def parse_item(self, response):
fund_name = response.meta['ext']
rows = response.css('table#table1 tr')[1:]
for r in rows:
td = r.css('::text').extract()
row = [_.strip() for _ in td if _.strip()]
date = row[0]
nav = row[1]
add_nav = row[2]
item = GGFundNavItem()
item['sitename'] = self.sitename
item['fund_name'] = fund_name
item['channel'] = self.channel
item['statistic_date'] = datetime.strptime(date, '%Y-%m-%d')
item['nav'] = float(nav) if nav else None
item['added_nav'] = float(add_nav) if add_nav else None
yield item
def parse_item(self, response):
fund_name = response.meta['ext']['fund_name']
rows = response.xpath('//table/tr')
type = response.xpath('//table/tr[1]/th[2]/text()').extract()
for row in rows[1:]:
statistic_date = row.xpath('./td[1]/text()').extract_first()
if statistic_date is None or statistic_date == '':
continue
nav = row.xpath('./td[2]/text()').extract_first()
added_nav = row.xpath('./td[3]/text()').extract_first()
item = GGFundNavItem()
item['sitename'] = self.sitename
item['channel'] = self.channel
item['url'] = response.url
item['fund_name'] = fund_name
item['statistic_date'] = datetime.strptime(statistic_date, '%Y%m%d')
if '份额净值' in type:
item['nav'] = float(nav) if nav is not None else None
item['added_nav'] = float(added_nav) if added_nav is not None else None
elif '万份收益' in type:
item['income_value_per_ten_thousand'] = float(nav) if nav is not None and nav != '--' else None
item['annualized_return'] = float(added_nav.strip('%'))/100.0 if added_nav is not None and added_nav != '--' else None
yield item
if len(rows) > int(response.meta['form']['numPerPage']):
code = response.meta['ext']['fund_code']
pg = response.meta['form']['curPage']
pg = int(pg)+1
self.ips.append({
'url': 'https://ziguan.xcsc.com/servlet/asset/AssetManage',
'ref': response.url,
'form': {
'function': 'loadFundJz',
'fundcode': code,
'curPage': str(pg),
'numPerPage': '10',
'reqUrl': '/servlet/asset/AssetManage?function=loadFundJz&fundcode=' + code,
'_': '1526452208722'
},
'ext': {'fund_name': fund_name, 'fund_code': code}
})
def parse_item(self, response):
fund_name = response.xpath("//div[@class='col-md-9']/h4//text()").extract_first()
rows = response.xpath("//div[@id='value']//div")
for row in rows:
statistic_date = row.xpath("./div[@class='col-lg-4'][1]//text()").extract_first()
nav = row.xpath("./div[@class='col-lg-4'][2]//text()").extract_first()
added_nav = row.xpath("./div[@class='col-lg-4'][3]//text()").extract_first()
if statistic_date:
statistic_date = statistic_date.strip()
nav = nav.strip()
added_nav = added_nav.strip()
item = GGFundNavItem()
item['sitename'] = self.sitename
item['channel'] = self.channel
item['url'] = response.url
item['fund_name'] = fund_name
item['nav'] = float(nav) if nav is not None else None
item['added_nav'] = float(added_nav) if added_nav is not None else None
item['statistic_date'] = datetime.strptime(statistic_date, '%Y-%m-%d')
yield item
def parse_item(self, response):
rows = response.css('div.product_con:nth-child(2) tr')[1:]
for r in rows:
dt = r.css('td:nth-child(1) ::text').extract()
nav = r.css('td:nth-child(2) ::text').extract_first()
add_nav = r.css('td:nth-child(3) ::text').extract_first()
date = ''.join(dt)
item = GGFundNavItem()
item['sitename'] = self.sitename
item['fund_name'] = response.meta['ext']
item['channel'] = self.channel
item['url'] = response.url
item['nav'] = float(nav) if nav else None
item['added_nav'] = float(add_nav) if add_nav else None
item['statistic_date'] = datetime.strptime(
date, '%Y%m%d') if date else None
yield item
def parse_item(self, response):
funds = json.loads(response.text)[2]['data']
f_list = scrapy.Selector(text=funds).xpath('//table//tr')
for i in f_list[1:]:
t = i.xpath('td//text()').extract()
fund_name = t[0]
nav = t[1]
added_nav = t[2]
statistic_date = t[3]
item = GGFundNavItem()
item['sitename'] = self.sitename
item['channel'] = self.channel
item['url'] = response.url
item['fund_name'] = fund_name
item['statistic_date'] = datetime.strptime(statistic_date,
'%Y-%m-%d')
item['nav'] = float(nav) if nav is not None else None
item['added_nav'] = float(
added_nav) if added_nav is not None else None
yield item
def parse_item(self, response):
if response.status == 200:
rows = response.xpath(
'//div[contains(@class,"product_tab_sub")][3]//tr')
fund_name = response.meta['ext'].replace(':', '')
for r in rows[1:]:
date = r.css('td:nth-child(1)::text').re_first('\S+')
add_nav = r.css('td:nth-child(2)::text').re_first('\S+')
item = GGFundNavItem()
item['sitename'] = self.sitename
item['fund_name'] = fund_name
item['channel'] = self.channel
item['url'] = response.url
item['added_nav'] = float(add_nav.replace(
' ', '')) if add_nav else None
item['statistic_date'] = datetime.strptime(
date, '%Y/%m/%d') if date else None
yield item
def parse_item(self, response):
fund_name = response.xpath(
'//div[@id="tagContent2"]/table/tbody//tr[2]//p//font//text()').extract_first().strip()
rows = response.xpath('//div[@class="tagContent"]//table//tbody//tr')
for row in rows[6:]:
i = row.xpath("td//font//text()").extract()
i2 = [_ for _ in i if _.strip()]
if len(i2) > 3:
nav = i2[0].replace(',', '').replace(' ', '')
statistic_date = i2[3].replace(',', '')
item = GGFundNavItem()
item['sitename'] = self.sitename
item['channel'] = self.channel
item['url'] = response.url
item['fund_name'] = fund_name.replace('净值披露表', '')
item['statistic_date'] = datetime.strptime(statistic_date, '%Y-%m-%d')
item['nav'] = float(nav) if nav is not None else None
yield item
def parse_item(self, response):
fund_name = response.meta['ext']
fund_list = response.xpath(
'//div[@name ="data"]/div[@class = "nr_con"][1]//table[@class = "tab tab_01"]//tr'
)
for i in fund_list:
t = i.xpath('td//text()').extract()
statistic_date = ''.join(t[0].split())
nav = ''.join(t[1].split())
# 网站复权累计净值不抓取
item = GGFundNavItem()
item['sitename'] = self.sitename
item['channel'] = self.channel
item['url'] = response.url
item['fund_name'] = fund_name
item['statistic_date'] = datetime.strptime(statistic_date,
'%Y-%m-%d')
item['nav'] = float(nav)
yield item
def parse_item(self, response):
fund_info = response.text
wz1 = fund_info.find('{"result')
fund_info1 = fund_info[wz1:len(fund_info) - 1]
fund_info2 = json.loads(fund_info1)
productname_bf = fund_info2['result']['name']
for k, v in enumerate(fund_info2['result']['date']):
statistic_date = v
nav = fund_info2['result']['value'][k]
statistic_date = statistic_date.replace('/', '-')
item = GGFundNavItem()
item['sitename'] = self.sitename
item['channel'] = self.channel
item['url'] = response.url
item['fund_name'] = productname_bf
item['statistic_date'] = datetime.strptime(statistic_date,
'%Y-%m-%d')
item['nav'] = float(nav) if nav else None
yield item
def parse_item(self, response):
res_text = re.sub('[\s,]', '', response.text)
target_str = re.findall('单位净值报告(.*)深圳市金中和投资管理有限公司', res_text,
re.DOTALL)
if target_str:
rows = target_str[0].split('</TR>')
for tr in rows:
date = re.findall('\d{4}\.\d{2}\.\d{2}', tr, re.DOTALL)
nav = re.findall('[^\d\.](\d{2,3}\.\d{2})[^%]', tr, re.DOTALL)
if date:
item = GGFundNavItem()
item['sitename'] = self.sitename
item['fund_name'] = response.meta['ext']
item['channel'] = self.channel
item['url'] = response.url
item['nav'] = float(nav[0].strip()) if nav else None
item['statistic_date'] = datetime.strptime(
date[0].strip(), '%Y.%m.%d') if date else None
yield item
def parse_item(self, response):
fund_name = response.meta['ext']['fund_name']
rows = response.xpath('//table[@id="dateTR"]/tbody/tr')
for row in rows:
nav = row.xpath('./td[2]/text()').extract_first()
added_nav = row.xpath('./td[3]/text()').extract_first()
statistic_date = row.xpath('./td[1]/text()').extract_first()
item = GGFundNavItem()
item['sitename'] = self.sitename
item['channel'] = self.channel
item['url'] = response.url
item['fund_name'] = fund_name
item['nav'] = float(nav) if nav is not None else None
item['added_nav'] = float(
added_nav) if added_nav is not None else None
item['statistic_date'] = datetime.strptime(statistic_date,
'%Y-%m-%d')
yield item
def parse_item(self, response):
fund_name = response.xpath(
'//div[@class="pro_title"]/h1/text()').extract_first()
nav_rows = response.xpath('//div[@class="pj_table"]//tr')
for row in nav_rows[1:]:
nav_info = row.xpath('td/text()').extract()
statistic_date = nav_info[0].replace('/', '-')
nav = nav_info[1]
item = GGFundNavItem()
item['sitename'] = self.sitename
item['channel'] = self.channel
item['url'] = response.url
item['fund_name'] = fund_name.replace('（已结束）',
'').replace('（已成立）', '')
item['statistic_date'] = datetime.strptime(statistic_date,
'%Y-%m-%d')
item['nav'] = float(nav) if nav is not None else None
yield item
def parse_item(self, response):
rows = response.xpath('//tbody/tr')[1:] if response.xpath(
'//tbody/tr[1]/td[1]/text()').extract_first().strip(
) == '产品名称' else response.xpath(
'//table/tbody/tr/td[1]/table/tbody/tr')[1:]
for row in rows:
fund_name = row.xpath('./td[1]/text()').extract_first().strip()
statistic_date = row.xpath('./td[2]/text()').re_first(
'\d+/\d+/\d+')
nav = row.xpath('./td[3]/text()').re_first('[0-9.]+')
item = GGFundNavItem()
item['sitename'] = self.sitename
item['channel'] = self.channel
item['url'] = response.url
item['fund_name'] = fund_name
item['nav'] = float(nav)
item['statistic_date'] = datetime.strptime(statistic_date,
'%Y/%m/%d')
yield item
def parse_item(self, response):
rows = json.loads(response.text)
fund_name = response.meta['ext']['fund_name']
for row in rows:
stamp = row[0]
nav = row[1]
date = time.strftime("%Y-%m-%d", time.localtime(int(stamp) / 1000))
item = GGFundNavItem()
item['sitename'] = self.sitename
item['channel'] = self.channel
item['url'] = response.url
item['fund_name'] = fund_name
item['nav'] = float(nav) / 100
item['added_nav'] = None
item['statistic_date'] = datetime.strptime(date, '%Y-%m-%d')
yield item
yield self.request_next()
def parse_item(self, response):
fund_name = response.meta['ext']['fund_name']
rows = json.loads(response.text)['results']
for row in rows:
item = GGFundNavItem()
item['sitename'] = self.sitename
item['channel'] = self.channel
item['url'] = response.url
item['fund_name'] = fund_name
statistic_date = row['create_time']
item['statistic_date'] = datetime.strptime(statistic_date,
'%Y%m%d')
nav = row['relate_price']
item['nav'] = float(nav) if nav is not None else None
added_nav = row['cumulative_net']
item['added_nav'] = float(
added_nav) if added_nav is not None else None
yield item
def parse_item(self, response):
ext = response.meta['ext']
fund_name = ext['fund_name']
page = int(ext['page'])
base_url = ext['url']
rows = response.xpath('//td[@bgcolor="#ffffff"]')
if rows and len(rows) > 1:
rows = rows[1]
rows = rows.xpath('.//tr')
head_row = rows[0].xpath('./td/text()').re('\S+')
if rows and len(rows) > 1:
for row in rows[1:]:
item = GGFundNavItem()
item['sitename'] = self.sitename
item['fund_name'] = fund_name
item['channel'] = self.channel
item['url'] = response.url
statistic_date = row.xpath('./td[1]/text()').extract_first()
item['statistic_date'] = datetime.strptime(statistic_date, '%Y-%m-%d') if statistic_date else None
if head_row.count('单位净值') > 0:
nav = row.xpath('./td[2]/text()').extract_first()
item['nav'] = float(nav) if nav else None
if head_row.count('累计净值') > 0:
added_nav = row.xpath('./td[3]/text()').extract_first()
item['added_nav'] = float(added_nav) if added_nav else None
if head_row.count('每万份收益') > 0:
income_value_per_ten_thousand = row.xpath('./td[2]/text()').extract_first()
item['income_value_per_ten_thousand'] = float(
income_value_per_ten_thousand) if income_value_per_ten_thousand else None
if head_row.count('七日年化收益率') > 0:
d7_annualized_return = row.xpath('./td[3]/text()').re_first('(\d+\.?\d*)')
item['d7_annualized_return'] = float(d7_annualized_return) if d7_annualized_return else None
yield item
url = base_url + '&pagesize=10¤tPage=' + str(page + 1)
self.ips.append({
'url': url,
'ref': response.url,
'ext': {'page': str(page + 1), 'url': base_url, 'fund_name': fund_name}
})
def parse_item(self, response):
info_json = json.loads(response.text)
datas = info_json['results'][0]['data']
for data in datas:
fund_name = data['pro_name']
nav = data['nav']
add_nav = data['accumulativenav']
statistic_date = data['tradedate']
statistic_date = datetime.strptime(statistic_date, '%Y-%m-%d')
item = GGFundNavItem()
item['sitename'] = self.sitename
item['channel'] = self.channel
item['url'] = response.url
item['fund_name'] = fund_name
item['statistic_date'] = statistic_date
item['nav'] = float(nav) if nav is not None else None
item['added_nav'] = float(add_nav) if add_nav is not None else None
yield item
# 总页数
tp = info_json['results'][0]['totalPages']
# 当前页
cp = info_json['results'][0]['currentPage']
pro_code = response.meta['ext']['pro_code']
if int(cp) < int(tp):
cp = cp + 1
self.ips.append({
'url': 'http://www.iztzq.com/servlet/json',
'ref': response.url,
'form': {
'funcNo': '834013',
'code': pro_code,
'page': str(cp),
'numPerPage': '10'
},
'ext': {
'pro_code': pro_code
}
})
def parse_item(self, response):
fund_name = response.xpath(
'//div[@class="main"]/div[2]/div[1]/p/text()').extract_first()
nav_list = response.xpath('//div[@id="cat_2"]//table//tr')
for row in nav_list[2:]:
row_info = row.xpath('td//text()').extract()
if len(row_info) >= 3:
statistic_date = row_info[0]
nav = row_info[2]
item = GGFundNavItem()
item['sitename'] = self.sitename
item['channel'] = self.channel
item['url'] = response.url
item['fund_name'] = fund_name.replace('【期限已到】',
'').replace('【分红】', '')
item['statistic_date'] = datetime.strptime(
statistic_date, '%Y%m%d')
item['nav'] = float(nav) if nav is not None else None
yield item
def parse_item(self, response):
fund_name = response.meta['ext']['fund_name']
rows = response.css('table tr')
for row in rows:
td_text = row.css('td::text').extract_first()
if '日期' in td_text:
continue
statistic_date = row.css('td::text').extract_first()
nav = row.css('td span::text').extract_first()
item = GGFundNavItem()
item['sitename'] = self.sitename
item['channel'] = self.channel
item['url'] = response.url
item['fund_name'] = fund_name
item['statistic_date'] = datetime.strptime(statistic_date, '%Y-%m-%d')
item['nav'] = float(nav)
item['added_nav'] = None
yield item
yield self.request_next()
def parse_item(self, response):
nvList = json.loads(response.text)['data']
for eachNv in nvList:
item = GGFundNavItem()
item['sitename'] = self.sitename
item['channel'] = self.channel
item['url'] = response.url
ext = response.meta['ext']
item['fund_name'] = ext['fund_name']
init_date = eachNv['cdate']
item['statistic_date'] = datetime.strptime(init_date, '%Y-%m-%d')
nav = eachNv['per_netvalue']
item['nav'] = float(nav) if nav is not None else None
added_nav = eachNv['total_netvalue']
item['added_nav'] = float(
added_nav) if added_nav is not None else None
yield item
yield self.request_next()
def parse_item(self, response):
fund_name = response.xpath(
'//*[@id="show1"]/table//tr[1]/th[2]/text()').extract_first()
rows = response.xpath('//*[@id="show2"]/div[2]/table//tr')
for row in rows[1:]:
fund_date = row.xpath('./td[2]/text()').extract_first().strip()
nav = row.xpath('./td[3]/text()').extract_first().strip()
added_nav = row.xpath('./td[4]/text()').extract_first().strip()
item = GGFundNavItem()
item['sitename'] = self.sitename
item['channel'] = self.channel
item['url'] = response.url
item['fund_name'] = fund_name
item['statistic_date'] = datetime.strptime(fund_date, '%Y年%m月%d日')
item['nav'] = float(nav) if nav is not None else None
if added_nav is not None and added_nav.count(
'%') == 0 and added_nav != '-':
item['added_nav'] = float(
added_nav) if nav is not None else None
yield item
def parse_item(self, response):
fund_names = re.findall('"name" : "(.*?)",', response.text)
navs = re.findall('"unit" : "(.*?)",', response.text)
added_navs = re.findall('"accumulation" : "(.*?)",', response.text)
statistic_dates = re.findall('"date" : "(.*?)"', response.text)
for row in zip(fund_names, statistic_dates, navs, added_navs):
fund_name = row[0]
statistic_date = row[1]
nav = row[2]
added_nav = row[3]
item = GGFundNavItem()
item['sitename'] = self.sitename
item['channel'] = self.channel
item['url'] = response.url
item['fund_name'] = fund_name
item['nav'] = float(nav) if nav is not None else None
item['added_nav'] = float(
added_nav) if added_nav is not None else None
item['statistic_date'] = datetime.strptime(statistic_date,
'%Y/%m/%d')
yield item
def parse_item(self, response):
fps = response.meta['fps']
ips = response.meta['ips']
rows = response.xpath('//div[@id="history"]/table/tr')[2:]
for row in rows:
fund_name = row.xpath(r'./td[1]/text()').extract_first()
nav = row.xpath(r'./td[2]/text()').extract_first()
added_nav = row.xpath(r'./td[3]/text()').extract_first()
statistic_date = row.xpath("./td[4]/text()").extract_first()
item = GGFundNavItem()
item['sitename'] = self.sitename
item['channel'] = self.channel
item['url'] = response.url
item['fund_name'] = fund_name
item['nav'] = float(nav)
item['added_nav'] = float(added_nav)
item['statistic_date'] = datetime.strptime(statistic_date,
'%Y-%m-%d')
yield item
yield self.request_next(fps, ips)
def parse_item(self, response):
sitename = response.meta['ext']['sitename']
fund_name = response.meta['ext']['fund_name']
rows = response.xpath('//table[@class="table2"]/tr')[1:]
for row in rows:
item = GGFundNavItem()
item['sitename'] = sitename
item['channel'] = self.channel
item['url'] = response.url
item['fund_name'] = fund_name
statistic_date = row.xpath('./td[1]').re_first('\d+-\d+-\d+')
if statistic_date is None:
continue
item['statistic_date'] = datetime.strptime(statistic_date,
'%Y-%m-%d')
nav = row.xpath('./td[2]').re_first('>\s*([0-9.]+)\s*<')
item['nav'] = float(nav) if nav is not None else None
yield item
def parse_item(self, response):
rows = response.xpath("//div[@class='ff']//tr")
fund_name = response.meta['ext']['fund_name']
for row in rows:
statistic_dates = row.xpath("./td[1]//text()").extract()
statistic_date = ''.join(statistic_dates).replace('/', '-')
nav = row.xpath("./td[2]//text()").extract_first()
added_nav = row.xpath("./td[3]//text()").extract_first()
if '20' in statistic_date:
item = GGFundNavItem()
item['sitename'] = self.sitename
item['channel'] = self.channel
item['url'] = response.url
item['fund_name'] = fund_name
item['nav'] = float(nav) if nav is not None else None
item['added_nav'] = float(
added_nav) if nav is not None else None
item['statistic_date'] = datetime.strptime(
statistic_date, '%Y-%m-%d')
yield item
def parse_item(self, response):
rows = json.loads(response.text)['result']['value']
fund_name = json.loads(response.text)['fundName']
for row in rows:
item = GGFundNavItem()
item['sitename'] = self.sitename
item['channel'] = self.channel
item['url'] = 'http://www.reganfund.com/product.html'
item['fund_name'] = fund_name
statistic_date = row['tradingDate']
item['statistic_date'] = datetime.strptime(statistic_date,
'%Y-%m-%d')
nav = row['nav']
item['nav'] = float(nav) if nav is not None else None
added_nav = row['nav']
item['added_nav'] = float(
added_nav) if added_nav is not None else None
yield item
def parse_item(self, response):
fund_name = response.xpath('//h2//text()').extract_first()
navs = re.findall('var data1= \[(.*?)\];',
response.text)[0].replace('"', '').split(',')
added_navs = re.findall(r'var data2= \[(.*?)\];',
response.text)[0].replace('"', '').split(',')
statistic_dates = re.findall(r'var data3= \[(.*?)\];',
response.text)[0].replace('"',
'').split(',')
for nav, added_nav, statistic_date in zip(navs, added_navs,
statistic_dates):
item = GGFundNavItem()
item['sitename'] = self.sitename
item['channel'] = self.channel
item['url'] = response.url
item['fund_name'] = fund_name
item['nav'] = float(nav) if nav is not None else None
item['added_nav'] = float(added_nav) if nav is not None else None
item['statistic_date'] = datetime.strptime(statistic_date,
'%Y-%m-%d')
yield item
def parse_item(self, response):
fund_name = response.meta['ext']
nav_rows = response.xpath('//tr[@class="dd"]')
for row in nav_rows:
nav_info = row.xpath('td/text()').extract()
statistic_date = nav_info[1].replace(
'25016-6-3', '2016-6-3').replace('.', '-').strip()
nav = nav_info[2].strip()
added_nav = nav_info[3].replace('..', '.').strip()
item = GGFundNavItem()
item['sitename'] = self.sitename
item['channel'] = self.channel
item['url'] = response.url
item['fund_name'] = fund_name
item['statistic_date'] = datetime.strptime(
statistic_date, '%Y-%m-%d') if statistic_date else None
item['nav'] = float(nav) if nav else None
item['added_nav'] = float(added_nav) if added_nav else None
yield item
def parse_item(self, response):
rows = response.xpath('//table[@class="tab_01"]/tr')[1:]
for row in rows:
fund_name = row.xpath('./td[2]/text()').extract_first()
statistic_date = row.xpath('./td[3]/text()').re_first(
'\d+-\d+-\d+')
nav = row.xpath('./td[4]/text()').re_first('[0-9.]+')
added_nav = row.xpath('./td[5]/text()').re_first('[0-9.]+')
item = GGFundNavItem()
item['sitename'] = self.sitename
item['channel'] = self.channel
item['url'] = response.url
item['fund_name'] = fund_name
item['nav'] = float(nav) if nav is not None else None
item['added_nav'] = float(
added_nav) if added_nav is not None else None
item['statistic_date'] = datetime.strptime(statistic_date,
'%Y-%m-%d')
yield item
t_count = response.xpath(
'//div[@class="pages_ul_page33"]/ul/li[1]/text()').re_first(
'共有([\d]+)条记录')
tp = int(t_count) / 10 if int(
t_count) % 10 == 0 else int(t_count) // 10 + 1
pg = response.meta['pg'] + 1
if pg <= tp:
class_id = response.meta['form']['classid']
self.ips.append({
'url': 'http://www.ydsc.com.cn/ydzq/zcgl/cpjhjzList.jsp',
'form': {
'classid': class_id,
'pageIndex': str(pg),
'pageSize': '10',
'hrefURL': '',
'filter': ''
},
'pg': pg
})
def parse_item(self, response):
fund_code = response.meta['ext']['fund_code']
fund_name = response.meta['ext']['fund_name']
is_currency_type = response.meta['ext']['is_currency_type']
tpg = response.xpath('//*[@class="dtitle_t"]/table/tr/td/text()[1]').re_first('共\s*(\d+)\s*页')
page = response.meta['ext']['page']
table = response.xpath('//*[@id="dataTable"]')
rows = table.xpath(".//tr")
for row in rows[1:]:
item = GGFundNavItem()
item['sitename'] = self.sitename
item['channel'] = self.channel
item['url'] = response.url
item['fund_name'] = fund_name
statistic_date = row.xpath('./td[2]/text()').extract_first().strip()
item['statistic_date'] = datetime.strptime(statistic_date, '%Y-%m-%d')
if is_currency_type == '0': # 常规产品
nav = row.xpath('./td[3]/text()').extract_first().strip()
added_nav = row.xpath('./td[4]/text()').extract_first().strip()
item['nav'] = float(nav) if nav is not None else None
item['added_nav'] = float(added_nav) if added_nav is not None else None
if is_currency_type == '1': # 货币型产品
income_value_per_ten_thousand = row.xpath('./td[3]/text()').extract_first().strip()
d7_annualized_return = row.xpath('./td[4]/text()').extract_first().strip().replace('%', '')
item['income_value_per_ten_thousand'] = float(
income_value_per_ten_thousand) if income_value_per_ten_thousand is not None else None
item['d7_annualized_return'] = float(d7_annualized_return) if d7_annualized_return is not None else None
# self.log(item)
yield item
if tpg is not None:
page = int(page)
if page < int(tpg):
self.ips.append({
'url': 'http://www.gtsfund.com.cn/chart-web/chart/fundnettable?pages=' + str(
page + 1) + '-15&fundcode=' + fund_code + '&from=&to=',
'ref': response.url,
'ext': {'fund_code': fund_code, 'fund_name': fund_name, 'page': str(page + 1),
'is_currency_type': is_currency_type}
})
