def test_multiple_ctx(self):
c1 = py_mini_racer.MiniRacer()
c2 = py_mini_racer.MiniRacer()
c3 = py_mini_racer.MiniRacer()
c1.eval('var x = 1')
c2.eval('var x = 2')
c3.eval('var x = 3')
self.assertEqual(c1.eval('(x)'), 1)
self.assertEqual(c2.eval('(x)'), 2)
self.assertEqual(c3.eval('(x)'), 3)
def stock_board_concept_name_ths() -> pd.DataFrame:
"""
同花顺-板块-概念板块-概念
http://q.10jqka.com.cn/gn/detail/code/301558/
:return: 所有概念板块的名称和链接
:rtype: pandas.DataFrame
"""
url = "http://q.10jqka.com.cn/gn/index/field/addtime/order/desc/page/1/ajax/1/"
js_code = py_mini_racer.MiniRacer()
js_content = _get_file_content_ths("ths.js")
js_code.eval(js_content)
v_code = js_code.call('v')
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36',
'Cookie': f'v={v_code}'
}
r = requests.get(url, headers=headers)
soup = BeautifulSoup(r.text, "lxml")
total_page = soup.find('span', attrs={'class': 'page_info'}).text.split('/')[1]
big_df = pd.DataFrame()
for page in tqdm(range(1, int(total_page)+1), leave=False):
url = f"http://q.10jqka.com.cn/gn/index/field/addtime/order/desc/page/{page}/ajax/1/"
js_code = py_mini_racer.MiniRacer()
js_content = _get_file_content_ths("ths.js")
js_code.eval(js_content)
v_code = js_code.call('v')
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36',
'Cookie': f'v={v_code}'
}
r = requests.get(url, headers=headers)
soup = BeautifulSoup(r.text, "lxml")
soup.find('table', attrs={'class': 'm-table m-pager-table'}).find('tbody')
url_list = []
for item in soup.find('table', attrs={'class': 'm-table m-pager-table'}).find('tbody').find_all('tr'):
inner_url = item.find_all("td")[1].find('a')['href']
url_list.append(inner_url)
temp_df = pd.read_html(r.text)[0]
temp_df['网址'] = url_list
big_df = big_df.append(temp_df, ignore_index=True)
big_df = big_df[[
'日期',
'概念名称',
'成分股数量',
'网址'
]]
big_df['日期'] = pd.to_datetime(big_df['日期']).dt.date
big_df['成分股数量'] = pd.to_numeric(big_df['成分股数量'])
big_df['代码'] = big_df['网址'].str.split("/", expand=True).iloc[:, 6]
return big_df
def stock_board_concept_name_ths() -> pd.DataFrame:
"""
同花顺-板块-概念板块-概念
http://q.10jqka.com.cn/gn/detail/code/301558/
:return: 所有概念板块的名称和链接
:rtype: pandas.DataFrame
"""
url = "http://q.10jqka.com.cn/gn/index/field/addtime/order/desc/page/1/ajax/1/"
js_code = py_mini_racer.MiniRacer()
js_content = _get_file_content_ths("ths.js")
js_code.eval(js_content)
v_code = js_code.call("v")
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36",
"Cookie": f"v={v_code}",
}
r = requests.get(url, headers=headers)
soup = BeautifulSoup(r.text, "lxml")
total_page = soup.find("span", attrs={"class": "page_info"}).text.split("/")[1]
big_df = pd.DataFrame()
for page in tqdm(range(1, int(total_page) + 1), leave=False):
url = f"http://q.10jqka.com.cn/gn/index/field/addtime/order/desc/page/{page}/ajax/1/"
js_code = py_mini_racer.MiniRacer()
js_content = _get_file_content_ths("ths.js")
js_code.eval(js_content)
v_code = js_code.call("v")
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36",
"Cookie": f"v={v_code}",
}
r = requests.get(url, headers=headers)
soup = BeautifulSoup(r.text, "lxml")
url_list = []
for item in (
soup.find("table", attrs={"class": "m-table m-pager-table"})
.find("tbody")
.find_all("tr")
):
inner_url = item.find_all("td")[1].find("a")["href"]
url_list.append(inner_url)
temp_df = pd.read_html(r.text)[0]
temp_df["网址"] = url_list
big_df = big_df.append(temp_df, ignore_index=True)
big_df = big_df[["日期", "概念名称", "成分股数量", "网址"]]
big_df["日期"] = pd.to_datetime(big_df["日期"]).dt.date
big_df["成分股数量"] = pd.to_numeric(big_df["成分股数量"])
big_df["代码"] = big_df["网址"].str.split("/", expand=True).iloc[:, 6]
return big_df
def stock_us_daily(symbol: str = "AAPL", adjust: str = "") -> pd.DataFrame:
"""
新浪财经-美股
http://finance.sina.com.cn/stock/usstock/sector.shtml
备注：CIEN 新浪复权因子错误
:param symbol: 可以使用 get_us_stock_name 获取
:type symbol: str
:param adjust: "": 返回未复权的数据 ; qfq: 返回前复权后的数据; qfq-factor: 返回前复权因子和调整;
:type adjust: str
:return: 指定 adjust 的数据
:rtype: pandas.DataFrame
"""
res = requests.get(f"https://finance.sina.com.cn/staticdata/us/{symbol}")
js_code = py_mini_racer.MiniRacer()
js_code.eval(zh_js_decode)
dict_list = js_code.call(
"d", res.text.split("=")[1].split(";")[0].replace('"', "")
) # 执行js解密代码
data_df = pd.DataFrame(dict_list)
data_df.index = pd.to_datetime(data_df["date"])
del data_df["amount"]
del data_df["date"]
data_df = data_df.astype("float")
res = requests.get(us_sina_stock_hist_qfq_url.format(symbol))
qfq_factor_df = pd.DataFrame(eval(res.text.split("=")[1].split("\n")[0])["data"])
qfq_factor_df.rename(columns={"c": "adjust", "d": "date", "f": "qfq_factor", }, inplace=True)
qfq_factor_df.index = pd.to_datetime(qfq_factor_df["date"])
del qfq_factor_df["date"]
# 处理复权因子
temp_date_range = pd.date_range("1900-01-01", qfq_factor_df.index[0].isoformat())
temp_df = pd.DataFrame(range(len(temp_date_range)), temp_date_range)
new_range = pd.merge(
temp_df, qfq_factor_df, left_index=True, right_index=True, how="left"
)
new_range = new_range.fillna(method="ffill")
new_range = new_range.iloc[:, [1, 2]]
if adjust == "qfq":
if len(new_range) == 1:
new_range.index.values[0] = pd.to_datetime(str(data_df.index.date[0]))
temp_df = pd.merge(
data_df, new_range, left_index=True, right_index=True, how="left"
)
temp_df.fillna(method="ffill", inplace=True)
temp_df.fillna(method="bfill", inplace=True)
temp_df = temp_df.astype(float)
temp_df["open"] = temp_df["open"] * temp_df["qfq_factor"] + temp_df["adjust"]
temp_df["high"] = temp_df["high"] * temp_df["qfq_factor"] + temp_df["adjust"]
temp_df["close"] = temp_df["close"] * temp_df["qfq_factor"] + temp_df["adjust"]
temp_df["low"] = temp_df["low"] * temp_df["qfq_factor"] + temp_df["adjust"]
temp_df = temp_df.apply(lambda x: round(x, 4))
temp_df = temp_df.astype("float")
return temp_df.iloc[:, :-2]
if adjust == "qfq-factor":
return qfq_factor_df
if adjust == "":
return data_df
def stock_zh_index_daily(symbol: str = "sh000922") -> pd.DataFrame:
"""
新浪财经-指数获取某个指数的历史行情数据, 大量抓取容易封IP
:param symbol: str e.g., sz399998
:return: pandas.DataFrame
open high low close volume
date
2015-06-16 2526.056 2577.092 2469.216 2487.513 2224345088
2015-06-17 2476.863 2567.842 2422.229 2560.914 2181699840
2015-06-18 2553.739 2587.655 2480.321 2480.674 2032781312
2015-06-19 2431.218 2453.794 2286.967 2287.758 1687013248
2015-06-23 2280.189 2341.795 2156.396 2341.359 1627453440
... ... ... ... ...
2019-11-11 1210.968 1210.968 1182.442 1182.718 415074658
2019-11-12 1184.118 1196.425 1184.005 1195.790 397246387
2019-11-13 1195.925 1195.925 1180.293 1185.293 334027614
2019-11-14 1185.788 1187.431 1178.414 1180.791 271514767
2019-11-15 1181.090 1181.739 1165.898 1166.536 338309880
"""
params = {"d": "2020_2_4"}
res = requests.get(zh_sina_index_stock_hist_url.format(symbol),
params=params)
js_code = py_mini_racer.MiniRacer()
js_code.eval(hk_js_decode)
dict_list = js_code.call("d",
res.text.split("=")[1].split(";")[0].replace(
'"', "")) # 执行js解密代码
data_df = pd.DataFrame(dict_list)
data_df.index = pd.to_datetime(data_df["date"])
del data_df["date"]
data_df = data_df.astype("float")
return data_df
def parse_item(self, response):
self.log('This is an item page! %s' % response.url)
searchObj = re.search(r'#jquery_jplayer_1.*?this', response.text,
re.S | re.I)
url = ''
# open('file.txt', 'w').write(response.text)
if searchObj:
code = searchObj.group()
code = ''.join(code.splitlines()[2:-1])
ctx = py_mini_racer.MiniRacer()
url = ctx.eval(code)
title = response.css(".jp-title ul li ::text").extract_first()
if title and url:
item = IshuyinItem()
item['title'] = title.strip().split('-')[0].strip()
item['file_urls'] = [url]
item['album'] = self.album
item['picture'] = self.picture
item['artist'] = self.artist
yield item
else:
logging.debug("Parse Item error - Title:%s URL:%s", title, url)
raise DropItem("Missing mp3 %s" % response.url)
def stock_rank_xzjp_ths() -> pd.DataFrame:
"""
同花顺-数据中心-技术选股-险资举牌
http://data.10jqka.com.cn/financial/xzjp/
:return: 险资举牌
:rtype: pandas.DataFrame
"""
js_code = py_mini_racer.MiniRacer()
js_content = _get_file_content_ths("ths.js")
js_code.eval(js_content)
v_code = js_code.call("v")
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36",
"Cookie": f"v={v_code}",
}
url = f"http://data.10jqka.com.cn/ajax/xzjp/field/DECLAREDATE/order/desc/ajax/1/free/1/"
r = requests.get(url, headers=headers)
soup = BeautifulSoup(r.text, "lxml")
try:
total_page = soup.find("span", attrs={"class": "page_info"}).text.split("/")[1]
except AttributeError as e:
total_page = 1
big_df = pd.DataFrame()
for page in tqdm(range(1, int(total_page) + 1), leave=False):
v_code = js_code.call("v")
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36",
"Cookie": f"v={v_code}",
}
url = f"http://data.10jqka.com.cn/ajax/xzjp/field/DECLAREDATE/order/desc/ajax/1/free/1/"
r = requests.get(url, headers=headers)
temp_df = pd.read_html(r.text, converters={"股票代码": str})[0]
big_df = big_df.append(temp_df, ignore_index=True)
big_df.columns = [
'序号',
'举牌公告日',
'股票代码',
'股票简称',
'现价',
'涨跌幅',
'举牌方',
'增持数量',
'交易均价',
'增持数量占总股本比例',
'变动后持股总数',
'变动后持股比例',
'历史数据',
]
big_df['涨跌幅'] = big_df['涨跌幅'].astype(str).str.zfill(6)
big_df["增持数量占总股本比例"] = big_df["增持数量占总股本比例"].astype(str).str.strip("%")
big_df["变动后持股比例"] = big_df["变动后持股比例"].astype(str).str.strip("%")
big_df["涨跌幅"] = pd.to_numeric(big_df["涨跌幅"], errors='coerce')
big_df["增持数量占总股本比例"] = pd.to_numeric(big_df["增持数量占总股本比例"])
big_df["变动后持股比例"] = pd.to_numeric(big_df["变动后持股比例"])
big_df["举牌公告日"] = pd.to_datetime(big_df["举牌公告日"]).dt.date
big_df["股票代码"] = big_df["股票代码"].astype(str).str.zfill(6)
big_df["现价"] = pd.to_numeric(big_df["现价"])
big_df["交易均价"] = pd.to_numeric(big_df["交易均价"])
del big_df['历史数据']
return big_df
def stock_zh_a_cdr_daily(
symbol: str = "sh689009", start_date: str = "19900101", end_date: str = "22201116"
) -> pd.DataFrame:
"""
新浪财经-A股-CDR个股的历史行情数据, 大量抓取容易封 IP
# TODO 观察复权情况
https://finance.sina.com.cn/realstock/company/sh689009/nc.shtml
:param start_date: 20201103; 开始日期
:type start_date: str
:param end_date: 20201103; 结束日期
:type end_date: str
:param symbol: sh689009
:type symbol: str
:return: specific data
:rtype: pandas.DataFrame
"""
res = requests.get(zh_sina_a_stock_hist_url.format(symbol))
js_code = py_mini_racer.MiniRacer()
js_code.eval(hk_js_decode)
dict_list = js_code.call(
"d", res.text.split("=")[1].split(";")[0].replace('"', "")
) # 执行js解密代码
data_df = pd.DataFrame(dict_list)
data_df.index = pd.to_datetime(data_df["date"])
del data_df["date"]
data_df = data_df.astype("float")
temp_df = data_df[start_date:end_date]
temp_df["open"] = round(temp_df["open"], 2)
temp_df["high"] = round(temp_df["high"], 2)
temp_df["low"] = round(temp_df["low"], 2)
temp_df["close"] = round(temp_df["close"], 2)
return temp_df
def test_cannot_parse(self):
context = py_mini_racer.MiniRacer()
js_source = "var f = function("
with six.assertRaisesRegex(self, py_mini_racer.JSParseException,
'.*Unexpected end of input.*'):
context.eval(js_source)
def get_us_stock_name() -> pd.DataFrame:
"""
u.s. stock's english name, chinese name and symbol
you should use symbol to get apply into the next function
http://finance.sina.com.cn/stock/usstock/sector.shtml
:return: stock's english name, chinese name and symbol
:rtype: pandas.DataFrame
"""
big_df = pd.DataFrame()
page_count = get_us_page_count()
for page in tqdm(range(1, page_count + 1)):
# page = "1"
us_js_decode = "US_CategoryService.getList?page={}&num=20&sort=&asc=0&market=&id=".format(
page)
js_code = py_mini_racer.MiniRacer()
js_code.eval(js_hash_text)
dict_list = js_code.call("d", us_js_decode) # 执行js解密代码
us_sina_stock_dict_payload.update({"page": "{}".format(page)})
res = requests.get(us_sina_stock_list_url.format(dict_list),
params=us_sina_stock_dict_payload)
data_json = json.loads(res.text[res.text.find("({") +
1:res.text.rfind(");")])
big_df = big_df.append(pd.DataFrame(data_json["data"]),
ignore_index=True)
return big_df[["name", "cname", "symbol"]]
def stock_zh_index_daily(symbol: str = "sh000922") -> pd.DataFrame:
"""
新浪财经-指数-历史行情数据, 大量抓取容易封 IP
https://finance.sina.com.cn/realstock/company/sh000909/nc.shtml
:param symbol: sz399998, 指定指数代码
:type symbol: str
:return: 历史行情数据
:rtype: pandas.DataFrame
"""
params = {"d": "2020_2_4"}
res = requests.get(zh_sina_index_stock_hist_url.format(symbol),
params=params)
js_code = py_mini_racer.MiniRacer()
js_code.eval(hk_js_decode)
dict_list = js_code.call("d",
res.text.split("=")[1].split(";")[0].replace(
'"', "")) # 执行js解密代码
temp_df = pd.DataFrame(dict_list)
temp_df["date"] = pd.to_datetime(temp_df["date"]).dt.date
temp_df["open"] = pd.to_numeric(temp_df["open"])
temp_df["close"] = pd.to_numeric(temp_df["close"])
temp_df["high"] = pd.to_numeric(temp_df["high"])
temp_df["low"] = pd.to_numeric(temp_df["low"])
temp_df["volume"] = pd.to_numeric(temp_df["volume"])
return temp_df
def bond_zh_hs_daily(symbol: str = "sh010107") -> pd.DataFrame:
"""
新浪财经-债券-沪深债券-历史行情数据, 大量抓取容易封IP
http://vip.stock.finance.sina.com.cn/mkt/#hs_z
:param symbol: 沪深债券代码; e.g., sh010107
:type symbol: str
:return: 指定沪深债券代码的日 K 线数据
:rtype: pandas.DataFrame
"""
res = requests.get(
zh_sina_bond_hs_hist_url.format(
symbol,
datetime.datetime.now().strftime("%Y_%m_%d")))
js_code = py_mini_racer.MiniRacer()
js_code.eval(hk_js_decode)
dict_list = js_code.call("d",
res.text.split("=")[1].split(";")[0].replace(
'"', "")) # 执行js解密代码
data_df = pd.DataFrame(dict_list)
data_df["date"] = pd.to_datetime(data_df["date"]).dt.date
data_df['open'] = pd.to_numeric(data_df['open'])
data_df['high'] = pd.to_numeric(data_df['high'])
data_df['low'] = pd.to_numeric(data_df['low'])
data_df['close'] = pd.to_numeric(data_df['close'])
return data_df
def test_cannot_parse(self):
context = py_mini_racer.MiniRacer()
js_source = "var f = function("
with self.assertRaisesRegex(
py_mini_racer.JSParseException,
'.*Unknown JavaScript error during parse.*'):
context.eval(js_source)
def test_cannot_parse(self):
context = py_mini_racer.MiniRacer()
js_source = "var f = function("
with self.assertRaises(py_mini_racer.JSParseException):
context.eval(js_source)
def stock_rank_lxxd_ths() -> pd.DataFrame:
"""
同花顺-数据中心-技术选股-连续下跌
http://data.10jqka.com.cn/rank/lxxd/
:return: 连续下跌
:rtype: pandas.DataFrame
"""
js_code = py_mini_racer.MiniRacer()
js_content = _get_file_content_ths("ths.js")
js_code.eval(js_content)
v_code = js_code.call("v")
headers = {
"User-Agent":
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36",
"Cookie": f"v={v_code}",
}
url = f"http://data.10jqka.com.cn/rank/lxxd/field/lxts/order/desc/page/1/ajax/1/free/1/"
r = requests.get(url, headers=headers)
soup = BeautifulSoup(r.text, "lxml")
try:
total_page = soup.find("span", attrs={
"class": "page_info"
}).text.split("/")[1]
except AttributeError as e:
total_page = 1
big_df = pd.DataFrame()
for page in tqdm(range(1, int(total_page) + 1), leave=False):
v_code = js_code.call("v")
headers = {
"User-Agent":
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36",
"Cookie": f"v={v_code}",
}
url = f"http://data.10jqka.com.cn/rank/lxxd/field/lxts/order/desc/page/{page}/ajax/1/free/1/"
r = requests.get(url, headers=headers)
temp_df = pd.read_html(r.text, converters={"股票代码": str})[0]
big_df = big_df.append(temp_df, ignore_index=True)
big_df.columns = [
"序号",
"股票代码",
"股票简称",
"收盘价",
"最高价",
"最低价",
"连涨天数",
"连续涨跌幅",
"累计换手率",
"所属行业",
]
big_df["连续涨跌幅"] = big_df["连续涨跌幅"].str.strip("%")
big_df["累计换手率"] = big_df["累计换手率"].str.strip("%")
big_df["连续涨跌幅"] = pd.to_numeric(big_df["连续涨跌幅"])
big_df["累计换手率"] = pd.to_numeric(big_df["累计换手率"])
big_df["收盘价"] = pd.to_numeric(big_df["收盘价"])
big_df["最高价"] = pd.to_numeric(big_df["最高价"])
big_df["最低价"] = pd.to_numeric(big_df["最低价"])
big_df["连涨天数"] = pd.to_numeric(big_df["连涨天数"])
return big_df
def _init(self):
# Set up interpreter
self._intp = py_mini_racer.MiniRacer()
self._time_cs = 0
# Make initial source read
for fname in self._js_filenames:
with open(fname, "r") as f:
self._intp.eval(f.read())
async def _get_us_stock_name_async(
request_per_batch: int = 15) -> pd.DataFrame:
count_per_page = 20
big_df = pd.DataFrame()
page_count = get_us_page_count(count_per_page)
start = time.time()
with tqdm(total=page_count) as pbar:
all_pages = range(1, page_count + 1)
finished_pages = []
while len(finished_pages) < page_count:
to_req_pages = [x for x in all_pages if x not in finished_pages]
request_per_batch = min(request_per_batch, len(to_req_pages))
tasks = {}
for page in to_req_pages:
if len(tasks) < request_per_batch:
us_js_decode = f"US_CategoryService.getList?page={page}&num={count_per_page}&sort=&asc=0&market=&id="
js_code = py_mini_racer.MiniRacer()
js_code.eval(js_hash_text)
dict_list = js_code.call("d", us_js_decode) # 执行js解密代码
us_sina_stock_dict_payload.update(
{"page": "{}".format(page)})
tasks[page] = asyncio.create_task(
request(us_sina_stock_list_url.format(dict_list),
us_sina_stock_dict_payload))
continue
# n requests per aio loop
for _, task in tasks.items():
await task
n_failed_req = 0
for page_no, task in tasks.items():
try:
res = task.result()
data_json = json.loads(res[res.find("({") +
1:res.rfind(");")])
big_df = big_df.append(pd.DataFrame(data_json["data"]),
ignore_index=True)
finished_pages.append(page_no)
pbar.update(1)
except requests.exceptions.ConnectionError as ident:
n_failed_req += 1
print(
f'{ident} page_no={page_no}, sleep for longer time and try in next batch'
)
pass
tasks.clear()
interval_time = 3
if n_failed_req >= 1:
# wait longger for sina anti-spider
interval_time = 10
time.sleep(interval_time)
end = time.time()
print('Cost time:', end - start)
return big_df[["name", "cname", "symbol"]]
def test_exception_thrown(self):
context = py_mini_racer.MiniRacer()
js_source = "var f = function() {throw 'error'};"
context.eval(js_source)
with self.assertRaises(py_mini_racer.JSEvalException):
context.eval("f()")
def stock_rank_cxd_ths(symbol: str = "创月新低") -> pd.DataFrame:
"""
同花顺-数据中心-技术选股-创新低
http://data.10jqka.com.cn/rank/cxd/
:param symbol: choice of {"创月新低", "半年新低", "一年新低", "历史新低"}
:type symbol: str
:return: 创新低数据
:rtype: pandas.DataFrame
"""
symbol_map = {
"创月新低": "4",
"半年新低": "3",
"一年新低": "2",
"历史新低": "1",
}
js_code = py_mini_racer.MiniRacer()
js_content = _get_file_content_ths("ths.js")
js_code.eval(js_content)
v_code = js_code.call("v")
headers = {
"User-Agent":
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36",
"Cookie": f"v={v_code}",
}
url = f"http://data.10jqka.com.cn/rank/cxd/board/{symbol_map[symbol]}/field/stockcode/order/asc/page/1/ajax/1/free/1/"
r = requests.get(url, headers=headers)
soup = BeautifulSoup(r.text, "lxml")
try:
total_page = soup.find("span", attrs={
"class": "page_info"
}).text.split("/")[1]
except AttributeError as e:
total_page = 1
big_df = pd.DataFrame()
for page in tqdm(range(1, int(total_page) + 1), leave=False):
v_code = js_code.call("v")
headers = {
"User-Agent":
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36",
"Cookie": f"v={v_code}",
}
url = f"http://data.10jqka.com.cn/rank/cxd/board/{symbol_map[symbol]}/field/stockcode/order/asc/page/{page}/ajax/1/free/1/"
r = requests.get(url, headers=headers)
temp_df = pd.read_html(r.text)[0]
big_df = big_df.append(temp_df, ignore_index=True)
big_df.columns = [
"序号", "股票代码", "股票简称", "涨跌幅", "换手率", "最新价", "前期低点", "前期低点日期"
]
big_df["股票代码"] = big_df["股票代码"].astype(str).str.zfill(6)
big_df["涨跌幅"] = big_df["涨跌幅"].str.strip("%")
big_df["换手率"] = big_df["换手率"].str.strip("%")
big_df["前期低点日期"] = pd.to_datetime(big_df["前期低点日期"]).dt.date
big_df["涨跌幅"] = pd.to_numeric(big_df["涨跌幅"])
big_df["换手率"] = pd.to_numeric(big_df["换手率"])
big_df["最新价"] = pd.to_numeric(big_df["最新价"])
big_df["前期低点"] = pd.to_numeric(big_df["前期低点"])
return big_df
def stock_dividents_cninfo(symbol: str = "600009") -> pd.DataFrame:
"""
巨潮资讯-个股-历史分红
http://webapi.cninfo.com.cn/#/company?companyid=600009
:param symbol: 股票代码
:type symbol: str
:return: 历史分红
:rtype: pandas.DataFrame
"""
url = "http://webapi.cninfo.com.cn/api/sysapi/p_sysapi1139"
params = {'scode': symbol}
random_time_str = str(int(time.time()))
js_code = py_mini_racer.MiniRacer()
js_code.eval(js_str)
mcode = js_code.call("mcode", random_time_str)
headers = {
"Accept": "*/*",
"Accept-Encoding": "gzip, deflate",
"Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
"Cache-Control": "no-cache",
"Content-Length": "0",
"Host": "webapi.cninfo.com.cn",
"mcode": mcode,
"Origin": "http://webapi.cninfo.com.cn",
"Pragma": "no-cache",
"Proxy-Connection": "keep-alive",
"Referer": "http://webapi.cninfo.com.cn/",
"User-Agent":
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.63 Safari/537.36",
"X-Requested-With": "XMLHttpRequest",
}
r = requests.post(url, params=params, headers=headers)
data_json = r.json()
temp_df = pd.DataFrame(data_json["records"])
temp_df.columns = [
"实施方案公告日期",
"送股比例",
"转增比例",
"派息比例",
"股权登记日",
"除权日",
"派息日",
"股份到账日",
"实施方案分红说明",
"分红类型",
"报告时间",
]
temp_df["实施方案公告日期"] = pd.to_datetime(temp_df["实施方案公告日期"]).dt.date
temp_df["送股比例"] = pd.to_numeric(temp_df["送股比例"], errors="coerce")
temp_df["转增比例"] = pd.to_numeric(temp_df["转增比例"], errors="coerce")
temp_df["派息比例"] = pd.to_numeric(temp_df["派息比例"], errors="coerce")
temp_df["股权登记日"] = pd.to_datetime(temp_df["股权登记日"],
errors="coerce").dt.date
temp_df["除权日"] = pd.to_datetime(temp_df["除权日"], errors="coerce").dt.date
temp_df["派息日"] = pd.to_datetime(temp_df["派息日"], errors="coerce").dt.date
return temp_df
def solveChallenge(self, text):
text = re.split("{|}|;", text)
replaceFunction = "return message.replace(/./g, function(char, position) {"
rebuilt = [
text[1] + "{", text[2] + ";", replaceFunction, text[9] + ";})};",
text[0]
]
jsEngine = py_mini_racer.MiniRacer()
solution = jsEngine.eval("".join(rebuilt))
return self._shiftBits(solution)
def test_null_byte(self):
context = py_mini_racer.MiniRacer()
s = "\x00 my string!"
# Try return a string including a null byte
in_val = "var str = \"" + s + "\"; str;"
result = context.eval(in_val)
self.assertEqual(result, s)
def solveChallenge(self, text):
# Rebuilt Javascript so engine can solve it
text = text.replace('\t', '', -1).encode('ascii', 'ignore').decode('utf-8')
text = re.split("{|}|;", text)
replaceFunction = "return message.replace(/./g, function(char, position) {"
rebuilt = [text[1] + "{", text[2] + ";", replaceFunction, text[7] + ";})};", text[0]]
jsEngine = py_mini_racer.MiniRacer()
solution = jsEngine.eval("".join(rebuilt))
return self._shiftBits(solution)
def find_dlbutton(html):
fullpage = BeautifulSoup(html, "html.parser")
dl = fullpage.find("dlbutton")
for e in fullpage.find_all("script", type="text/javascript"):
if "dlbutton" in (e.text):
line = e.text.split(";")
for l in line:
if "dlbutton" in l:
l = l.split("=")[1]
ctx = py_mini_racer.MiniRacer()
print(ctx.eval(l))
def covid_tracker():
ctx = py_mini_racer.MiniRacer()
tracker_xpath = '/html/body/script[1]/text()'
r = session.get('https://covidtracker.5lab.co/')
if r.status_code == 200:
raw_script = r.html.xpath(tracker_xpath)
function = util.m_func(raw_script)
data_exe = ctx.execute(function)
cases_data = data_exe['state']['cases']
Export(cases_data, 'covid-tracker')
print('Extract Covid-Tracker Successful')
def execute_javascript(function, source, args):
interpreter = py_mini_racer.MiniRacer()
interpreter.eval('%s = function () { %s }' % (function, source))
def stringify(s):
return '"%s"' % s.replace('"', '\\"')
eval_args = ','.join(stringify(a) for a in args)
return interpreter.eval('%s(%s)' % (function, eval_args),
timeout=EvalClient.JS_TIMEOUT,
max_memory=EvalClient.JS_MEMORY)
def predict(self, X):
code = get_file_content(self.script_path)
args = ",".join(map(utils.format_arg, X))
caller = f"score([{args}])"
ctx = py_mini_racer.MiniRacer()
ctx.eval(code)
result = ctx.execute(caller)
return result
def stock_board_concept_cons_ths(symbol: str = "阿里巴巴概念") -> pd.DataFrame:
"""
同花顺-板块-概念板块-成份股
http://q.10jqka.com.cn/gn/detail/code/301558/
:param symbol: 板块名称
:type symbol: str
:return: 成份股
:rtype: pandas.DataFrame
"""
stock_board_ths_map_df = stock_board_concept_name_ths()
symbol = (
stock_board_ths_map_df[stock_board_ths_map_df["概念名称"] == symbol]["网址"]
.values[0]
.split("/")[-2]
)
js_code = py_mini_racer.MiniRacer()
js_content = _get_file_content_ths("ths.js")
js_code.eval(js_content)
v_code = js_code.call("v")
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36",
"Cookie": f"v={v_code}",
}
url = f"http://q.10jqka.com.cn/gn/detail/field/264648/order/desc/page/1/ajax/1/code/{symbol}"
r = requests.get(url, headers=headers)
soup = BeautifulSoup(r.text, "lxml")
try:
page_num = int(soup.find_all("a", attrs={"class": "changePage"})[-1]["page"])
except IndexError as e:
page_num = 1
big_df = pd.DataFrame()
for page in tqdm(range(1, page_num + 1), leave=False):
v_code = js_code.call("v")
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36",
"Cookie": f"v={v_code}",
}
url = f"http://q.10jqka.com.cn/gn/detail/field/264648/order/desc/page/{page}/ajax/1/code/{symbol}"
r = requests.get(url, headers=headers)
temp_df = pd.read_html(r.text)[0]
big_df = big_df.append(temp_df, ignore_index=True)
big_df.rename(
{
"涨跌幅(%)": "涨跌幅",
"涨速(%)": "涨速",
"换手(%)": "换手",
"振幅(%)": "振幅",
},
inplace=True,
axis=1,
)
del big_df["加自选"]
big_df["代码"] = big_df["代码"].astype(str).str.zfill(6)
return big_df
def stock_board_industry_cons_ths(symbol: str = "半导体及元件") -> pd.DataFrame:
"""
同花顺-板块-行业板块-成份股
http://q.10jqka.com.cn/thshy/detail/code/881121/
:param symbol: 板块名称
:type symbol: str
:return: 成份股
:rtype: pandas.DataFrame
"""
stock_board_ths_map_df = stock_board_industry_name_ths()
symbol = stock_board_ths_map_df[stock_board_ths_map_df['name'] ==
symbol]['url'].values[0].split('/')[-2]
js_code = py_mini_racer.MiniRacer()
js_content = _get_file_content_ths("ths.js")
js_code.eval(js_content)
v_code = js_code.call('v')
headers = {
'User-Agent':
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36',
'Cookie': f'v={v_code}'
}
url = f'http://q.10jqka.com.cn/thshy/detail/field/199112/order/desc/page/1/ajax/1/code/{symbol}'
r = requests.get(url, headers=headers)
soup = BeautifulSoup(r.text, "lxml")
try:
page_num = int(
soup.find_all('a', attrs={'class': 'changePage'})[-1]['page'])
except IndexError as e:
page_num = 1
big_df = pd.DataFrame()
for page in tqdm(range(1, page_num + 1)):
v_code = js_code.call('v')
headers = {
'User-Agent':
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36',
'Cookie': f'v={v_code}'
}
url = f'http://q.10jqka.com.cn/thshy/detail/field/199112/order/desc/page/{page}/ajax/1/code/{symbol}'
r = requests.get(url, headers=headers)
temp_df = pd.read_html(r.text)[0]
big_df = big_df.append(temp_df, ignore_index=True)
big_df.rename(
{
"涨跌幅(%)": "涨跌幅",
"涨速(%)": "涨速",
"换手(%)": "换手",
"振幅(%)": "振幅",
},
inplace=True,
axis=1)
del big_df['加自选']
big_df['代码'] = big_df['代码'].astype(str).str.zfill(6)
return big_df
def prepare_js(self):
logging.info('prepare js runtime')
js_tag = self.etree.find('./{}'.format(self.etree.getroot().attrib.get(
'script', 'script')))
self.js = py_mini_racer.MiniRacer()
for item in js_tag.findall('./require/item'):
libcode = self.url.get(item.attrib['url'])
logging.info('load script require: {}'.format(item.attrib['url']))
self.js.eval(libcode)
logging.info('load script')
self.js.eval(js_tag.find('./code').text)
self.js.eval('SiteD = {}') # TODO 导入 SiteD 全局变量
