Python股票信息抓取~

本来想把股票的涨跌抓取出来，用汇通网的股票为例，就找了国际外汇为例。

页面里有xhr请求,并且每个xhr的url请求的 http://api.q.fx678.com/history.php?symbol=USD&limit=288&resolution=5&codeType=8100&st=0.43342772855649625
然后请求里面哟一个limit=288表示288个时间段，汇通网里面将5分钟为一个时间段，所以一天的话有288个时间间隔。

xhr请求中的st参数好像是跟页面的请求的过期与否有关，因为有的股票可以通过该st值获得数据，但是有的股票就不可以。然后此xhr请求可以将从该时间段为止的24小时内的所有股票的变动返回，包括该时间段的开盘，收盘，最高，最低，然后依次来解析。



处理的时候只是将所有整点的数据该股票的最高点解析出来，xhr请求中的时间戳是秒级的，然后将之转换成北京时间，并且将时间进行排序，然后获取正确的其他的并没有进行处理，程序中存储时间和最高点都是用数组存储的，并且改程序是单进程，会更新~

只想说xpath是真心好用，第二次用，解析参数的时候很方便。

#-*-coding:utf-8 -*-
import urllib
import re
import json
import urllib2
from lxml import etree
import requests
import time
from Queue import Queue
import matplotlib.pyplot as plt
URL = 'http://quote.fx678.com/exchange/WH'
nation_que = Queue()
nation = Queue()
high = Queue()
start_time = Queue()

Chart = []
def __cmp__(self, other):
if self.time < other.time:
return -1
elif self.time == other.time:
return 0
else:
return 1
class Share:
def __init__(self,time,score):
self.time = time
self.score = score

def __getitem__(self, key):
self.item.get(key)

def __cmp__(self, other):
return cmp(self.time, other.time)

def __str__(self):
return self.time + " " + str(self.score)

def download(url, headers, num_try=2):
while num_try >0:
num_try -= 1
try:
content = requests.get(url, headers=headers)
return content.text

except urllib2.URLError as e:
print 'Download error', e.reason

return None

def get_type_url():
headers = {
'User_agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36',
'Referer': 'http://quote.fx678.com/exchange/WH',
'Cookie': 'io=-voMclEjiizK9nWKALqB; UM_distinctid=15f5938ddc72db-089cf9ba58d9e5-31657c00-fa000-15f5938ddc8b24; Hm_lvt_d25bd1db5bca2537d34deae7edca67d3=1509030420; Hm_lpvt_d25bd1db5bca2537d34deae7edca67d3=1509031023',
'Accept-Language': 'zh-CN,zh;q=0.8',
'Accept-Encoding': 'gzip, deflate',
'Accept': '*/*'
}
content = download(URL,headers)
html = etree.HTML(content)
result = html.xpath('//a[@class="mar_name"]/@href')
for each in result:
print each
st = each.split('/')
nation_que.put(st[len(st)-1])

get_precent()

def get_precent():

while not nation_que.empty():
ss = nation_que.get(False)
print ss
url = 'http://api.q.fx678.com/history.php?symbol=' + ss +'&limit=288&resolution=5&codeType=8100&st=0.43342772855649625'
print url
headers = {'Accept':'application/json, text/javascript, */*; q=0.01',
'Accept-Encoding':'gzip, deflate',
'Accept-Language':'zh-CN,zh;q=0.8',
'Connection':'keep-alive',
'Host':'api.q.fx678.com',
'Origin':'http://quote.fx678.com',
'Referer':'http://quote.fx678.com/symbol/USD',
'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36'
}
num_try = 2
while num_try >0:
num_try -= 1
try:
content = requests.get(url, headers=headers)
html = json.loads(content.text)
st = html['h']
T_time = html['t']
if  len(st) > 0 and len(T_time) > 0:
nation.put(ss)
high.put(st)
start_time.put(T_time)
break
except urllib2.URLError as e:
print 'Download error', e.reason
nation_que.task_done()
draw_pict()

def sub_sort(array,array1,low,high):
key = array[low]
key1 = array1[low]
while low < high:
while low < high and array[high] >= key:
high -= 1
while low < high and array[high] < key:
array[low] = array[high]
array1[low] = array1[high]
low += 1
array[high] = array[low]
array1[high] = array1[low]
array[low] = key
array1[low] = key1
return low

def quick_sort(array,array1,low,high):
if low < high:
key_index = sub_sort(array,array1,low,high)
quick_sort(array,array1,low,key_index)
quick_sort(array,array1,key_index+1,high)

def draw_pict():
while True:
Nation = nation.get(False)
High = high.get(False)
Time = start_time.get(False)
T_time = []
High_Rate = []
num = 0
for each,high1 in zip(Time,High):
st = time.localtime(float(each))
if st.tm_min == 0:
T_time.append(st.tm_hour)
High_Rate.append(high1)

quick_sort(T_time,High_Rate,0,len(T_time)-1)

plt.plot(T_time,High_Rate, marker='*')
plt.show()
plt.title(Nation)
nation.task_done()
high.task_done()
break

if __name__ == '__main__':
get_type_url()