最近在看mongodb，然后会用了一些最简单的mongodb的操作，然后想着结合股票信息的数据的抓取，然后将数据存储在mongodb中，对于mongo和数据库的最大的区别是，mongo不需要建表，直接进行存储，然后在选择数据表的时候在进行插入数据的时候要将str格式的字符串转换成json的格式进行插入，这个我在插入数据的时候调试了十多分钟，一直以为是自己字符串的原因，然后看了看插入数据的格式和百度，然后才发现这点。然后我是插入在本机的test.Share表中的，然后其他的注重点就没有什么了～代码写的很丑，冗余也很大，还是会继续更新～并且程序是但进程进行的数据抓取～嗯～ 很蠢～
#-*-coding:utf-8 -*-
import urllib
import re
import json
import urllib2
from lxml import etree
import requests
import time
from Queue import Queue
from pymongo import MongoClient
import matplotlib.pyplot as plt
URL = 'http://quote.fx678.com/exchange/WH'
nation_que = Queue()
client = MongoClient('localhost',27017)
db = client.test
Share = db.Share 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 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 current_quto = Queue()
open_quto = Queue()
high_quto = Queue()
low_quto = Queue()
close_quto = Queue()
update_time = Queue()
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')
result1 = html.xpath('//td/text()')
num = 0
for each in result1: if num%6 == 0:
current_quto.put(each)
num += 1
elif num%6 == 1:
open_quto.put(each)
num += 1
elif num%6 == 2:
high_quto.put(each)
num += 1
elif num%6 == 3:
low_quto.put(each)
num += 1
elif num %6 == 4:
close_quto.put(each)
num +=1
elif num %6 == 5:
update_time.put(each)
num +=1
#while not
for each in result:
st = each.split('/')
nation_que.put(st[len(st)-1]) get_precent() def get_precent(): while not nation_que.empty():
if not update_time.empty():
time_update = update_time.get(False)
update_time.task_done()
if not current_quto.empty():
new_rates = current_quto.get(False)
current_quto.task_done()
if not open_quto.empty():
opening = open_quto.get(False)
open_quto.task_done()
if not high_quto.empty():
high = high_quto.get(False)
high_quto.task_done()
if not low_quto.empty():
low = low_quto.get(False)
low_quto.task_done()
if not close_quto.empty():
closing = close_quto.get(False)
close_quto.task_done() ss = nation_que.get(False)
print ss
print low
print high
print time_update
print new_rates
print opening url = 'http://api.q.fx678.com/history.php?symbol=' + ss +'&limit=288&resolution=5&codeType=8100&st=0.8274405615006541'
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:
draw_pict(ss,T_time,st,time_update,new_rates,opening,high,low,closing)
break
except urllib2.URLError as e:
print 'Download error', e.reason
nation_que.task_done()
List = []
def draw_pict(name,T_time1,high_rate,time_update,new_rate,opening,high,low,closing): High = T_time1
Time = high_rate
High_Rate = []
T_time = []
mmap = "{\"Type\":\"%s\",\"Current_quto\":\"%s\",\"Opening_quto\":\"%s\",\"High_quto\":\"%s\",\"low_quto\":\"%s\",\"Closing_quto\":\"%s\",\"Update_Time\":\"%s\",\"Real_TIme_infor\":{" % ( name, new_rate, opening, high, low, closing, time_update)
print mmap
flag = 0
for each,high1 in zip(T_time1,high_rate):
if flag == 1:
mmap += ","
else:
flag = 1
mm = "\"%s\":\"%s\""%(each,high1) st = time.localtime(float(each))
mmap += mm
if st.tm_min == 0:
T_time.append(st.tm_hour)
High_Rate.append(high1)
else:
pass
mmap += "}}"
mmap1 = json.loads(mmap)
print mmap1
Share.insert(mmap1)
if len(T_time) == len(High_Rate):
quick_sort(T_time,High_Rate,0,len(High_Rate)-1)
List.append(High_Rate) def draw_picture():
colu = len(List) num = 1
for each in List:
plt.subplot(colu/2 + 1,2,num)
num+=1 list = each
T_time = []
for i in range(len(list)):
T_time.append(i)
print len(list)
print len(T_time)
plt.plot(T_time, list, marker='*') plt.show()
plt.title('Share Message') if __name__ == '__main__':
get_type_url()
draw_picture()