath('./ProdLimit/text()').extract()[0]
item["pfloor"] = data.xpath('./PurStarAmo/text()').extract()[0]
yield item
def parse(self, response):
print('响应开始：')
print(response.text)
datas = json.loads(response.text)['List']
for data in datas:
item = FundsInfoItem()
item["pid"] = data['PrdCode']
item["pname"] = data['PrdName']
item["prate"] = data['IncomeRateExt']
# item["pperiod"] = str(data['LiveTime'])+'*'+data['UnitLiveTime']
item["pperiod"] = str(data['LiveTime']) + '天'
item["pfloor"] = data['PfirstAmt']
yield item
def parse(self, response):
page = response.text
reg = r'(永乐\d号[^<]*).*(\w\w\d\d\d\d).*(\d\.\d\d%).*起点金额(.*)[\S]上限'.decode(
'utf-8')
reg = re.compile(reg)
finfos = reg.findall(page)
for data in finfos:
item = FundsInfoItem()
item["pid"] = data[1]
item["pname"] = data[0]
item["prate"] = data[2]
item["pperiod"] = u'未找到投资期限'
item["pfloor"] = data[3]
yield item
def parse(self, response):
begin = re.search('jsonpCallback', response.text).end()
datas = json.loads(response.text[begin + 1:-1])['ProdList']
for data in datas:
if data["yieldRate"] == 0.0:
# 试图从子页面抓取最新收益率
data["yieldRate"] = self.get_ccb_detail_rate(data['code'])
item = FundsInfoItem()
item["pid"] = data['code']
item["pname"] = data['name']
item["prate"] = data['yieldRate']
item["pperiod"] = data['investPeriod']
item["pfloor"] = data['purFloorAmt']
# item["pscale"] = data['instructionUrl']
yield item
def parse(self, response):
reg = r'ft">(.*)<span>(.*)</span>[\s\S]{1,1000}value="(.*)"\sna[\s\S]{1,2900}font"[^<>]*>([^<>]*)</span>[\s\S]' \
r'{1,2900}<td class="bot"><span class="font" >(.*)</span><span class="grey">(.*)</span></td>'
reg = re.compile(reg)
funds_info = reg.findall(response.text)
print(funds_info)
print(len(funds_info))
for data in funds_info:
item = FundsInfoItem()
item["pid"] = data[1]
item["pname"] = data[0]
item["prate"] = data[2]
item["pperiod"] = data[3]
item["pfloor"] = data[4] + data[5]
yield item
def parse(self, response):
datas = json.loads(response.text)['rows']
# print(datas[1])
for data in datas:
item = FundsInfoItem()
item["pid"] = data['finance_no']
item["pname"] = data['finance_allname']
item["prate"] = data['finance_anticipate_rate']
# 利率格式归一化
item["prate"] = item["prate"].replace('％', '').replace(
'\r', '').replace('\n', '').replace('\t', '')
if item["prate"][-1] != '%':
item["prate"] = item["prate"] + '%'
item["pperiod"] = data['finance_lmttime_info']
item["pfloor"] = data['finance_indi_ipominamnt']
yield item
def parsehq(self, response):
# print "打印response"
datas = json.loads(response.body)["data"]["recommendAreas"]
# print len(datas[0]["recommendProducts"])
for data_list in datas:
for data in data_list["recommendProducts"]:
item = FundsInfoItem()
item["pid"] = data["prdCode"]+","
item["pname"] = data["recommendName"]
item["prate"] = data["newIndexContent"]
item["pperiod"] = data["recommendType"]
item["pscale"] = data["redirectUrl"]
if data["product"].has_key("finaSaleStatusInfo"):
item["pfloor"] = data["product"]["finaSaleStatusInfo"]["minAmount"]
elif data["product"].has_key("fundSaleStatusInfo"):
item["pfloor"] = data["product"]["fundSaleStatusInfo"]["pfirstAmt"]
yield item
def parse(self, response):
# return response
# print('响应开始：')
# print(response.text)
respo = json.loads(response.text)
datas = respo["returnData"]["list"]
# f = open('test.txt', 'w')
# f.write(str(datas))
# f.close()
for data in datas:
item = FundsInfoItem()
item["pid"] = data['PRD_CODE']
item["pname"] = data['PRD_NAME']
item["prate"] = data['NEXT_INCOME_RATE']
item["pperiod"] = str(data['LIVE_TIME'])+u'天'
item["pfloor"] = data['PFIRST_AMT']
yield item
def parse(self, response):
# print "打印response"
datas = response.xpath('//Table')
# print len(datas)
for data in datas:
item = FundsInfoItem()
item["pid"] = data.xpath('./ProductNo/text()').extract()[0]
item["pname"] = data.xpath('./ProdName/text()').extract()[0]
item["prate"] = data.xpath('./ProdProfit/text()').extract()[0]
item["pperiod"] = data.xpath('./ProdLimit/text()').extract()[0]
item["pfloor"] = data.xpath('./PurStarAmo/text()').extract()[0]
productUrl = self.start_urls[1] + '/' + str(item["pid"]) + '.htm'
# yield item
yield scrapy.FormRequest(url=productUrl,
method='GET',
meta={"item": item},
callback=self.parse_pdf)
def parse(self, response):
re_pid = re.compile(r'(2301\d*)</font>')
re_pname = re.compile(r'<fontclass="autosho[^>]*>([^<]*)|<fontclass="xianjin[^>]*>([^<]*)')
re_prate = re.compile(r'1-2">([^<]*)<|准-->([^<]*)<')
re_pperiod = re.compile(r'日-->([^<]*)<|td>([0123456789天月年\-]+)<')
re_pfloor = re.compile(r'aid[^>]*>([^<]*)|位-->([^<]*)|td>([^<]*万元)')
res_clean = response.text.replace(' ', '').replace('\r', '').replace('\n', '').replace('\t', '')
pids = re_pid.findall(res_clean)
pnames = re_pname.findall(res_clean)
prates = re_prate.findall(res_clean)
pperiods = re_pperiod.findall(res_clean)
pfloors = re_pfloor.findall(res_clean)
datas = []
for i in range(len(pids)):
data = [pids[i], pnames[i][0], prates[i][0], pperiods[i][0], pfloors[i][0]]
if data[1] == '':
data[1] = pnames[i][1]
if data[2] == '':
data[2] = prates[i][1]
if data[3] == '':
data[3] = pperiods[i][1]
if data[3] == '':
data[3] = '无'
if data[4] == '':
data[4] = pfloors[i][1]
if data[4] == '':
data[4] = pfloors[i][2]
datas.append(data)
for data in datas:
item = FundsInfoItem()
item["pid"] = data[0]
item["pname"] = data[1]
item["prate"] = data[2]
# 利率格式归一化
item["prate"] = item["prate"].replace('％', '').replace('\r', '').replace('\n', '').replace('\t', '')
try:
if item["prate"][-1] != '%':
item["prate"] = item["prate"] + '%'
except Exception as e:
print('Error:{}'.format(e))
print(item["prate"])
item["pperiod"] = data[3]
item["pfloor"] = data[4]
yield item
def parseacb(self, response):
print("抓取安存宝")
products = response.xpath('//tr[@class="acb_table"]')
print(len(products))
for pro in products:
procon = pro.xpath('./td')
endtime = procon[2].xpath('./span')[1].xpath(
'string(.)').extract()[0]
if self.now() < endtime:
print(endtime, "未过期")
item = FundsInfoItem()
item["pname"] = procon[0].xpath('./a/@title').extract()[0]
# item["pid"]
item["prate"] = procon[5].xpath('string(.)').extract()[0]
item["pperiod"] = procon[4].xpath('string(.)').extract()[0]
item["pfloor"] = procon[3].xpath('string(.)').extract(
)[0] + procon[1].xpath('string(.)').extract()[0]
yield item
else:
print(endtime, "已过期")
def parse_pdf(self, response):
print(response.url)
filename = 'pdf/' + response.url.split('/')[-1]
f = open(filename, 'wb')
f.write(response.body)
f.close()
pdf = pdfplumber.open(filename)
p0 = pdf.pages[0] #注意此处的pages是一个列表，索引是从0开始的
table = p0.extract_table()
item = FundsInfoItem()
item["pid"] = "".join(table[2][1].split())
item["pname"] = table[1][1]
item["prate"] = table[11][1]
item["pperiod"] = table[10][1]
item["pfloor"] = "".join(table[5][1].split())
item['pscale'] = "".join(table[4][1].split())
yield item
def parse(self, response):
# print "打印response"
datas = response.xpath('//ol/li[@name="pageli"]')
# print len(datas)
# print datas[0].xpath('./div/p/a/text()').extract()[0].encode("utf-8")
# print datas[0].xpath('normalize-space(./div/div[@class="box_lf"]/p[@class="box_num"]/text())').extract()[0]
# print datas[0].xpath('./div/ul/li/span[@class="amt"]/text()').extract()[0].encode("utf-8")+'万'
# print datas[0].xpath('normalize-space(./div/ul/li/span[@class="highlight"]/text())').extract()[0].encode("utf-8")
for data in datas:
item = FundsInfoItem()
# item["pid"] =
item["pname"] = data.xpath('./div/p/a/text()').extract()[0]
item["prate"] = data.xpath(
'normalize-space(./div/div[@class="box_lf"]/p[@class="box_num"]/text())'
).extract()[0]
item["pperiod"] = data.xpath(
'normalize-space(./div/ul/li/span[@class="highlight"]/text())'
).extract()[0]
item["pfloor"] = data.xpath(
'./div/ul/li/span[@class="amt"]/text()').extract()[0] + '0000'
yield item
def parse5(self, response):
# print "打印response"
# print len(response.xpath('//div[@class="lccp_main_content_tx"]/ul/li'))
# datas = response.xpath('//div[@class="lccp_main_content_tx"]/ul/li')
datas = response.xpath(
'//div[@class="lccp_main_content_lb"]/table/tbody/tr')
# print len(datas)
for data in datas[1:]:
item = FundsInfoItem()
temp = data.xpath('./td')
# print len(temp)
item["pid"] = temp[0].xpath(
'./a/@data-analytics-click').extract()[0].split('-')[-1]
item["pname"] = temp[0].xpath(
'normalize-space(./a/text())').extract()[0]
item["prate"] = temp[5].xpath(
'normalize-space(./div/span/text())').extract()[0]
item["pperiod"] = temp[4].xpath(
'normalize-space(./text())').extract()[0]
item["pfloor"] = temp[3].xpath(
'normalize-space(./text())').extract()[0]
yield item
def parsein(self, response):
# print "内部网页"
indatas = response.xpath('//tr')
item = FundsInfoItem()
for data in indatas:
if u'产品名称' in data.xpath('./th/text()').extract()[0]:
# print "产品名称"
item["pname"] = data.xpath(
'normalize-space(./td/text())').extract()[0]
if u'产品代码' in data.xpath('./th/text()').extract()[0]:
# print "产品代码"
item["pid"] = data.xpath(
'normalize-space(./td/text())').extract()[0]
if u'预计年化收益率' in data.xpath('./th/text()').extract()[0]:
# print "预计年化收益率"
item["prate"] = data.xpath(
'normalize-space(./td/text())').extract()[0]
if u'起点金额' in data.xpath('./th/text()').extract()[0]:
# print "起点金额"
item["pfloor"] = data.xpath(
'normalize-space(./td/text())').extract()[0]
if u'投资期限' in data.xpath('./th/text()').extract()[0]:
# print "投资期限"
item["pperiod"] = data.xpath(
'normalize-space(./td/text())').extract()[0]
url = response.xpath('//ul[@class="title-ul"]/li/a')
# print len(url)
# yield item
if len(url) < 1:
item["pscale"] = "not found"
yield item
else:
pdfUrl = url.xpath('@href').extract()[0]
# print pdfUrl
yield scrapy.FormRequest(url=pdfUrl,
method='GET',
meta={"item": item},
callback=self.get_scale)
def parse(self, response):
# print "内部网页"
# print response.body
indatas = response.xpath('//tbody/tr')
for data in indatas:
item = FundsInfoItem()
item["pname"] = data.xpath('./td')[1].xpath(
'./text()').extract()[0]
item["pid"] = data.xpath('./td')[0].xpath('./text()').extract()[0]
item["prate"] = data.xpath('./td')[3].xpath(
'./text()').extract()[0]
item["pfloor"] = data.xpath('./td')[4].xpath(
'./text()').extract()[0]
item["pperiod"] = data.xpath('./td')[2].xpath(
'./text()').extract()[0]
yield item
def parse(self, response):
begin = re.search('jsonpCallback', response.text).end()
datas = json.loads(response.text[begin + 1:-1])['ProdList']
for data in datas:
item = FundsInfoItem()
item["pid"] = data['code']
item["pname"] = data['name']
item["prate"] = data['yieldRate']
item["pperiod"] = data['investPeriod']
item["pfloor"] = data['purFloorAmt']
# item["pscale"] = data['instructionUrl']
if item["prate"] == 0.0:
item["prate"] = self.get_ccb_detail_rate(item['pid'])
if item["prate"] == 'html中无法获取到收益率':
# 试图从子页面抓取最新收益率
url = r'http://finance.ccb.com/cc_webtran/queryFinanceProdDetail.gsp?'
headers = {
'User-Agent':
r'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:61.0) Gecko/20100101 Firefox/61.0',
'Referer':
r'http://finance.ccb.com/cn/finance/product.html',
'Connection': 'keep-alive'
}
data = {
'jsoncallback':
'jQuery191036942510719116894_1533864732025',
'params.code': item["pid"]
}
yield scrapy.FormRequest(url=url,
method='POST',
headers=headers,
formdata=data,
meta={"item": item},
callback=self.find_pdf)
else:
yield item
def parse(self, response):
# print "内部网页"
# print response.body
indatas = response.xpath('//tr[@class="bg2"]')
# print len(indatas)
# item = FundsInfoItem()
# item["pid"] = "test"
for data in indatas:
item = FundsInfoItem()
item["pname"] = data.xpath(
'normalize-space(./td[@class="name"]/a/text())').extract()[0]
item["pid"] = data.xpath('./td[@class="name"]/a/@href').extract(
)[0].split('productno=')[-1]
item["prate"] = data.xpath('./td')[4].xpath(
'./b/text()').extract()[0]
item["pfloor"] = data.xpath('./td')[3].xpath(
'./text()').extract()[0]
item["pperiod"] = data.xpath('./td')[2].xpath(
'normalize-space(./text())').extract()[0]
yield item
def parse(self, response):
# print "内部网页"
# print response.body
tables = response.xpath('//table')
# print len(indatas)
for table in tables:
floor = 5
rate = 6
period = 4
table_head = table.xpath('./thead')
if len(table_head)>0:
for data in table.xpath('./tbody/tr'):
item = FundsInfoItem()
item["pname"] = data.xpath('./td')[0].xpath('string(.)').extract()[0]
item["pid"] = data.xpath('./td')[-1].xpath('./img/@src').extract()[0].split('lccp')[-1].split('.')[0]
item["prate"] = data.xpath('./td')[rate].xpath('./text()').extract()[0]
item["pfloor"] = data.xpath('./td')[floor].xpath('./text()').extract()[0]
item["pperiod"] = data.xpath('./td')[period].xpath('./text()').extract()[0]
yield item
else:
table_title = table.xpath('./tbody/tr')[0].xpath('./td')
for i in range(len(table_title)):
title = table_title[i].xpath('string(.)').extract()[0]
# print title
if u'起购' in title:
floor = i
elif u'客户年化' in title or u'比较基准' in title or u'客户参考浮动年化净收益率' in title:
rate = i
elif u'天' in title:
period = i
for data in table.xpath('./tbody/tr')[1:]:
item = FundsInfoItem()
item["pname"] = data.xpath('./td')[0].xpath('string(.)').extract()[0]
item["pid"] = data.xpath('./td')[-1].xpath('./img/@src').extract()[0].split('lccp')[-1].split('.')[0]
item["prate"] = data.xpath('./td')[rate].xpath('./text()').extract()[0]
if item['prate'] == '以我行网站刊登的参考收益率公告为准':
try:
html_id = '201' + str(item["pid"][-4:-1])
if html_id == '201201':
html_id = '201203'
inner_url_1 = 'http://wealth.cib.com.cn/retail/duration/cash/referNetValue/' + html_id + '/' + \
html_id + '.html'
res = urllib.request.urlopen(inner_url_1)
inner_html_1 = res.read().decode('utf-8')
re_1 = '(/retail/duration/cash/referNetValue/' + html_id + '/'\
+ html_id + '_[\d]*.html)'
inner_url_2 = re.search(re_1, inner_html_1).group()
inner_url_2 = 'http://wealth.cib.com.cn' + inner_url_2
res_2 = urllib.request.urlopen(inner_url_2)
inner_html_2 = res_2.read().decode('utf-8')
re_2 = '<td>([\d\.]*%)</td>'
final = re.search(re_2, inner_html_2).group(1)
item['prate'] = final
except Exception as e:
print('errorinfo:{}'.format(e))
item['prate'] = '未能在子页面获取到收益'
item["pfloor"] = data.xpath('./td')[floor].xpath('./text()').extract()[0]
item["pperiod"] = data.xpath('./td')[period].xpath('./text()').extract()[0]
for sub_item_key in item.keys():
item[sub_item_key] = str(item[sub_item_key]).replace('\r', '').replace('\n', '')\
.replace('\t', '').strip()
print(item[sub_item_key])
yield item
