def stock_base_info(code):
"""
得到股票其他的基础数据信息
包含：
pe_trands 市盈率（动态）：47.98
type 分类 ：big（大盘股）medium （中盘股）small（小盘股）
pe_static 市盈率（静态）：8.61
total_capital 总股本 44.7亿股
ciculate_capital 流通股本 44.7亿股
pb 市净率 1.24
"""
url = "http://basic.10jqka.com.cn/%s/" % code
content = httpGetContent(url)
if content:
stock_dict = {}
soup = BeautifulSoup(content)
profile = soup.select('div#profile')
table = profile[0].select('table')[1]
td_list = table.select('td')
td_select = lambda td: td.select('span')[1].text
# regex = re.compile(r'^([0-9]{1,}[.][0-9]*|-[0-9]{1,}[.][0-9]*|\d+|-\d+)')
# find = lambda value: float(re.findall(regex, value)[0]) if re.findall(regex, value) else None
stock_dict["code"] = code
for i, td in enumerate(td_list):
if i == 0: # 市盈率(动态)：
stock_dict["pe_ratio_dynamic"] = validate_decimal(
td_select(td))
elif i == 3: # 分类
text = td_select(td)
if text == u"大盘股":
stock_dict['type'] = 'big'
elif text == u'中盘股':
stock_dict['type'] = 'medium'
elif text == u"小盘股":
stock_dict['type'] = 'small'
else:
stock_dict['type'] = text
elif i == 4: # 市盈率(静态)
stock_dict['pe_ratio_static'] = validate_decimal(td_select(td))
elif i == 7: # 总股本
stock_dict['total_capital'] = validate_decimal(td_select(td))
elif i == 8: # 市净率
stock_dict['pb'] = validate_decimal(td_select(td))
elif i == 11: # 流通股本
stock_dict['circulate_capital'] = validate_decimal(
td_select(td))
return stock_dict
def stock_base_info(code):
"""
得到股票其他的基础数据信息
包含：
pe_trands 市盈率（动态）：47.98
type 分类 ：big（大盘股）medium （中盘股）small（小盘股）
pe_static 市盈率（静态）：8.61
total_capital 总股本 44.7亿股
ciculate_capital 流通股本 44.7亿股
pb 市净率 1.24
"""
url = "http://basic.10jqka.com.cn/%s/" % code
content = httpGetContent(url)
if content:
stock_dict = {}
soup = BeautifulSoup(content)
profile = soup.select('div#profile')
table = profile[0].select('table')[1]
td_list = table.select('td')
td_select = lambda td: td.select('span')[1].text
# regex = re.compile(r'^([0-9]{1,}[.][0-9]*|-[0-9]{1,}[.][0-9]*|\d+|-\d+)')
# find = lambda value: float(re.findall(regex, value)[0]) if re.findall(regex, value) else None
stock_dict["code"] = code
for i, td in enumerate(td_list):
if i == 0: # 市盈率(动态)：
stock_dict["pe_ratio_dynamic"] = validate_decimal(td_select(td))
elif i == 3: # 分类
text = td_select(td)
if text == u"大盘股":
stock_dict['type'] = 'big'
elif text == u'中盘股':
stock_dict['type'] = 'medium'
elif text == u"小盘股":
stock_dict['type'] = 'small'
else:
stock_dict['type'] = text
elif i == 4: # 市盈率(静态)
stock_dict['pe_ratio_static'] = validate_decimal(td_select(td))
elif i == 7: # 总股本
stock_dict['total_capital'] = validate_decimal(td_select(td))
elif i == 8: # 市净率
stock_dict['pb'] = validate_decimal(td_select(td))
elif i == 11: # 流通股本
stock_dict['circulate_capital'] = validate_decimal(td_select(td))
return stock_dict
def stock_finical_post():
"""抓取同花顺业绩公告板块
http://data.10jqka.com.cn/financial/yjgg/
http://data.10jqka.com.cn/financial/yjgg/page/56/ajax/1/
"""
headers = {
"Host": "data.10jqka.com.cn",
"Referer": "http://data.10jqka.com.cn/financial/yjyg/",
"X-Requested-With": "XMLHttpRequest"
}
count = range(1, 60)
urls = [
"http://data.10jqka.com.cn/financial/yjgg/page/%s/ajax/1/" % num
for num in count
]
for url in urls:
content = httpGetContent(url, headers, "gb2312")
if content:
soup = BeautifulSoup(content)
stock_item = soup.select("tbody > tr")
for item in stock_item:
tds = item.select('td')
stock_dict = {}
for i, td in enumerate(tds):
if i == 1: # 代码
stock_dict["code"] = td.select('a')[0].string
elif i == 3: # 日期
stock_dict["date"] = str_to_date(td.string, "%Y-%m-%d")
elif i == 4: # 每股收益
stock_dict["earnings"] = decimal(td.string)
elif i == 5: # 营业收入
stock_dict["main_income"] = decimal(td.string)
elif i == 6: # 营业收入同比增长%
stock_dict["income_rise"] = validate_decimal(td.string)
elif i == 7: # 净利润 万元
stock_dict["net_profit"] = decimal(td.string)
elif i == 8: #净利润同比增长%
stock_dict["net_profit_rise"] = validate_decimal(
td.string)
yield stock_dict
def stock_finical_post():
"""抓取同花顺业绩公告板块
http://data.10jqka.com.cn/financial/yjgg/
http://data.10jqka.com.cn/financial/yjgg/page/56/ajax/1/
"""
headers = {
"Host": "data.10jqka.com.cn",
"Referer": "http://data.10jqka.com.cn/financial/yjyg/",
"X-Requested-With": "XMLHttpRequest"
}
count = range(1, 60)
urls = ["http://data.10jqka.com.cn/financial/yjgg/page/%s/ajax/1/" % num for num in count]
for url in urls:
content = httpGetContent(url, headers, "gb2312")
if content:
soup = BeautifulSoup(content)
stock_item = soup.select("tbody > tr")
for item in stock_item:
tds = item.select('td')
stock_dict = {}
for i, td in enumerate(tds):
if i == 1: # 代码
stock_dict["code"] = td.select('a')[0].string
elif i == 3: # 日期
stock_dict["date"] = str_to_date(td.string, "%Y-%m-%d")
elif i == 4: # 每股收益
stock_dict["earnings"] = decimal(td.string)
elif i == 5: # 营业收入
stock_dict["main_income"] = decimal(td.string)
elif i == 6: # 营业收入同比增长%
stock_dict["income_rise"] = validate_decimal(td.string)
elif i == 7: # 净利润 万元
stock_dict["net_profit"] = decimal(td.string)
elif i == 8: #净利润同比增长%
stock_dict["net_profit_rise"] = validate_decimal(td.string)
yield stock_dict
def stock_base_info(code):
"""
得到股票其他的基础数据信息
包含：
pe_trands 市盈率（动态）：47.98
type 分类 ：big（大盘股）medium （中盘股）small（小盘股）
pe_static 市盈率（静态）：8.61
total_capital 总股本 44.7亿股
ciculate_capital 流通股本 44.7亿股
pb 市净率 1.24
"""
url = "http://basic.10jqka.com.cn/%s/" % code
content = httpGetContent(url)
if content:
stock_dict = {}
soup = BeautifulSoup(content)
profile = soup.select('div#profile')
table = profile[0].select('table')[0]
td_list = table.select('td')
td_select_key = lambda td: td.select('span')[0].text.strip().replace(
'\t', '')
td_select_value = lambda td: td.select('span')[1].text.strip().replace(
'\t', '')
for i, td in enumerate(td_list):
#print td_select_key(td), td_select_value(td)
#stock_dict[td_select_key(td)] = td_select_value(td)
if i == 0: # 主营业务：
stock_dict["main_busyness"] = td_select_value(td)
elif i == 1: # 所属行业：
stock_dict["industry"] = td_select_value(td)
elif i == 2: # 涉及概念：
stock_dict["concept"] = td_select_value(td)
table = profile[0].select('table')[1]
td_list = table.select('td')
td_select_key = lambda td: td.select('span')[0].text.strip().replace(
'\t', '')
#td_select_value = lambda td: td.select('span')[1].text.strip().replace('\t','')
td_select = lambda td: td.select('span')[1].text.strip().replace(
'\t', '')
for i, td in enumerate(td_list):
#print td_select_key(td), td_select_value(td)
#stock_dict[td_select_key(td)] = td_select_value(td)
stock_dict["code"] = code
if i == 0: # 市盈率(动态)：
stock_dict["pe_ratio_dynamic"] = validate_decimal(
td_select(td))
elif i == 2: # 净资产收益率
stock_dict['return_on_equity'] = validate_decimal(
td_select(td))
elif i == 3: # 分类
text = td_select(td)
if text == u"大盘股":
stock_dict['type'] = 'big'
elif text == u'中盘股':
stock_dict['type'] = 'medium'
elif text == u"小盘股":
stock_dict['type'] = 'small'
else:
stock_dict['type'] = text
elif i == 4: # 市盈率(静态)
stock_dict['pe_ratio_static'] = validate_decimal(td_select(td))
elif i == 5: # 营业收入
stock_dict['income'] = validate_decimal(td_select(td))
elif i == 6: # 每股净资产
stock_dict['assert_per_share'] = validate_decimal(
td_select(td))
elif i == 7: # 总股本
stock_dict['total_capital'] = validate_decimal(td_select(td))
elif i == 8: # 市净率
stock_dict['pb'] = validate_decimal(td_select(td))
elif i == 9: # 净利润
stock_dict['net_profit'] = validate_decimal(td_select(td))
elif i == 10: # 每股现金流
stock_dict['cash_flow_per_share'] = validate_decimal(
td_select(td))
elif i == 11: # 流通股本
stock_dict['circulate_capital'] = validate_decimal(
td_select(td))
#for item in stock_dict:
# print item, stock_dict[item]
return stock_dict
