理想论坛有些长贴,针对这些长贴做统计可以知道某ID什么时段更活跃。
爬虫代码为:
#------------------------------------------------------------------------------------ # 理想论坛爬虫长贴版1.00,用于爬取单个长贴,数据存到文件里 # 再由insertDB.py读取插DB,sum.py取出分时段数据,statistics chart显示数据 # 2018年4月27日 #------------------------------------------------------------------------------------ from bs4 import BeautifulSoup import requests import threading import re import time import datetime import os import json import colorama from colorama import Fore, Back, Style colorama.init() user_agent='Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36' headers={'User-Agent':user_agent} # 存储数据文件的目录 folder="" #------------------------------------ # 以不同颜色在控制台输出文字 # pageUrl:论坛页url #------------------------------------ def log(text,color): if color=='red': print(Fore.RED + text+ Style.RESET_ALL) elif color=='green': print(Fore.GREEN + text+ Style.RESET_ALL) elif color=='yellow': print(Fore.YELLOW + text+ Style.RESET_ALL) else: print(text) #------------------------------------ # 找到并保存帖子的细节 # index:序号,url:地址,title:标题 #------------------------------------ def saveTopicDetail(index,url,title): infos=[] # 找到的子贴信息 tried=0; # 尝试次数 while(len(infos)==0): try: rsp=requests.get(url,headers=headers) rsp.encoding = 'gb18030' #解决中文乱码问题的关键 soup= BeautifulSoup(rsp.text,'html.parser',from_encoding='gb2312') session = requests.session() session.keep_alive = False for divs in soup.find_all('div',class_="postinfo"): # 用正则表达式将多个空白字符替换成一个空格 RE = re.compile(r'(\s+)') line=RE.sub(" ",divs.text) arr=line.split(' ') arrLength=len(arr) if arrLength==7: info={'楼层':arr[1], '作者':arr[2].replace('只看:',''), '日期':arr[4], '时间':arr[5],'title':title,'url':url} infos.append(info) elif arrLength==8: info={'楼层':arr[1], '作者':arr[2].replace('只看:',''), '日期':arr[5], '时间':arr[6],'title':title,'url':url} infos.append(info) #存文件 filename=folder+"/"+str(index)+'.json' with open(filename,'w',encoding='utf-8') as fObj: json.dump(infos,fObj) except Exception as e: log("saveTopicDetail访问"+url+"时出现异常:"+str(e),'red') time.sleep(5) # 如果出现异常,休息五秒后再试 tried=tried+1 if(tried>4): log("尝试5次仍无法访问:"+url+",只得跳过此页",'yellow') break continue #------------------------------------ # 入口函数 # pageCount共多少页,pageUrl:长贴地址,title:帖子标题 #------------------------------------ def main(pageCount,url,title): # 创建目录 currTime=time.strftime('%H_%M_%S',time.localtime(time.time())) global folder folder="./"+currTime os.makedirs(folder) print("目录"+folder+"创建完成") # 获取主贴 topics=[] # 主帖数组 topic={'pageCount':pageCount,'url':url,'title':title} topics.append(topic) n=len(topics) log("共读取到:"+str(n)+"个主贴",'green') # 获取主贴及其子贴 finalTopics=[] index=0 for topic in topics: end=int(topic['pageCount'])+1 title=topic['title'] for i in range(1,end): pattern='-(\d+)-(\d+)-(\d+)' newUrl=re.sub(pattern,lambda m:'-'+m.group(1)+'-'+str(i)+'-'+m.group(3),topic['url']) #print(newUrl) newTopic={'index':index,'url':newUrl,'title':title} finalTopics.append(newTopic) index=index+1 n=len(finalTopics) log("共读取到:"+str(n)+"个帖子",'green') # 遍历finalTopics for newTopic in finalTopics: saveTopicDetail(newTopic['index'],newTopic['url'],newTopic['title']); # 开始 main(240,'http://www.55188.com/thread-8047146-1-2.html','仁义宾实盘8 真正实盘实时交流!有股票,有思路,有策略,有分析,有分享,有活动!')
插DB代码为:
# 读取理想论坛爬虫1.06生成的数据,然后写入DB import pymysql import time import datetime import os import json # 数据库插值 def insertDB(sqls): conn=pymysql.connect(host=',db='test',charset='utf8') sum=0;# 插入成功总数 for sql in sqls: try: count=conn.query(sql) #单条是否成功 except Exception as e: print("sql'"+sql+"'出现异常:"+str(e)) continue; if count==0: print(sql+'插入记录失败'); sum+=count conn.commit() conn.close() return sum # 入口函数 def main(folder): starttime = datetime.datetime.now() allinfos=[] for filename in os.listdir(folder): filePathname=folder+"/"+filename with open(filePathname,'r',encoding='utf-8') as fObj: infos=json.load(fObj) #print(infos) allinfos.extend(infos) sqls=[] for info in allinfos: sql="insert into test.topicryb(floor,author,tdate,ttime,addtime,url,title) values ('"+info['楼层']+"','"+info['作者']+"','"+info['日期']+"','"+info['时间']+"',"+"now(),'"+info['url']+"','"+info['title']+"' "+" )" sqls.append(sql) print("将向数据库插入"+str(len(sqls))+"条记录") retval=insertDB(sqls) print("已向数据库插入"+str(retval)+"条记录") endtime = datetime.datetime.now() print("插数据用时"+str((endtime - starttime).seconds)+"秒") # 开始 main("./18_09_57")
取数据进行统计的代码为:
# 对发帖时间进行统计 import re import pymysql # 入口函数 def main(): dic={':0} conn=pymysql.connect(host=',db='test',charset='utf8') cs=conn.cursor() cs.execute("select * from topicryb where author='仁义宾' ") results = cs.fetchall() for row in results: ttime=row[4] hour=ttime.split(':')[0] dic[hour]=dic[hour]+1 conn.close() print(dic) # 开始 main()
得到数据是:
C:\Users\horn1\Desktop\python\29>python sum.py {': 22} C:\Users\horn1\Desktop\python\29>
进行绘图的JS代码是:
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd"> <html> <head> <title> New Document </title> <meta name="Generator" content="EditPlus"> <meta name="Author" content=""> <meta name="Keywords" content=""> <meta name="Description" content=""> </head> <script src="ichart.1.2.min.js"></script> <body> <div id='canvasDiv'></div> </body> </html> <script type="text/javascript"> <!-- var dic={'00': 9, '01': 0, '02': 0, '03': 0, '04': 1, '05': 1, '06': 4, '07': 27, '08': 47, '09': 259, '10': 318, '11': 216, '12': 97, '13': 201, '14': 201, '15': 133, '16': 85, '17': 82, '18': 80, '19': 84, '20': 68, '21': 66, '22': 48, '23': 22}; //定义数据 var data = [ {name : '0-1点', value : dic['00'],color:'#a5c2d5'}, {name : '1-2点', value : dic['01'],color:'#cbab4f'}, {name : '2-3点', value : dic['02'],color:'#76a871'}, {name : '3-4点', value : dic['03'],color:'#76a871'}, {name : '4-5点', value : dic['04'],color:'#a56f8f'}, {name : '5-6点', value : dic['05'],color:'#c12c44'}, {name : '6-7点', value : dic['06'],color:'#a56f8f'}, {name : '7-8点', value : dic['07'],color:'#9f7961'}, {name : '8-9点', value : dic['08'],color:'#76a871'}, {name : '9-10点', value : dic['09'],color:'#6f83a5'}, {name : '10-11点',value : dic['10'],color:'#a5c2d5'}, {name : '11-12点',value : dic['11'],color:'#cbab4f'}, {name : '12-13点',value : dic['12'],color:'#76a871'}, {name : '13-14点',value : dic['13'],color:'#76a871'}, {name : '14-15点',value : dic['14'],color:'#a56f8f'}, {name : '15-16点',value : dic['15'],color:'#c12c44'}, {name : '16-17点',value : dic['16'],color:'#a56f8f'}, {name : '17-18点',value : dic['17'],color:'#9f7961'}, {name : '18-19点',value : dic['18'],color:'#76a871'}, {name : '19-20点',value : dic['19'],color:'#6f83a5'}, {name : '20-21点',value : dic['20'],color:'#c12c44'}, {name : '21-22点',value : dic['21'],color:'#a56f8f'}, {name : '22-23点',value : dic['22'],color:'#9f7961'}, {name : '23-24点',value : dic['23'],color:'#76a871'} ]; $(function(){ var chart = new iChart.Column2D({ render : 'canvasDiv',//渲染的Dom目标,canvasDiv为Dom的ID data: data,//绑定数据 title : 'http://www.55188.com/thread-8047146-1-2.html中 ID‘仁义宾’24小时每时段发帖量统计',//设置标题 width : 1400,//设置宽度,默认单位为px height : 400,//设置高度,默认单位为px shadow:true,//激活阴影 shadow_color:'#c7c7c7',//设置阴影颜色 coordinate:{//配置自定义坐标轴 scale:[{//配置自定义值轴 position:'left',//配置左值轴 start_scale:0,//设置开始刻度为0 end_scale:500,//设置结束刻度 scale_space:50,//设置刻度间距 listeners:{//配置事件 parseText:function(t,x,y){//设置解析值轴文本 return {text:t+""} } } }] } }); //调用绘图方法开始绘图 chart.draw(); }); //--> </script>
最后我们就看到这张图片:
全体代码+数据下载:https://files.cnblogs.com/files/xiandedanteng/lixryb20180427.rar