教你用Python爬蟲股票評論，簡單分析股民使用者情緒
阿新 • • 發佈：2019-01-07
一、背景
股民是網路使用者的一大群體，他們的網路情緒在一定程度上反映了該股票的情況，也反映了股市市場的波動情況。作為一隻時間充裕的研究僧，我課餘時間準備寫個小程式碼get一下股民的評論資料，分析使用者情緒的走勢。程式碼還會修改，因為結果不準確，哈哈！
二、資料來源
本次專案不用於商用，資料來源於東方財富網，由於物理條件，我只獲取了一隻股票的部分評論，沒有爬取官方的帖子，都是獲取的散戶的評論。
三、資料獲取
Python是個好工具，這次我使用了selenium和PhantomJS組合進行爬取網頁資料，當然還是要分析網頁的dom結構拿到自己需要的資料。
爬蟲部分：
from selenium import webdriver import time import json import re # from HTMLParser import HTMLParser from myNLP import * # from lxml import html # import requests class Crawler: url = '' newurl = set() headers = {} cookies = {} def __init__(self, stocknum, page): self.url = 'http://guba.eastmoney.com/list,'+stocknum+',5_'+page+'.html' cap = webdriver.DesiredCapabilities.PHANTOMJS cap["phantomjs.page.settings.resourceTimeout"] = 1000 #cap["phantomjs.page.settings.loadImages"] = False #cap["phantomjs.page.settings.localToRemoteUrlAccessEnabled"] = True self.driver = webdriver.PhantomJS(desired_capabilities=cap) def crawAllHtml(self,url): self.driver.get(url) time.sleep(2) # htmlData = requests.get(url).content.decode('utf-8') # domTree = html.fromstring(htmlData) # return domTree def getNewUrl(self,url): self.newurl.add(url) def filterHtmlTag(self, htmlStr): self.htmlStr = htmlStr #先過濾CDATA re_cdata=re.compile('//<!CDATA [>]∗// >',re.I) #匹配CDATA re_script=re.compile('<\s*script[^>]*>[^<]*<\s*/\s*script\s*>',re.I)#Script re_style=re.compile('<\s*style[^>]*>[^<]*<\s*/\s*style\s*>',re.I)#style re_br=re.compile('<br\s*?/?>')#處理換行 re_h=re.compile('</?\w+[^>]*>')#HTML標籤 re_comment=re.compile('<!--[^>]*-->')#HTML註釋 s=re_cdata.sub('',htmlStr)#去掉CDATA s=re_script.sub('',s) #去掉SCRIPT s=re_style.sub('',s)#去掉style s=re_br.sub('\n',s)#將br轉換為換行 blank_line=re.compile('\n+')#去掉多餘的空行 s = blank_line.sub('\n',s) s=re_h.sub('',s) #去掉HTML 標籤 s=re_comment.sub('',s)#去掉HTML註釋 #去掉多餘的空行 blank_line=re.compile('\n+') s=blank_line.sub('\n',s) return s def getData(self): comments = [] self.crawAllHtml(self.url) postlist = self.driver.find_elements_by_xpath('//*[@id="articlelistnew"]/div') for post in postlist: href = post.find_elements_by_tag_name('span')[2].find_elements_by_tag_name('a') if len(href): self.getNewUrl(href[0].get_attribute('href')) # if len(post.find_elements_by_xpath('./span[3]/a/@href')): # self.getNewUrl('http://guba.eastmoney.com'+post.find_elements_by_xpath('./span[3]/a/@href')[0]) for url in self.newurl: self.crawAllHtml(url) time = self.driver.find_elements_by_xpath('//*[@id="zwconttb"]/div[2]') post = self.driver.find_elements_by_xpath('//*[@id="zwconbody"]/div') age = self.driver.find_elements_by_xpath('//*[@id="zwconttbn"]/span/span[2]') if len(post) and len(time) and len(age): text = self.filterHtmlTag(post[0].text) if len(text): tmp = myNLP(text) comments.append({'time':time[0].text,'content':tmp.prob, 'age':age[0].text}) commentlist = self.driver.find_elements_by_xpath('//*[@id="zwlist"]/div') if len(commentlist): for comment in commentlist: time = comment.find_elements_by_xpath('./div[3]/div[1]/div[2]') post = comment.find_elements_by_xpath('./div[3]/div[1]/div[3]') age = comment.find_elements_by_xpath('./div[3]/div[1]/div[1]/span[2]/span[2]') if len(post) and len(time) and len(age): text = self.filterHtmlTag(post[0].text) if len(text): tmp = myNLP(text) comments.append({'time':time[0].text,'content':tmp.prob, 'age':age[0].text}) return json.dumps(comments)
儲存部分：
這部分其實可以用資料庫來做，但是由於只是試水，就簡單用json檔案來存部分資料：
import io class File: name = '' type = '' src = '' file = '' def __init__(self,name, type, src): self.name = name self.type = type self.src = src filename = self.src+self.name+'.'+self.type self.file = io.open(filename,'w+', encoding = 'utf-8') def inputData(self,data): self.file.write(data.decode('utf-8')) self.file.close() def closeFile(self): self.file.close()
測試用的local伺服器：
這裡只是為了要用瀏覽器瀏覽資料圖，由於需要讀取資料，js沒有許可權操作本地的檔案，只能利用一個簡單的伺服器來弄了：
import SimpleHTTPServer
import SocketServer;
PORT = 8000
Handler = SimpleHTTPServer.SimpleHTTPRequestHandler
httpd = SocketServer.TCPServer(("", PORT), Handler);
httpd.serve_forever()
NLP部分：snowNLP這個包還是用來評價買賣東西的評論比較準確
不是專門研究自然語言的，直接使用他人的演算法庫。這個snowNLP可以建立一個訓練，有空自己來弄一個關於股票評論的。
#!/usr/bin/env python
# -*- coding: UTF-8 -*-
from snownlp import SnowNLP
class myNLP:
prob = 0.5
def _init_(self, text):
self.prob = SnowNLP(text).sentiments 主排程：
# -*- coding: UTF-8 -*-
'''''
Created on 2017年5月17日
@author: luhaiya
@id: 2016110274
@description:
'''
#http://data.eastmoney.com/stockcomment/ 所有股票的列表資訊
#http://guba.eastmoney.com/list,600000,5.html 某隻股票股民的帖子頁面
#http://quote.eastmoney.com/sh600000.html?stype=stock 查詢某隻股票
from Crawler import *
from File import *
import sys
default_encoding = 'utf-8'
if sys.getdefaultencoding() != default_encoding:
reload(sys)
sys.setdefaultencoding(default_encoding)
def main():
stocknum = str(600000)
total = dict()
for i in range(1,10):
page = str(i)
crawler = Crawler(stocknum, page)
datalist = crawler.getData()
comments = File(stocknum+'_page_'+page,'json','./data/')
comments.inputData(datalist)
data = open('./data/'+stocknum+'_page_'+page+'.json','r').read()
jsonData = json.loads(data)
for detail in jsonData:
num = '1' if '年' not in detail['age'].encode('utf-8') else detail['age'].encode('utf-8').replace('年','')
num = float(num)
date = detail['time'][4:14].encode('utf-8')
total[date] = total[date] if date in total.keys() else {'num':0, 'content':0}
total[date]['num'] = total[date]['num'] + num if total[date]['num'] else num
total[date]['content'] = total[date]['content'] + detail['content']*num if total[date]['content'] else detail['content']*num
total = json.dumps(total)
totalfile = File(stocknum,'json','./data/')
totalfile.inputData(total)
if __name__ == "__main__":
main() 四、前端資料展示
使用百度的echarts。使用者的情緒是使用當天所有評論的情緒值的加權平均，加權係數與使用者的股齡正相關。
<!DOCTYPE html>
<html>
<head>
<meta charset="UTF-8">
<title>分析圖表</title>
<style>
body{texr-align:center;}
#mainContainer{width:100%;}
#fileContainer{width:100%; text-align:center;}
#picContainer{width: 800px;height:600px;margin:0 auto;}
</style>
</head>
<body>
<div id = 'mainContainer'>
<div id = 'fileContainer'>這裡是資料夾列表</div>
<div id = 'picContainer'></div>
</div>
<script src="http://apps.bdimg.com/libs/jquery/2.1.1/jquery.min.js"></script>
<script src = "./echarts.js"></script>
<script>
main();
function main(){
var stocknum = 600000;
getDate(stocknum);
}
function getDate(stocknum){
var src = "./data/"+stocknum+".json";
$.getJSON(src, function (res){
var date = [];
for(var key in res){
key = key.replace('-','/').replace('-','/');
date.push(key);
}
date.sort();
data = [];
for (var i = 0; i < date.length; i++) {
dat = date[i].replace('/','-').replace('/','-');
data.push(res[dat]['content']/res[dat]['num']);
}
drawPic(date,data);
})
}
function drawPic(date, data){
//initialize and setting options
var myChart = echarts.init(document.getElementById('picContainer'));
option = {
tooltip: {
trigger: 'axis',
position: function (pt) {
return [pt[0], '10%'];
}
},
title: {
left: 'center',
text: '股票情緒走向圖',
},
toolbox: {
feature: {
dataZoom: {
yAxisIndex: 'none'
},
restore: {},
saveAsImage: {}
}
},
xAxis: {
type: 'category',
boundaryGap: false,
data: date
},
yAxis: {
type: 'value',
boundaryGap: [0, '100%']
},
dataZoom: [{
type: 'inside',
start: 0,
end: 10
}, {
start: 0,
end: 10,
handleIcon: 'M10.7,11.9v-1.3H9.3v1.3c-4.9,0.3-8.8,4.4-8.8,9.4c0,5,3.9,9.1,8.8,9.4v1.3h1.3v-1.3c4.9-0.3,8.8-4.4,8.8-9.4C19.5,16.3,15.6,12.2,10.7,11.9z M13.3,24.4H6.7V23h6.6V24.4z M13.3,19.6H6.7v-1.4h6.6V19.6z',
handleSize: '80%',
handleStyle: {
color: '#fff',
shadowBlur: 3,
shadowColor: 'rgba(0, 0, 0, 0.6)',
shadowOffsetX: 2,
shadowOffsetY: 2
}
}],
series: [
{
name:'stocknum',
type:'line',
smooth:true,
symbol: 'none',
sampling: 'average',
itemStyle: {
normal: {
color: 'rgb(255, 70, 131)'
}
},
areaStyle: {
normal: {
color: new echarts.graphic.LinearGradient(0, 0, 0, 1, [{
offset: 0,
color: 'rgb(255, 158, 68)'
}, {
offset: 1,
color: 'rgb(255, 70, 131)'
}])
}
},
data: data
}
]
};
//draw pic
myChart.setOption(option);
}
</script>
</body>
</html>
圖1是我分析使用者情緒畫出的時間推進圖，理論上小於0.5表消極情緒，大於0.5表示積極情緒。圖2是實際股價的走勢。