**
python之websocket数据爬取
**
首先我爬取的是 货币网的 https://www.zbg.com/exOtc
爬取商家的购买和出售的数据
下面是我利用websocket库进行爬取的代码
不废话,直接上码.
import json, time
from websocket import create_connection
class OTC:
#number 是区分购买和出售
number = 0
#这个 url 是websocket 长连接的url
url = 'wss://www.zbg.com/exchange/base/socket/WebSocketHandler'
#定义好请求的数据
exc_symbol = {
'currencyName': 'usdt',
'pageIndex': 1,
'pageSize': 10,
'salesTerritory': 'cny',
'subscribe_event': 'trade',
'tradeType': 0,
}
exc_symbol_2 = {
'currencyName': 'usdt',
'pageIndex': 1,
'pageSize': 10,
'salesTerritory': 'cny',
'subscribe_event': 'trade',
'tradeType': 1,
}
def get_web_socket(self):
while 1:
if self.number == 0:
try:
# 链接服务器
ws = create_connection(self.url)
except Exception as e:
print('retry to connect...')
continue
# 发送消息,把请求的数据类似于post表单的数据发送给服务器获取想要的数据
ws.send(json.dumps(self.exc_symbol))
# 接收消息,然后把数据处理一下打印!
data = ws.recv()
result = json.loads(data)
tradeList = result['datas']['tradeList']
spiderdata = []
for trade in tradeList:
info_data = {}
info_data['商家'] = (trade['userName']) # 商家信息
info_data['订单量'] = (trade['lastOrderCount']) # 订单量
number = trade['amount'][0:6]
info_data['数量'] = number # 数量
fixedPrice = trade['fixedPrice'][0:6]
info_data['单价'] = fixedPrice # 单价
spiderdata.append(info_data)
print(spiderdata)
print("-" * 200)
self.number += 1
# 数据监测间隔
time.sleep(1)
# 这里是爬取出售的数据
if self.number == 1:
try:
ws = create_connection(self.url)
except Exception as e:
print('retry to connect...')
continue
# 发送消息
ws.send(json.dumps(self.exc_symbol_2))
# 接收消息
data = ws.recv()
result = json.loads(data)
tradeList = result['datas']['tradeList']
spiderdata = []
for trade in tradeList:
info_data = {}
info_data['商家'] = (trade['userName']) # 商家信息
info_data['订单量'] = (trade['lastOrderCount']) # 订单量
number = trade['amount'][0:6]
info_data['数量'] = number # 数量
fixedPrice = trade['fixedPrice'][0:6]
info_data['单价'] = fixedPrice # 单价
spiderdata.append(info_data)
print(spiderdata)
print("-" * 200)
self.number += 1
# 数据监测间隔
time.sleep(1)
if self.number == 2:
break
otc = OTC()
otc.get_web_socket()
这是我爬取的结果
谢谢!