python实现数据爬取-清洗-持久化存储-数据平台可视化
Posted
tags:
篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了python实现数据爬取-清洗-持久化存储-数据平台可视化相关的知识，希望对你有一定的参考价值。
基于python对淘宝模特个人信息进行筛选爬取，数据清洗，持久化写入mysql数据库.使用django对数据库中的数据信息筛选并生成可视化报表进行分析。
数据爬取，筛选，存库：
# -*- coding:utf-8 -*-
import requests
from bs4 import BeautifulSoup
import sys
import re
reload(sys)
sys.setdefaultencoding(‘utf-8‘)
import MySQLdb
import chardet
conn= MySQLdb.connect(
host=‘localhost‘,
port = 数据库端口,
user=‘root‘,
passwd=‘数据库密码
db =‘xxnlove‘,
charset=‘utf8‘
)
cur = conn.cursor()
cur.execute("create table model(name text(225),age varchar(10),blood varchar(10),school text(225),height varchar(10),weight varchar(10),Measurements text(225),cup varchar(20),location text(225))ENGINE=InnoDB DEFAULT CHARSET=utf8;")
#CREATE DATABASE gmtdb DEFAULT CHARACTER SET utf8mb4;
for num in range(521,1314):
try:
URL = ‘http://mm.taobao.com/json/request_top_list.htm?page=%d‘ % num
#print "现在爬取的网站url是：" + URL
response = requests.get(URL)
response.encoding = ‘gb2312‘
text = response.text
soup = BeautifulSoup(text, ‘lxml‘)
for model in soup.select(".list-item"):
try:
model_id = model.find(‘span‘, {‘class‘: ‘friend-follow J_FriendFollow‘})[‘data-userid‘]
json_url = "http://mm.taobao.com/self/info/model_info_show.htm?user_id=%d" % int(model_id)
response_json = requests.get(json_url)
response_json.encoding = ‘gb2312‘
text_response_json = response_json.text
soup_json = BeautifulSoup(text_response_json, ‘lxml‘)
#print "***********************************" + model.find(‘a‘, {‘class‘: ‘lady-name‘}).string + "*********************************"
#print "模特的名字:" + model.find(‘a‘, {‘class‘: ‘lady-name‘}).string
name = model.find(‘a‘, {‘class‘: ‘lady-name‘}).string
#print "模特的年龄："+ model.find(‘p‘, {‘class‘: ‘top‘}).em.strong.string
age = model.find(‘p‘, {‘class‘: ‘top‘}).em.strong.string
blood = soup_json.find_all(‘li‘, {‘class‘: ‘mm-p-cell-right‘})[1].span.string
# if blood is None:
# blood = "None"
school = soup_json.find_all(‘li‘)[5].span.string
height = soup_json.find(‘li‘, {‘class‘: ‘mm-p-small-cell mm-p-height‘}).p.string
weight = soup_json.find(‘li‘, {‘class‘: ‘mm-p-small-cell mm-p-weight‘}).p.string
Measurements = soup_json.find(‘li‘, {‘class‘: ‘mm-p-small-cell mm-p-size‘}).p.string
location = model.find(‘p‘, {‘class‘: ‘top‘}).span.string
cup = soup_json.find(‘li‘, {‘class‘: ‘mm-p-small-cell mm-p-bar‘}).p.string
sqli="insert into model values(%s,%s,%s,%s,%s,%s,%s,%s,%s)"
cur.execute(sqli,(name,age,blood,school,height,weight,Measurements,cup,location))
#print "罩杯：" + soup_json.find(‘li‘, {‘class‘: ‘mm-p-small-cell mm-p-bar‘}).p.string
‘‘‘
print "生日：" + soup_json.find(‘li‘, {‘class‘: ‘mm-p-cell-left‘}).span.string
blood = soup_json.find_all(‘li‘, {‘class‘: ‘mm-p-cell-right‘})[1].span.string
if blood is None:
blood = "无"
print "血型：" + blood
print "学校/专业：" + soup_json.find_all(‘li‘)[5].span.string
print "身高：" + soup_json.find(‘li‘, {‘class‘: ‘mm-p-small-cell mm-p-height‘}).p.string
print "体重：" + soup_json.find(‘li‘, {‘class‘: ‘mm-p-small-cell mm-p-weight‘}).p.string
print "三围：" + soup_json.find(‘li‘, {‘class‘: ‘mm-p-small-cell mm-p-size‘}).p.string
print "罩杯：" + soup_json.find(‘li‘, {‘class‘: ‘mm-p-small-cell mm-p-bar‘}).p.string
print "鞋码：" + soup_json.find(‘li‘, {‘class‘: ‘mm-p-small-cell mm-p-shose‘}).p.string
print "模特所在地："+ model.find(‘p‘, {‘class‘: ‘top‘}).span.string
print "模特的id："+ model.find(‘span‘, {‘class‘: ‘friend-follow J_FriendFollow‘})[‘data-userid‘]
print "模特的标签："+ model.find_all(‘p‘)[1].em.string
print "模特的粉丝数："+ model.find_all(‘p‘)[1].strong.string
print "模特的排名:"+ [text for text in model.find(‘div‘, {‘class‘: ‘popularity‘}).dl.dt.stripped_strings][0]
print model.find(‘ul‘, {‘class‘: ‘info-detail‘}).get_text(" ",strip=True)
print "模特的个人资料页面:" +"http:"+ model.find(‘a‘, {‘class‘: ‘lady-name‘})[‘href‘]
print "模特的个人作品页面:" +"http:"+ model.find(‘a‘, {‘class‘: ‘lady-avatar‘})[‘href‘]
print "模特的个人头像：" + "http:" + model.find(‘img‘)[‘src‘]
print "***********************************" + model.find(‘a‘, {‘class‘: ‘lady-name‘}).string + "*********************************"
print "\n"
‘‘‘
except:
print "error"
except:
print num + "page is error"
cur.close()
conn.commit()
conn.close()数据库结构：
写入数据库中的模特记录数量：
写入数据库中模特信息部分图：
django 实现图表展示：
#coding:utf-8 # Create your views here. from django.shortcuts import render,render_to_response from django.http import HttpResponse,HttpResponseRedirect import MySQLdb import sys import re import json import jieba from operator import itemgetter from pytagcloud import create_tag_image, make_tags import random import time import smtplib from email.mime.text import MIMEText reload(sys) sys.setdefaultencoding(‘utf-8‘) conn= MySQLdb.connect( host=‘localhost‘, port = 端口, user=‘root‘, passwd=‘密码‘, db =‘xxnlove‘, charset=‘utf8‘ ) def receive_message(request): if request.method == ‘POST‘: name = request.POST[‘name‘] email = request.POST[‘email‘] subject = request.POST[‘subject‘] message = request.POST[‘message‘] cur = conn.cursor() sql = "insert into message values(%s,%s,%s,%s)" cur.execute(sql,(name,email,subject,message)) cur.close() conn.commit() conn.close() return render_to_response(‘index.html‘) def send_email(request): _user = "[email protected]" _pwd = "**************" _to = "[email protected]" msg = MIMEText("Test") msg["Subject"] = "don‘t panic" msg["From"] = _user msg["To"] = _to try: s = smtplib.SMTP_SSL("smtp.qq.com", 465) s.login(_user, _pwd) s.sendmail(_user, _to, msg.as_string()) s.quit() return HttpResponse("邮件发送成功") except smtplib.SMTPException,e: return HttpResponse("Falied,%s"%e ) def create_pictures(request): cur = conn.cursor() sql = "select school from model " cur.execute(sql) rows = cur.fetchall() cur.close() conn.commit() conn.close() fclist = [] for row in rows: fclist.append(row[0].encode("utf-8")) fcstr = " ".join(fclist) wg = jieba.cut_for_search(fcstr) wd = {} nonsense = [u"我的", u"什么", u"你好"] for w in wg: if len(w) < 2: continue elif w in nonsense: continue try: str(w) continue finally: if w not in wd: wd[w] = 1 else: wd[w] += 1 swd = sorted(wd.iteritems(), key=itemgetter(1), reverse=True) swd = swd[1:100] tags = make_tags(swd,maxsize = 100) create_tag_image(tags, ‘./modles/static/1.jpg‘, #background=(0, 0, 0, 255), size=(500, 300), fontname="STKAITI") # cur.close() # conn.commit() # conn.close() return render(request,‘index.html‘) def cloud(request): return render(request,‘cloud.html‘) def index(request): return render(request,‘index.html‘) def search(request): if request.method == ‘POST‘: modelname = request.POST[‘name‘] sql = "select * from model where name=‘%s‘" % modelname cur = conn.cursor() try: search = cur.execute(sql) info = cur.fetchmany(search) name = info[0][0] age = info[0][1] school = info[0][3] school = ‘‘.join(school.split()) height = info[0][4] weight = info[0][5] Measurements = info[0][6] return render(request, ‘index.html‘, {‘name‘: name,‘age‘: age,‘school‘:school,‘height‘:height,‘weight‘:weight,‘Measurements‘:Measurements}) except: prompt = "sorry: 数据库中没有 "+modelname+" 这个模特的信息" return render(request, ‘index.html‘, {‘prompt‘: prompt}) cur.close() conn.commit() conn.close() else: return HttpResponse(‘提交的方式不是post‘) def show(request): cur = conn.cursor() agedata = [] category = [] for i in range(10,40): category.append(i) age = i sql = "select count(*) from model where age=‘%s‘" % age age = cur.execute(sql) i = int(cur.fetchmany(age)[0][0]) agedata.append(i) return render(request,‘show.html‘,{‘category‘:category,‘agedata‘:agedata}) cur.close() conn.commit() conn.close() def area(request): cur = conn.cursor() citydict = {‘jianxi‘:‘南昌市|赣州市|上饶市|吉安市|九江市|新余市|抚>州市|宜春市|景德镇市|萍乡市|鹰潭市|江西‘, ‘beijin‘:‘北京‘, ‘guangdong‘:‘东莞市|广州市|中山市|深圳市|惠州市|江门市|珠海市|汕头市|佛山市|湛江市|河源市|肇庆市|清远市|潮州市|韶关市|揭阳市|阳江市|梅州市|云浮市|茂名市|汕尾市|广东‘, ‘shandong‘:‘济南市|青岛市|临沂市|济宁市|菏泽市|烟台市|淄博市|泰安市|潍坊市|日照市|威海市|滨州市|东营市|聊城市|德州市|莱芜市|枣庄市|山东‘, ‘jiangsu‘:‘苏州市|徐州市|盐城市|无锡市|南京市|南通市|连云港市|常州市|镇江市|扬州市|淮安市|泰州市|宿迁市‘, ‘henan‘:‘郑州市|南阳市|新乡市|安阳市|洛阳市|信阳市|平顶山市|周口市|商丘市|开封市|焦作市|驻马店市|濮阳市|三门峡市|漯河市|许昌市|鹤壁市|济源市|河南‘, ‘shanghai‘:‘松江区|宝山区|金山区|嘉定区|南汇区|青浦区|>浦东新区|奉贤区|徐汇区|静安区|闵行区|黄浦区|杨浦区|虹口区|普陀区|闸北区|长宁区|崇明县|卢湾区|上海‘, ‘hebei‘: ‘石家庄市|唐山市|保定市|邯郸市|邢台市|河北区|沧州市|秦皇岛市|张家口市|衡水市|廊坊市|承德市|河北‘, ‘zhejiang‘:‘温州市|宁波市|杭州市|台州市|嘉兴市|金华市|>湖州市|绍兴市|舟山市|丽水市|衢州市|浙江‘, ‘shanxi‘:‘西安市|咸阳市|宝鸡市|汉中市|渭南市|安康市|榆>林市|商洛市|延安市|铜川市|陕西‘, ‘hunan‘:‘长沙市|邵阳市|常德市|衡阳市|株洲市|湘潭市|永州市|岳阳市|怀化市|郴州市|娄底市|益阳市|张家界市|湘西州|湖南‘, ‘chongqing‘:‘江北区|渝北区|沙坪坝区|九龙坡区|万州区|永川市|南岸区|酉阳县|北碚区|涪陵区|秀山县|巴南区|渝中区|石柱县|忠县|合川市|大渡口区|开县|长寿区|荣昌县|云阳县|梁平县|潼南县|江津市|彭水县|綦江县|璧山县|黔江区|大足县|巫山县|巫溪县|垫江县|丰都县|武隆县|万盛区|铜梁县|南川市|奉节县|双桥区|城口县|重庆‘, ‘fujian‘:‘漳州市|厦门市|泉州市|福州市|莆田市|宁德市|三明市|南平市|龙岩市|福建‘, ‘tianjin‘:‘和平区|北辰区|河北区|河西区|西青区|津南区|东丽区|武清区|宝坻区|红桥区|大港区|汉沽区|静海县|塘沽区|宁河县|蓟县|南开区|河东区|天津‘, ‘yunnan‘:‘昆明市|红河州|大理州|文山州|德宏州|曲靖市|昭通市|楚雄州|保山市|玉溪市|丽江地区|临沧地区|思茅地区|西双版纳州|怒江州|迪庆州|云南‘, ‘sichuan‘:‘成都市|绵阳市|广元市|达州市|南充市|德阳市|广安市|阿坝州|巴中市|遂宁市|内江市|凉山州|攀枝花市|乐山市|自贡市|泸州市|雅安市|宜宾市|资阳市|眉山市|甘孜州|四川‘, ‘guangxi‘:‘贵港市|玉林市|北海市|南宁市|柳州市|桂林市|梧州市|钦州市|来宾市|河池市|百色市|贺州市|崇左市|防城港市|广西‘, ‘anhui‘:‘安徽|芜湖市|合肥市|六安市|宿州市|阜阳市|安庆市|马鞍山市|蚌埠市|淮北市|淮南市|宣城市|黄山市|铜陵市|亳州市|池州市|巢湖市|滁州市‘, ‘hainan‘:‘三亚市|海口市|琼海市|文昌市|东方市|昌江县|陵水县|乐东县|保亭县|五指山市|澄迈县|万宁市|儋州市|临高县|白沙县|定安县|琼中县|屯昌县|海南‘, ‘jiangxi‘:‘南昌市|赣州市|上饶市|吉安市|九江市|新余市|抚州市|宜春市|景德镇市|萍乡市|鹰潭市|江西‘, ‘hubei‘:‘武汉市|宜昌市|襄樊市|荆州市|恩施州|黄冈市|孝感市|十堰市|咸宁市|黄石市|仙桃市|天门市|随州市|荆门市|潜江市|鄂州市|神农架林区|湖北‘, ‘shanxi2‘:‘太原市|大同市|运城市|长治市|晋城市|忻州市|临汾市|吕梁市|晋中市|阳泉市|朔州市|山西‘, ‘liaoning‘:‘大连市|沈阳市|丹东市|辽阳市|葫芦岛市|锦州市|朝阳市|营口市|鞍山市|抚顺市|阜新市|盘锦市|本溪市|铁岭市|辽宁‘, ‘taiwan‘:‘台北市|高雄市|台中市|新竹市|基隆市|台南市|嘉义市|台湾‘, ‘heilongjiang‘:‘齐齐哈尔市|哈尔滨市|大庆市|佳木斯市|双鸭山市|牡丹江市|鸡西市|黑河市|绥化市|鹤岗市|伊春市|大兴安岭地区|七台河市|黑龙江‘, ‘neimenggu‘:‘赤峰市|包头市|通辽市|呼和浩特市|鄂尔多斯市|乌海市|呼伦贝尔市|兴安盟|巴彦淖尔盟|乌兰察布盟|锡林郭勒盟|阿拉善盟|内蒙古‘, ‘guizhou‘:‘贵阳市|黔东南州|黔南州|遵义市|黔西南州|毕节地区|铜仁地区|安顺市|六盘水市‘, ‘gansu‘:‘兰州市|天水市|庆阳市|武威市|酒泉市|张掖市|陇南地区|白银市|定西地区|平凉市|嘉峪关市|临夏回族自治州|金昌市|甘南州|甘肃‘, ‘qinghai‘:‘西宁市|海西州|海东地区|海北州|果洛州|玉树州|黄南藏族自治州|青海‘, ‘xinjiang‘:‘乌鲁木齐市|伊犁州|昌吉州|石河子市|哈密地区|阿克苏地区|巴音郭楞州|喀什地区|塔城地区|克拉玛依市|和田地区|阿勒泰州|吐鲁番地区|阿拉尔市|博尔塔拉州|五家渠市|克孜勒苏州|图木舒克市|新疆‘, ‘xizang‘:‘拉萨市|山南地区|林芝地区|日喀则地区|阿里地区|昌都地区|那曲地区|西藏‘, ‘jiling‘:‘吉林市|长春市|白山市|延边州|白城市|松原市|辽源市|通化市|四平市|吉林‘, ‘ningxia‘:‘银川市|吴忠市|中卫市|石嘴山市|固原市|宁夏‘ } numdict = {} for key in citydict : sql = "select count(*) from model where location REGEXP ‘%s‘" % citydict[key] city = cur.execute(sql) num = int(cur.fetchmany(city)[0][0]) numdict[key] = num return render(request, ‘area.html‘,{‘jianxi‘:numdict[‘jianxi‘],‘beijin‘:numdict[‘beijin‘],‘guangdong‘:numdict[‘guangdong‘],‘shandong‘:numdict[‘shandong‘],‘jiangsu‘:numdict[‘jiangsu‘],‘henan‘:numdict[‘henan‘],‘shanghai‘:numdict[‘shanghai‘],‘hebei‘:numdict[‘hebei‘],‘zhejiang‘:numdict[‘zhejiang‘],‘shanxi‘:numdict[‘shanxi‘],‘hunan‘:numdict[‘hunan‘],‘chongqing‘:numdict[‘chongqing‘],‘fujian‘:numdict[‘fujian‘],‘tianjin‘:numdict[‘tianjin‘],‘yunnan‘:numdict[‘yunnan‘],‘sichuan‘:numdict[‘sichuan‘],‘guangxi‘:numdict[‘guangxi‘],‘anhui‘:numdict[‘anhui‘],‘hainan‘:numdict[‘hainan‘],‘jiangxi‘:numdict[‘jiangxi‘],‘hubei‘:numdict[‘hubei‘],‘shanxi2‘:numdict[‘shanxi2‘],‘liaoning‘:numdict[‘liaoning‘],‘taiwan‘:numdict[‘taiwan‘],‘heilongjiang‘:numdict[‘heilongjiang‘],‘neimenggu‘:numdict[‘neimenggu‘],‘guizhou‘:numdict[‘guizhou‘],‘gansu‘:numdict[‘gansu‘],‘qinghai‘:numdict[‘qinghai‘],‘xinjiang‘:numdict[‘xinjiang‘],‘xizang‘:numdict[‘xizang‘],‘jiling‘:numdict[‘jiling‘],‘ningxia‘:numdict[‘ningxia‘]})
{% load staticfiles %}
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<title>Charts demo</title>
<script src="{% static "js/echarts.js" %}"></script>
<script src="{% static "js/china.js" %}"></script>
<script src="https://code.jquery.com/jquery-3.1.1.min.js"></script>
</head>
<body>
<div id="main" style="height:600px;"></div>
<script type="text/javascript">
var myChart = echarts.init(document.getElementById(‘main‘));
option = {
title : {
text: ‘淘宝模特所在省份分部情况‘,
subtext: ‘‘,
x:‘center‘
},
tooltip : {
trigger: ‘item‘
},
legend: {
orient: ‘vertical‘,
x:‘left‘,
data:[‘‘]
},
dataRange: {
min: 0,
max: 2500,
x: ‘left‘,
y: ‘bottom‘,
text:[‘高‘,‘低‘], // 文本，默认为数值文本
calculable : true
},
toolbox: {
show: true,
orient : ‘vertical‘,
x: ‘right‘,
y: ‘center‘,
feature : {
mark : {show: true},
dataView : {show: true, readOnly: false},
restore : {show: true},
saveAsImage : {show: true}
}
},
roamController: {
show: true,
x: ‘right‘,
mapTypeControl: {
‘china‘: true
}
},
series : [
{
name: ‘人数‘,
type: ‘map‘,
mapType: ‘china‘,
roam: false,
itemStyle:{
normal:{label:{show:true}},
emphasis:{label:{show:true}}
},
data:[
{name: ‘北京‘,value: {{ beijin }}},
{name: ‘江西‘,value: {{ jianxi }}},
{name: ‘广东‘,value: {{ guangdong }}},
{name: ‘山东‘,value: {{ shandong }}},
{name: ‘江苏‘,value: {{ jiangsu }}},
{name: ‘河南‘,value: {{ henan }}},
{name: ‘上海‘,value: {{ shanghai }}},
{name: ‘河北‘,value: {{ hebei }}},
{name: ‘浙江‘,value: {{ zhejiang }}},
{name: ‘陕西‘,value: {{ shanxi }}},
{name: ‘湖南‘,value: {{ hunan }}},
{name: ‘重庆‘,value: {{ chongqing }}},
{name: ‘福建‘,value: {{ fujian }}},
{name: ‘天津‘,value: {{ tianjin }}},
{name: ‘云南‘,value: {{ yunnan }}},
{name: ‘四川‘,value: {{ sichuan }}},
{name: ‘广西‘,value: {{ guangxi }}},
{name: ‘安徽‘,value: {{ anhui }}},
{name: ‘海南‘,value: {{ hainan }}},
{name: ‘江西‘,value: {{ jiangxi }}},
{name: ‘湖北‘,value: {{ hubei }}},
{name: ‘山西‘,value: {{ shanxi2 }}},
{name: ‘辽宁‘,value: {{ liaoning }}},
{name: ‘台湾‘,value: {{ taiwan }}},
{name: ‘黑龙江‘,value: {{ heilongjiang }}},
{name: ‘贵州‘,value: {{ guizhou }}},
{name: ‘甘肃‘,value: {{ gansu }}},
{name: ‘青海‘,value: {{ qinghai }}},
{name: ‘新疆‘,value: {{ xinjiang }}},
{name: ‘西藏‘,value: {{ xizang }}},
{name: ‘吉林‘,value: {{ jiling }}},
{name: ‘宁夏‘,value: {{ ningxia }}},
{name: ‘内蒙古‘,value: {{ neimenggu }}},
]
}
]
};
myChart.setOption(option);
</script>
</body>
</html>{% load staticfiles %}
<!DOCTYPE html>
<head>
<meta charset="utf-8">
<title>动态数据展示</title>
</head>
<body>
<!-- 为ECharts准备一个具备大小（宽高）的Dom -->
<div id="main" style="height:400px"></div>
<!-- ECharts单文件引入 -->
<script src="http://echarts.baidu.com/build/dist/echarts.js"></script>
<script type="text/javascript">
// 路径配置
require.config({
paths: {
echarts: ‘http://echarts.baidu.com/build/dist‘
}
});
// 使用
require(
[
‘echarts‘,
‘echarts/chart/bar‘ // 使用柱状图就加载bar模块，按需加载
],
function (ec) {
// 基于准备好的dom，初始化echarts图表
var myChart = ec.init(document.getElementById(‘main‘));
var option = {
tooltip: {
show: true
},
legend: {
color:‘#0000FF‘,
data:[‘模特年龄‘]
},
xAxis : [
{
type : ‘category‘,
data : {{ category }}
}
],
yAxis : [
{
type : ‘value‘
}
],
series : [
{
"name":"模特年龄",
"type":"bar",
"data":{{ agedata }}
}
]
};
// 为echarts对象加载数据
myChart.setOption(option);
}
);
</script>
</body>网站首页：
提交的信息会写入数据库中：
模特年龄正态分布情况：
首先对信息进行分词处理，然后排序，选取出现频率最高的前100个词。
这个花了我很多时间，要解决echarts地图只精确到省或者直辖市，而我爬取到的数据可能是具体的某一个地方市名，针对这个问题：我首先找了一下各省下面的市都有哪些，sql语句使用正则匹配想要获取的信息。我创建了个字典存放省名和下属的市名。另外创建个字典存放省名和匹配到的人数。
简单小结：这里面涉及到的知识点还挺多的：
爬虫：我使用的requests和beautiful这俩库。
数据库：使用的是mysql，涉及到数据库编码，sql查询，模糊匹配，python对数据库的操作，中文显示乱码的问题。
词云：jieba进行分词，pytagcloud用来生成词云。
django：views、templates、static 、url，因为我用的MySQLdb，所以没有使用django自身的ORM(models)，这样我觉得更灵活。
前端展示：bootstrap（主要用来做网站的布局）和echarts（进行图表展示和数据分析用）。
本文出自 “付炜超” 博客，请务必保留此出处http://9399369.blog.51cto.com/9389369/1953469
以上是关于python实现数据爬取-清洗-持久化存储-数据平台可视化的主要内容，如果未能解决你的问题，请参考以下文章