def __get_data_fhpx(self):
response = requests.get(self.__url_fhpx)
if response.status_code == 200:
html = etree.HTML(response.text)
nodes = html.cssselect(
'body > div.area > div:nth-child(5) > table > tr')
self.fhpx_ggrq = [] # 公告日期
self.fhpx_years = [] # 分红派息年份
self.fhpx_sg = [] # 送股
self.fhpx_zz = [] # 转增
self.fhpx_px = [] # 派息
self.fhpx_cqcxr = [] # 除权除息日
for i, node in enumerate(nodes):
all_td = node.findall('td')
if len(all_td) == 1: # 暂无数据
break
self.fhpx_ggrq.append(all_td[0].text)
self.fhpx_years.append(all_td[1].text)
self.fhpx_sg.append(change_text(all_td[2].text, 0))
self.fhpx_zz.append(change_text(all_td[3].text, 0))
self.fhpx_px.append(change_text(all_td[4].text, 0))
self.fhpx_cqcxr.append(change_text(all_td[6].text,
to_type=str))
del response
gc.collect()
def __get_data_lrb(self):
df = pd.read_csv(self.__url_lrb, encoding=self.encoding)
self.lrb_years = [
ymd[:4] for ymd in df.columns.to_list()[1:]
if ymd.strip() != '' and ymd[:4].isdigit()
]
self.lrb_jlr_gm = [] # 归属于母公司所有者的净利润 CSV_LINE:42 DF_INDEX:40
self.lrb_jlr = [] # 净利润 CSV_LINE:41 DF_INDEX:39
self.lrb_yysr = [] # 营业收入 CSV_LINE:2 DF_INDEX:0
self.lrb_yysr_hj = [
] # 营业收入合计 CSV_LINE:3+4+5+6+7+8 DF_INDEX:1+2+3+4+5+6
self.lrb_yycb = [] # 营业成本 CSV_LINE:10 DF_INDEX:8
self.lrb_yycb_hj = [] # 营业成本合计 CSV_LINE:10~21 DF_INDEX:8~19
self.lrb_yylr = [] # 营业利润 CSV_LINE:34 DF_INDEX:32
self.lrb_mgyy = [] # 每股盈余 CSV_LINE:45 DF_INDEX:43
for year in self.lrb_years:
data = df[f'{year}-12-31']
self.lrb_jlr_gm.append(change_text(data[40], 0))
self.lrb_jlr.append(change_text(data[39], 0))
self.lrb_yysr.append(change_text(data[0], 0))
self.lrb_yysr_hj.append(sum([change_text(v, 0)
for v in data[1:7]]))
self.lrb_yycb.append(change_text(data[8], 0))
self.lrb_yycb_hj.append(
sum([change_text(v, 0) for v in data[8:20]]))
self.lrb_yylr.append(change_text(data[32], 0))
self.lrb_mgyy.append(change_text(data[43], 0))
del df
gc.collect()
def __get_data_gszl(self):
response = requests.get(self.__url_gszl)
if response.status_code == 200:
html = etree.HTML(response.text)
self.zzxs = change_text(html.xpath(
'/html/body/div[2]/div[4]/table/tr[1]/td[2]')[0].text,
to_type=str) # 组织形式
self.dy = html.xpath(
'/html/body/div[2]/div[4]/table/tr[1]/td[4]')[0].text # 地域
self.zwjc = html.xpath(
'/html/body/div[2]/div[4]/table/tr[2]/td[2]')[0].text # 中文简称
self.zwjc_py = pinyin(self.zwjc) # 中文简称_拼音首字母
self.gsqc = html.xpath(
'/html/body/div[2]/div[4]/table/tr[3]/td[2]')[0].text # 公司全称
comment = html.xpath('/html/body/div[2]/div[4]/table/comment()')[0]
comment = etree.fromstring(comment.text)
self.gswz = change_text(comment.xpath('/tr/td[2]')[0].text,
to_type=str) # 公司网站
self.zyyw = html.xpath(
'/html/body/div[2]/div[4]/table/tr[10]/td[2]')[0].text.strip(
) # 主营业务
self.jyfw = html.xpath(
'/html/body/div[2]/div[4]/table/tr[11]/td[2]')[0].text.strip(
) # 经营范围
self.clrq = change_text(html.xpath(
'/html/body/div[2]/div[5]/table/tr[1]/td[2]')[0].text,
to_type=str) # 成立日期
self.ssrq = change_text(html.xpath(
'/html/body/div[2]/div[5]/table/tr[2]/td[2]')[0].text,
to_type=str) # 上市日期
self.sssc = self.market() # 上市市场
self.zcxs = change_text(html.xpath(
'/html/body/div[2]/div[5]/table/tr[16]/td[2]')[0].text,
to_type=str) # 主承销商
self.ssbjr = change_text(html.xpath(
'/html/body/div[2]/div[5]/table/tr[17]/td[2]')[0].text,
to_type=str) # 上市保荐人
self.kjssws = change_text(html.xpath(
'/html/body/div[2]/div[5]/table/tr[18]/td[2]')[0].text,
to_type=str) # 会计师事务所
del response
gc.collect()
def __get_data_xjllb(self):
df = pd.read_csv(self.__url_xjllb, encoding=self.encoding)
self.xjllb_years = [
ymd[:4] for ymd in df.columns.to_list()[1:]
if ymd.strip() != '' and ymd[:4].isdigit()
]
self.xjllb_yyhdxjll = [] # 营业活动现金流量 CSV_LINE:26 DF_INDEX:24
self.xjllb_tzhdxjll = [] # 投资活动现金流量 CSV_LINE:41 DF_INDEX:39
self.xjllb_czhdxjll = [] # 筹资活动现金流量 CSV_LINE:53 DF_INDEX:51
self.xjllb_xjgl = [] # 现金股利 CSV_LINE:49 DF_INDEX:47
self.xjllb_zbzc = [] # 资本支出 CSV_LINE:34 DF_INDEX:32
self.xjllb_chjse = [] # 存货减少额 CSV_LINE:76 DF_INDEX:74
for year in self.xjllb_years:
data = df[f'{year}-12-31']
self.xjllb_yyhdxjll.append(change_text(data[24], 0))
self.xjllb_tzhdxjll.append(change_text(data[39], 0))
self.xjllb_czhdxjll.append(change_text(data[51], 0))
self.xjllb_xjgl.append(change_text(data[47], 0))
self.xjllb_zbzc.append(change_text(data[32], 0))
self.xjllb_chjse.append(change_text(data[74], 0))
del df
gc.collect()
def __get_data_zcfzb(self):
df = pd.read_csv(self.__url_zcfzb, encoding=self.encoding)
self.zcfzb_years = [
ymd[:4] for ymd in df.columns.to_list()[1:]
if ymd.strip() != '' and ymd[:4].isdigit()
]
self.zcfzb_zgb = [] # 总股本 CSV_LINE:96 DF_INDEX:94
self.zcfzb_xjyydxj = [
] # 现金与约当现金 CSV_LINE:2+3+4+5+6 DF_INDEX:0+1+2+3+4
self.zcfzb_yszk = [] # 应收账款 CSV_LINE:8 DF_INDEX:6
self.zcfzb_ch = [] # 存货 CSV_LINE:21 DF_INDEX:19
self.zcfzb_ldzc = [] # 流动资产 CSV_LINE:26 DF_INDEX:24
self.zcfzb_yfzk = [] # 应付账款 CSV_LINE:61 DF_INDEX:59
self.zcfzb_yfkx = [] # 预付款项 CSV_LINE:9 DF_INDEX:7
self.zcfzb_ldfz = [] # 流动负债 CSV_LINE:85 DF_INDEX:83
self.zcfzb_cqfz = [] # 长期负债 CSV_LINE:94 DF_INDEX:92
self.zcfzb_gdqy = [] # 股东权益 CSV_LINE:108 DF_INDEX:106
self.zcfzb_gdqy_gm = [] # 归属母公司股东权益 CSV_LINE:106 DF_INDEX:104
self.zcfzb_gdzc = [] # 固定资产 CSV_LINE:38 DF_INDEX:36
self.zcfzb_zjgc = [] # 在建工程 CSV_LINE:39 DF_INDEX:37
self.zcfzb_gcwz = [] # 工程物资 CSV_LINE:40 DF_INDEX:38
self.zcfzb_zfz = [] # 总负债 CSV_LINE:95 DF_INDEX:93
self.zcfzb_zzc = [] # 总资产 CSV_LINE:53 DF_INDEX:51
for year in self.zcfzb_years:
data = df[f'{year}-12-31']
# 总股本
self.zcfzb_zgb.append(change_text(data[94], 0))
# 现金与约当现金
v_csv_2 = change_text(data[0], 0)
v_csv_3 = change_text(data[1], 0)
v_csv_4 = change_text(data[2], 0)
v_csv_5 = change_text(data[3], 0)
v_csv_6 = change_text(data[4], 0)
self.zcfzb_xjyydxj.append(v_csv_2 + v_csv_3 + v_csv_4 + v_csv_5 +
v_csv_6)
# 应收账款
self.zcfzb_yszk.append(change_text(data[6], 0))
# 预付款项
self.zcfzb_yfkx.append(change_text(data[7], 0))
# 存货
self.zcfzb_ch.append(change_text(data[19], 0))
# 流动资产
self.zcfzb_ldzc.append(change_text(data[24], 0))
# 应付账款
self.zcfzb_yfzk.append(change_text(data[59], 0))
# 流动负债
self.zcfzb_ldfz.append(change_text(data[83], 0))
# 长期负债
self.zcfzb_cqfz.append(change_text(data[92], 0))
# 股东权益
self.zcfzb_gdqy.append(change_text(data[106], 0))
# 归属母公司股东权益
self.zcfzb_gdqy_gm.append(change_text(data[104], 0))
# 总负债
self.zcfzb_zfz.append(change_text(data[93], 0))
# 固定资产
self.zcfzb_gdzc.append(change_text(data[36], 0))
# 在建工程
self.zcfzb_zjgc.append(change_text(data[37], 0))
# 工程物资
self.zcfzb_gcwz.append(change_text(data[38], 0))
# 总资产
self.zcfzb_zzc.append(change_text(data[51], 0))
del df
gc.collect()