def parse_manager_detail(self, response):
item = response.meta.get("item")
manager_id, manager_name, company_id, company_name = item.get(
"manager_id"), item.get("manager_name"), item.get(
"company_id"), item.get("company_name")
response = etree.HTML(response.text)
fund_list = response.xpath("//div[@class='content_in']//tbody/tr")
for fund in fund_list:
item = dict()
item["manager_id"] = manager_id
item["manager_name"] = manager_name
item["company_id"] = company_id
item["company_name"] = company_name
item["avatar"] = response.xpath("//img[@id='photo']/@src")[0]
item["start_day"] = response.xpath(
"//div[@class='right jd ']/text()")[3].strip()
item["scale"] = response.xpath(
"//div[@class='gmleft gmlefts ']//span[@class='redText']/text()"
)[0]
item["scale"] = eval(item["scale"])
item["best_reward"] = response.xpath(
"//div[@class='gmleft']//span[@class='numtext']/span/text()"
)[0]
item["description"] = response.xpath(
"//div[@class='jlinfo clearfix']/div[@class='right ms']/p//text()"
)[-1].strip()
item["fund_id"] = "\t" + fund.xpath("./td[1]/a/text()")[0]
item["fund_name"] = fund.xpath("./td[2]/a/text()")[0]
save_item_in_csv(item, "manager_{}.csv".format(str_now_day),
self.title_num)
self.title_num = 1
print(item)
def parse_fund_earning_perday(self, response):
item = response.meta.get("item")
code = item.get("code")
fund_type = item.get("fund_type")
name = item.get("name")
response = response.text
data = re.findall(r'\((.*?)\)$', response)[0]
data = json.loads(data)
for i in data.get("Data").get("LSJZList"):
item = {
"fund_type": fund_type,
"code": code,
"name": name,
"date": i.get("FSRQ"),
"total_day": data.get("TotalCount"),
"net_value": i.get("DWJZ"),
"accumulative_value": i.get("LJJZ"),
"rate_day": i.get("JZZZL"),
"buy_status": i.get("SGZT"),
"sell_status": i.get("SHZT"),
"profit": i.get("FHSP")
}
print(item), save_item_in_csv(
item, "fund_earning_perday_{}.csv".format(str_now_day),
self.title_num_2_1)
self.title_num_2_1 = 1
def parse_fund_basic_info(self, response):
item = response.meta.get("item")
code = item.get("code")
response = etree.HTML(response.text)
item = {"full_name": response.xpath("//th[text()='基金全称']/../td[1]/text()"), "code": code,
"fund_url": 'http://fundf10.eastmoney.com/jbgk_{}.html'.format(code.strip()),
"type": response.xpath("//th[text()='基金类型']/../td[2]/text()"),
"publish_date": response.xpath("//th[text()='发行日期']/../td[1]/text()"),
"setup_date_and_scale": response.xpath("//th[text()='成立日期/规模']/../td[2]/text()"),
"asset_scale": response.xpath("//th[text()='资产规模']/../td[1]/text()"),
"amount_scale": response.xpath("//th[text()='份额规模']/../td[2]/a/text()"),
"company": response.xpath("//th[text()='基金管理人']/../td[1]/a/text()"),
"company_url": response.xpath("//th[text()='基金管理人']/../td[1]/a/@href"),
"bank": response.xpath("//th[text()='基金托管人']/../td[2]/a/text()"),
"bank_url": response.xpath("//th[text()='基金托管人']/../td[2]/a/@href"),
"manager": response.xpath("//th[text()='基金经理人']/../td[1]//a/text()"),
"manager_url": response.xpath("//th[text()='基金经理人']/../td[1]//a/@href"),
"profit_situation": response.xpath("//th[text()='基金经理人']/../td[2]/a/text()"),
"management_feerate": response.xpath("//th[text()='管理费率']/../td[1]/text()"),
"trustee_feerate": response.xpath("//th[text()='托管费率']/../td[2]/text()"),
"standard_compared": response.xpath("//th[text()='业绩比较基准']/../td[1]/text()"),
"followed_target": response.xpath("//th[text()='跟踪标的']/../td[2]/text()")}
for i_name in ["full_name", "type", "publish_date", "setup_date_and_scale", "asset_scale", "amount_scale",
"company", "company_url", "bank", "bank_url", "manager", "manager_url", "profit_situation",
"management_feerate", "trustee_feerate", "standard_compared", "followed_target"]:
item[i_name] = item[i_name][0] if len(item[i_name]) > 0 else None
for i in ["company_url", "bank_url", "manager_url"]:
item[i] = "http:" + item[i]
print(item), save_item_in_csv(item, "fund_basic_info_{}.csv".format(str_now_day), self.title_num_2_2)
self.title_num_2_2 = 1
def parse_company_fundscale(self, response):
item = response.meta.get("item")
company_code = item.get("company_code")
company_shortName = item.get("company_shortName")
response = etree.HTML(response.body.decode())
item = {
"company_code": company_code,
"company_shortName": company_shortName,
"fund_type": response.xpath("//tr[1]/th[2]/span/text()"),
"fund_scale": response.xpath("//tr[2]/td[2]/text()"),
"fund_scale_mean": response.xpath("//tr[2]/td[3]/text()"),
"fund_scale_rank": response.xpath("//tr[2]/td[4]/text()"),
"fund_amount": response.xpath("//tr[3]/td[2]/text()"),
"fund_amount_mean": response.xpath("//tr[3]/td[3]/text()"),
"fund_amount_rank": response.xpath("//tr[3]/td[4]/text()"),
"fund_manager_amount": response.xpath("//tr[4]/td[2]/text()"),
"fund_manager_amount_mean": response.xpath("//tr[4]/td[3]/text()"),
"fund_manager_amount_rank": response.xpath("//tr[4]/td[4]/text()")
}
for i_name in [
'fund_type', 'fund_scale', 'fund_scale_mean',
'fund_scale_rank', 'fund_amount', 'fund_amount_mean',
'fund_amount_rank', 'fund_manager_amount',
'fund_manager_amount_mean', 'fund_manager_amount_rank'
]:
item[i_name] = item[i_name][0] if len(item[i_name]) > 0 else None
print(item), save_item_in_csv(
item, "company_fundscale_{}.csv".format(str_now_day),
self.title_num_2_2)
self.title_num_2_2 = 1
def parse_fund_position(self, response):
item = response.meta.get("item")
code = item.get("code")
fund_type = item.get("fund_type")
name = item.get("name")
response = response.body.decode()
response = re.findall(r'var apidata={ content:(.*?),arryear', response)[0]
response = etree.HTML(response)
div_list = response.xpath("//div[@class='boxitem w790']")
for div in div_list:
label = div.xpath(".//label[@class='left']/text()")[0].strip()
time_1 = div.xpath(".//label[@class='right lab2 xq505']/font/text()")[0].strip()
tr_list = div.xpath(".//table[@class='w782 comm tzxq']/tbody/tr")
for tr in tr_list:
# 单位万股，万元
item = {"code": code, "name": name, "fund_type": fund_type, "label": label, "time": time_1,
"stock_code": "\t" + tr.xpath("./td[2]/a/text()")[0], # 为了把0开头的存入，加tab
"stock_name": tr.xpath("./td[3]/a/text()"),
"stock_proportion": tr.xpath("./td[last()-2]/text()"), # 持仓占净值比例
"stock_amount": tr.xpath("./td[last()-1]/text()"), # 持仓股数，万股
"stock_value": tr.xpath("./td[last()]/text()")} # 持仓市值，万元
for i_name in ["stock_name", "stock_proportion", "stock_amount", "stock_value"]:
item[i_name] = item[i_name][0] if len(item[i_name]) > 0 else None
print(item), save_item_in_csv(item, "fund_stock10_{}.csv".format(str_now_day), self.title_num_2_3)
self.title_num_2_3 = 1
def parse(self, response):
response = response.text
response = re.findall(r'=(.*?)$', response)[0]
response = json.loads(response)
for i in response.get("data"):
item = dict()
item["marketType"] = i.get("MarketType")
item["datetime"] = i.get("DetailDate")
item["datetime"] = item["datetime"].replace('T00:00:00', '')
item["total_net_in"] = round(i.get("DRCJJME") / 100, 2) # 当日成交净买额
item["total_in"] = round(i.get("MRCJE") / 100, 2) # 买入成交额
item["total_out"] = round(i.get("MCCJE") / 100, 2) # 卖出成交额
item["today_in"] = round(i.get("DRZJLR") / 100,
2) # 当日资金流入 同花顺是这个！包含了当日成交净买额 + 申报未成交的部分
item["grand_total_in"] = round(i.get("LSZJLR") / 100,
2) # 历史资金累计流入 当日资金流入的合计
item["today_balance"] = round(i.get("DRYE") / 100, 2) # 当日余额
item["stock_code"] = "\t" + i.get("LCGCode")
item["stock"] = i.get("LCG")
item["stock_up"] = round(i.get("LCGZDF"), 2)
item["sz_index"] = i.get("SSEChange")
item["sz_index_percent"] = round(
i.get("SSEChangePrecent") * 100, 2)
print(item), save_item_in_csv(
item, "beixiang_{}.csv".format(str_now_day), self.title_num)
self.title_num = 1
def parse(self, response):
response = response.text
# data1 沪股通十大成交股
data1 = re.findall(r'var DATA1 = (.*?);', response)[0]
data1 = json.loads(data1)
for i in data1.get("data"):
item = dict()
item["marketType"] = str(int(i.get("MarketType")))
item["date_time"] = i.get("DetailDate")
item["date_time"] = item["date_time"].replace('T00:00:00', '')
item["rank"] = str(int(i.get("Rank")))
item["code"] = i.get("Code")
item["name"] = i.get("Name")
item["close"] = i.get("Close")
item["changePercent"] = i.get("ChangePercent")
# 单位亿，净买入，买入，卖出，成交额（买+卖）
item["net_in"] = round(i.get("HGTJME") / 100000000, 2)
item["in"] = round(i.get("HGTMRJE") / 100000000, 2)
item["out"] = round(i.get("HGTMCJE") / 100000000, 2)
item["total"] = round(i.get("HGTCJJE") / 100000000, 2)
print(item), save_item_in_csv(
item, "beixiang_10stock_{}.csv".format(str_now_day),
self.title_num_1)
self.title_num_1 = 1
# data2 深股通十大成交股
data2 = re.findall(r'var DATA2 = (.*?);', response)[0]
data2 = json.loads(data2)
for i in data2.get("data"):
item = dict()
item["marketType"] = str(int(i.get("MarketType")))
item["date_time"] = i.get("DetailDate")
item["date_time"] = item["date_time"].replace('T00:00:00', '')
item["rank"] = str(int(i.get("Rank")))
item["code"] = i.get("Code")
item["name"] = i.get("Name")
item["close"] = i.get("Close")
item["changePercent"] = i.get("ChangePercent")
# 单位亿，净买入，买入，卖出，成交额（买+卖）
item["net_in"] = round(i.get("SGTJME") / 100000000, 2)
item["in"] = round(i.get("SGTMRJE") / 100000000, 2)
item["out"] = round(i.get("SGTMCJE") / 100000000, 2)
item["total"] = round(i.get("SGTCJJE") / 100000000, 2)
print(item), save_item_in_csv(
item, "beixiang_10stock_{}.csv".format(str_now_day),
self.title_num_1)
self.title_num_1 = 1
def parse_company_info(self, response):
item = response.meta.get("item")
company_code = item.get("company_code")
company_shortName = item.get("company_shortName")
response = etree.HTML(response.body.decode())
item = {
"company_code":
company_code,
"company_shortName":
company_shortName,
"company_name":
response.xpath("//p[@class='ttjj-panel-main-title']/text()"),
"position":
response.xpath(
"//div[@class='firm-contact clearfix']/div[1]/p[1]/label/text()"
),
"general_manager":
response.xpath(
"//div[@class='firm-contact clearfix']/div[1]/p[2]/label/text()"
),
"website_url":
response.xpath(
"//div[@class='firm-contact clearfix']/div[2]/p[1]/label/text()"
),
"tell":
response.xpath(
"//div[@class='firm-contact clearfix']/div[2]/p[2]/label/text()"
),
"manager_total_asset":
response.xpath("//a[text()='管理规模']/../label/text()"),
"fund_amount":
response.xpath(
"//div[@class='fund-info']/ul/li[2]/label/a/text()"),
"manager_amount":
response.xpath(
"//div[@class='fund-info']/ul/li[3]/label/a/text()"),
"publish_date":
response.xpath("//div[@class='fund-info']/ul/li[5]/label/text()"),
"company_property":
response.xpath("//div[@class='fund-info']/ul/li[6]/label/text()")
[0].strip()
}
for i_name in [
'company_name', 'position', 'general_manager', 'website_url',
'tell', 'manager_total_asset', 'fund_amount', 'manager_amount',
'publish_date'
]:
item[i_name] = item[i_name][0] if len(item[i_name]) > 0 else None
print(item), save_item_in_csv(
item, "company_info_{}.csv".format(str_now_day),
self.title_num_2_1)
self.title_num_2_1 = 1
def parse_company_industry_category(self, response):
item = response.meta.get("item")
company_code = item.get("company_code")
company_shortName = item.get("company_shortName")
response = etree.HTML(response.body.decode())
tr_list = response.xpath("//div[@id='contentWrap']/div[2]//tbody[1]/tr")[1:] # 第一个是标题，不要
for tr in tr_list:
item = {"company_code": company_code,
"company_shortName": company_shortName,
"industry_category": tr.xpath("./td[2]/text()")[0],
"havein_mycomanpy_fund": tr.xpath("./td[4]/a/text()")[0],
"hold_in_value": tr.xpath("./td[5]/text()")[0], "stock_value": tr.xpath("./td[6]/text()")[0]}
print(item), save_item_in_csv(item, "company_industry_category_{}.csv".format(str_now_day),
self.title_num_2_5)
self.title_num_2_5 = 1
def parse_company_fundList(self, response):
item = response.meta.get("item")
company_code = item.get("company_code")
company_shortName = item.get("company_shortName")
response = etree.HTML(response.body.decode())
tr_list = response.xpath("//tbody/tr")
for tr in tr_list:
item = {"company_code": company_code,
"company_shortName": company_shortName,
"fund_name": tr.xpath("./td/a[1]/text()"),
"fund_code": tr.xpath("./td/a[2]/text()")}
item["fund_name"] = item["fund_name"][0] if len(item["fund_name"]) > 0 else None
item["fund_code"] = "\t" + tr.xpath("./td/a[2]/text()")[0] if len(item["fund_code"]) > 0 else None
print(item), save_item_in_csv(item, "company_fund_list_{}.csv".format(str_now_day), self.title_num_2_3)
self.title_num_2_3 = 1
def parse(self, response):
fund_type = re.findall(r'kf&ft=(.*?)&rs=&gs=0&sc=zzf&st=desc', response.url)[0]
response = response.text
response = re.findall(r"var rankData = (.*?);$", response)[0]
response = re.findall(r"\[(.*?)]", response)[0]
fund_list = response.split('"')
fund_list = [i for i in fund_list if i != ""]
fund_list = [i for i in fund_list if i != ","]
for fund in fund_list:
f = fund.split(",")
# 为了把0开头的存入，加tab
item = {"fund_type": fund_type, "code": "\t" + f[0], "name": f[1], "today": f[3], "net_value": f[4],
"accumulative_value": f[5], "rate_day": f[6], "rate_recent_week": f[7], "rate_recent_month": f[8],
"rate_recent_3month": f[9], "rate_recent_6month": f[10], "rate_recent_year": f[11],
"rate_recent_2year": f[12], "rate_recent_3year": f[13], "rate_from_this_year": f[14],
"rate_from_begin": f[15], "rate_buy": f[20]}
item["url"] = "http://fund.eastmoney.com/" + item["code"] + ".html"
print(item), save_item_in_csv(item, "fund_earning_list_{}.csv".format(str_now_day), self.title_num_1)
self.title_num_1 = 1
# 2.1基金成立以来每日净值
if self.need_fund_earning_perday:
yield scrapy.Request(
"http://api.fund.eastmoney.com/f10/lsjz?callback=jQuery183036648984792081185_1575425405289&"
"fundCode={}"
"&pageIndex=1&pageSize=20".format(item.get("code").strip()), # pageSize写2万一次加载完。一个月就写20。
headers={"Referer": "http://fundf10.eastmoney.com"},
callback=self.parse_fund_earning_perday,
meta={"item": item},
)
# 2.2基金基本信息
if self.need_fund_basic_info:
yield scrapy.Request(
"http://fundf10.eastmoney.com/jbgk_{}.html".format(item["code"].strip()),
callback=self.parse_fund_basic_info,
meta={"item": item},
)
# 2.3基金10大持仓股(指定按年)
if self.need_fund_position:
for year in ["2020", "2021"]:
yield scrapy.Request(
"http://fundf10.eastmoney.com/FundArchivesDatas.aspx?type=jjcc&code={}&topline=10&year={}"
"&month=".format(item["code"].strip(), year),
callback=self.parse_fund_position,
meta={"item": item},
)
def parse_company_10stock(self, response):
item = response.meta.get("item")
company_code = item.get("company_code")
company_shortName = item.get("company_shortName")
response = etree.HTML(response.body.decode())
tr_list = response.xpath("//div[@id='contentWrap']/div[2]//tbody[1]/tr")
for tr in tr_list:
item = dict()
item["company_code"] = company_code
item["company_shortName"] = company_shortName
item["stock_code"] = tr.xpath("./td[2]/a/text()")[0]
item["stock_code"] = "\t" + item["stock_code"]
item["stock_name"] = tr.xpath("./td[3]/a/text()")[0]
item["havein_mycomanpy_fund"] = tr.xpath("./td[5]/a/text()")[0] # 本公司持有基金数
item["hold_in_value"] = tr.xpath("./td[6]/text()")[0] # 占总净值比例
item["stock_amount"] = tr.xpath("./td[7]/text()")[0] # 持股数(万股)
item["stock_value"] = tr.xpath("./td[8]/text()")[0] # 持仓市值(万元)
print(item), save_item_in_csv(item, "company_10stock_{}.csv".format(str_now_day), self.title_num_2_4)
self.title_num_2_4 = 1
def parse(self, response):
response = re.findall(r'\((.*?)\);$', response.text)[0]
response = json.loads(response)
for i in response.get("data").get("klines"):
item = {
"code": response.get("data").get("code"),
"name": response.get("data").get("name"),
"datetime": i.split(",")[0],
"price_start": i.split(",")[1],
"price_end": i.split(",")[4],
"price_max": i.split(",")[3],
"amount": i.split(",")[5],
"value": i.split(",")[6],
"swing": i.split(",")[7]
}
print(item), save_item_in_csv(
item, "market_index_{}.csv".format(str_now_day),
self.title_num_1)
self.title_num_1 = 1
def parse_company_industry_category(self, response):
item = response.meta.get("item")
company_code = item.get("company_code")
company_shortName = item.get("company_shortName")
response = etree.HTML(response.body.decode())
tr_list = response.xpath(
"//table[@class='ttjj-table ttjj-table-hover']//tr")[1:] # [1:]去标题
for tr in tr_list:
item = {
"company_code": company_code,
"company_shortName": company_shortName,
"industry_category": tr.xpath("./td[2]/text()")[0],
"havein_mycomanpy_fund": tr.xpath("./td[4]/a/text()")[0],
"hold_in_value_percent": tr.xpath("./td[5]/text()")[0],
"stock_value": tr.xpath("./td[6]/text()")[0]
}
print(item), save_item_in_csv(
item, "company_industry_category_{}.csv".format(str_now_day),
self.title_num_2_5)
self.title_num_2_5 = 1
def parse(self, response):
response = response.text
# data1 沪股通十大成交股
data1 = re.findall(r'var DATA1 = (.*?);', response)[0]
data1 = json.loads(data1)
for i in data1.get("data"):
item = dict()
item["marketType"] = str(int(i.get("MarketType")))
item["date_time"] = i.get("DetailDate")
item["date_time"] = item["date_time"].replace('T00:00:00', '')
item["rank"] = str(int(i.get("Rank")))
item["code"] = "\t" + i.get("Code")
item["name"] = i.get("Name")
item["close"] = i.get("Close")
item["changePercent"] = i.get("ChangePercent")
# 单位亿，净买入，买入，卖出，成交额（买+卖）
item["net_in"] = round(i.get("HGTJME") / 10**8, 2)
item["in"] = round(i.get("HGTMRJE") / 10**8, 2)
item["out"] = round(i.get("HGTMCJE") / 10**8, 2)
item["total"] = round(i.get("HGTCJJE") / 10**8, 2)
print(item), save_item_in_csv(
item, "beixiang_20stock_{}.csv".format(str_now_day),
self.title_num_1)
self.title_num_1 = 1
# data2 深股通十大成交股
data2 = re.findall(r'var DATA2 = (.*?);', response)[0]
data2 = json.loads(data2)
for i in data2.get("data"):
item = dict()
item["marketType"] = str(int(i.get("MarketType")))
item["date_time"] = i.get("DetailDate")
item["date_time"] = item["date_time"].replace('T00:00:00', '')
item["rank"] = str(int(i.get("Rank")))
item["code"] = "\t" + i.get("Code")
item["name"] = i.get("Name")
item["close"] = i.get("Close")
item["changePercent"] = i.get("ChangePercent")
# 单位亿，净买入，买入，卖出，成交额（买+卖）
item["net_in"] = round(i.get("SGTJME") / 10**8, 2)
item["in"] = round(i.get("SGTMRJE") / 10**8, 2)
item["out"] = round(i.get("SGTMCJE") / 10**8, 2)
item["total"] = round(i.get("SGTCJJE") / 10**8, 2)
print(item), save_item_in_csv(
item, "beixiang_20stock_{}.csv".format(str_now_day),
self.title_num_1)
self.title_num_1 = 1
# data3 港股通(沪)十大成交股
data3 = re.findall(r'var DATA3 = (.*?);', response)[0]
data3 = json.loads(data3)
# 若data3里面已经有了data4的数据,则跳过
item_dict = set()
for i in data3.get("data"):
item = dict()
# 基本信息
item["marketType"] = i.get("MarketType")
item["date_time"] = i.get("DetailDate")
item["date_time"] = item["date_time"].replace('T00:00:00', '')
item["rank"] = str(int(i.get("Rank")))
item["code"] = "\t" + i.get("Code")
item["name"] = i.get("Name")
item["close"] = i.get("Close")
item["changePercent"] = i.get("ChangePercent")
# 单位亿，净买入，买入，卖出，成交额（买+卖）
# 港股通（沪）
item["net_in_h"] = round(i.get("GGTHJME") / 10**8,
2) if i.get("GGTHJME") != "-" else 0
item["in_h"] = round(i.get("GGTHMRJE") /
10**8, 2) if i.get("GGTHMRJE") != "-" else 0
item["out_h"] = round(i.get("GGTHMCJE") /
10**8, 2) if i.get("GGTHMCJE") != "-" else 0
item["total_h"] = round(i.get("GGTHCJJE") / 10**8,
2) if i.get("GGTHCJJE") != "-" else 0
# 港股通（深）
item["net_in_s"] = round(i.get("GGTSJME") / 10**8,
2) if i.get("GGTSJME") != "-" else 0
item["in_s"] = round(i.get("GGTSMRJE") /
10**8, 2) if i.get("GGTSMRJE") != "-" else 0
item["out_s"] = round(i.get("GGTSMCJE") /
10**8, 2) if i.get("GGTSMCJE") != "-" else 0
item["total_s"] = round(i.get("GGTSCJJE") / 10**8,
2) if i.get("GGTSCJJE") != "-" else 0
# 港股通合计（沪+深）
item["net_in"] = round(i.get("GGTJME") /
10**8, 2) if i.get("GGTJME") != "-" else 0
item["total"] = round(i.get("GGTCJL") /
10**8, 2) if i.get("GGTCJL") != "-" else 0
print("data3", item), save_item_in_csv(
item, "nanxiang_20stock_{}.csv".format(str_now_day),
self.title_num_2)
self.title_num_2 = 1
item_dict.add(item.get("code"))
# data4 港股通(深)十大成交股
data4 = re.findall(r'var DATA4 = (.*?);', response)[0]
data4 = json.loads(data4)
for i in data4.get("data"):
item = dict()
# 若data3里面已经有了data4的数据,则跳过
if "\t" + i.get("Code") in item_dict:
continue
# 基本信息
item["marketType"] = i.get("MarketType")
item["date_time"] = i.get("DetailDate")
item["date_time"] = item["date_time"].replace('T00:00:00', '')
item["rank"] = str(int(
i.get("Rank"))) if i.get("Rank") != "-" else 0
item["code"] = "\t" + i.get("Code")
item["name"] = i.get("Name")
item["close"] = i.get("Close")
item["changePercent"] = i.get("ChangePercent")
# 单位亿，净买入，买入，卖出，成交额（买+卖）
# 港股通（沪）
item["net_in_h"] = round(i.get("GGTHJME") / 10**8,
2) if i.get("GGTHJME") != "-" else 0
item["in_h"] = round(i.get("GGTHMRJE") /
10**8, 2) if i.get("GGTHMRJE") != "-" else 0
item["out_h"] = round(i.get("GGTHMCJE") /
10**8, 2) if i.get("GGTHMCJE") != "-" else 0
item["total_h"] = round(i.get("GGTHCJJE") / 10**8,
2) if i.get("GGTHCJJE") != "-" else 0
# 港股通（深）
item["net_in_s"] = round(i.get("GGTSJME") / 10**8,
2) if i.get("GGTSJME") != "-" else 0
item["in_s"] = round(i.get("GGTSMRJE") /
10**8, 2) if i.get("GGTSMRJE") != "-" else 0
item["out_s"] = round(i.get("GGTSMCJE") /
10**8, 2) if i.get("GGTSMCJE") != "-" else 0
item["total_s"] = round(i.get("GGTSCJJE") / 10**8,
2) if i.get("GGTSCJJE") != "-" else 0
# 港股通合计（沪+深）
item["net_in"] = round(i.get("GGTJME") /
10**8, 2) if i.get("GGTJME") != "-" else 0
item["total"] = round(i.get("GGTCJL") /
10**8, 2) if i.get("GGTCJL") != "-" else 0
print("data4", item), save_item_in_csv(
item, "nanxiang_20stock_{}.csv".format(str_now_day),
self.title_num_2)
self.title_num_2 = 1
def parse(self, response):
response_url = response.url
# 沪股通十大成交股
if "MarketType=1" in response_url:
response = eval(response.text)
for i in response:
item = dict()
item = get_item(i, item)
item["rank"] = str(int(i.get("Rank")))
# 单位亿，净买入，买入，卖出，成交额（买+卖）
item["net_in"] = round(i.get("HGTJME") / 10 ** 8, 2)
item["in"] = round(i.get("HGTMRJE") / 10 ** 8, 2)
item["out"] = round(i.get("HGTMCJE") / 10 ** 8, 2)
item["total"] = round(i.get("HGTCJJE") / 10 ** 8, 2)
print("沪股通十大成交股:", item)
save_item_in_csv(item, "beixiang_10stock_{}.csv".format(str_now_day), self.title_num_1)
self.title_num_1 = 1
# 深股通十大成交股
elif "MarketType=3" in response_url:
response = eval(response.text)
for i in response:
item = dict()
item = get_item(i, item)
item["rank"] = str(int(i.get("Rank")))
# 单位亿，净买入，买入，卖出，成交额（买+卖）
item["net_in"] = round(i.get("SGTJME") / 10 ** 8, 2)
item["in"] = round(i.get("SGTMRJE") / 10 ** 8, 2)
item["out"] = round(i.get("SGTMCJE") / 10 ** 8, 2)
item["total"] = round(i.get("SGTCJJE") / 10 ** 8, 2)
print("深股通十大成交股:", item)
save_item_in_csv(item, "beixiang_10stock_{}.csv".format(str_now_day), self.title_num_1)
self.title_num_1 = 1
# 港股通（沪）十大成交股
elif "MarketType=2" in response_url:
response = eval(response.text)
for i in response:
item = dict()
item = get_item(i, item)
item["rank"] = str(int(i.get("Rank")))
# 单位亿，净买入，买入，卖出，成交额（买+卖）
item["net_in"] = round(i.get("GGTHJME") / 10 ** 8, 2)
item["in"] = round(i.get("GGTHMRJE") / 10 ** 8, 2)
item["out"] = round(i.get("GGTHMCJE") / 10 ** 8, 2)
item["total"] = round(i.get("GGTHCJJE") / 10 ** 8, 2)
print("港股通（沪）十大成交股:", item)
save_item_in_csv(item, "nanxiang_10stock_{}.csv".format(str_now_day), self.title_num_2)
self.title_num_2 = 1
# 港股通（深）十大成交股
elif "MarketType=4" in response_url:
response = eval(response.text)
for i in response:
item = dict()
item = get_item(i, item)
item["rank"] = str(int(i.get("Rank1")))
# 单位亿，净买入，买入，卖出，成交额（买+卖）
item["net_in"] = round(i.get("GGTSJME") / 10 ** 8, 2)
item["in"] = round(i.get("GGTSMRJE") / 10 ** 8, 2)
item["out"] = round(i.get("GGTSMCJE") / 10 ** 8, 2)
item["total"] = round(i.get("GGTSCJJE") / 10 ** 8, 2)
print("港股通（深）十大成交股:", item)
save_item_in_csv(item, "nanxiang_10stock_{}.csv".format(str_now_day), self.title_num_2)
self.title_num_2 = 1
