文章目录
⭐前言
大家好，我是yma16，本文分享关于python自动化获取个人博客质量分并可视化。
该系列文章：
python爬虫_基本数据类型
python爬虫_函数的使用
python爬虫_requests的使用
⭐selenium
python使用selenium调用WebDriver自动控制浏览器动作
💖 获取所有的文章url
思路分解
- 获取article标签
- 拿到a标签的属性链接
- 拿到a标签内容的标题
html的元素分析
注意：需要完全滚动到底部加载所有的文章
代码块：
from selenium import webdriver
import time,re,json
dir_path='C:\\Users\MY\PycharmProjects\Spider_python\study2021\day07\dirver\msedgedriver.exe'
driver=webdriver.Edge(executable_path=dir_path)
url='https://blog.csdn.net/qq_38870145?type=blog'
driver.get(url)
now_url=driver.current_url
#定义一个初始值
temp_height=0
time.sleep(3)
while True:
#循环将滚动条下拉
driver.execute_script("window.scrollBy(0,1000)")
#sleep一下让滚动条反应一下
time.sleep(5)
#获取当前滚动条距离顶部的距离
check_height = driver.execute_script("return document.documentElement.scrollTop || window.pageYOffset || document.body.scrollTop;")
#如果两者相等说明到底了
if check_height==temp_height:
break
temp_height=check_height
jsonData={
'articleInfo':[
# {src,title,name,aId}
]
}
def next_list():
article=driver.find_elements_by_xpath('//article[@class="blog-list-box"]')
for item in article:
link=item.find_element_by_tag_name('a').get_attribute('href')
text=item.text
title=text.split('\n')[0]
print('link', link)
print('title',title)
compile1 = re.compile(r'https://(.*?).blog.csdn.net/article/details/(.*?)$', re.S) # 匹配 name和用户id
result = re.findall(compile1, link)
print('result',result)
uid=''
aid=''
for uid, aid in result:
uid=uid
aid=aid
jsonData['articleInfo'].append({
'title':title,
'src':link,
'article':aid,
'username':uid
})
next_list()
driver.close()
with open("./articleContent.json", 'w') as write_f:
write_f.write(json.dumps(jsonData, indent=4, ensure_ascii=False))
写入json成功！
💖 根据url查询分数
思路分解：
- 自动填充url
- 获取分数
- 记录分数
注意：获取分数显示的渲染需要延迟一段时间
单个url读取代码块：
from selenium import webdriver
import time,re,json
dir_path='C:\\Users\MY\PycharmProjects\Spider_python\study2021\day07\dirver\msedgedriver.exe'
driver=webdriver.Edge(executable_path=dir_path)
url='https://www.csdn.net/qc'
driver.get(url)
now_url=driver.current_url
def autoWriteUrl(url):
driver.find_element_by_xpath('//input[@type="text" and @popperclass="csdn-input-autocomplete"]') \
.send_keys(url) # 输入内容
searchBtn()
getGrade()
def searchBtn():
driver.find_element_by_xpath('//div[@class="trends-input-box-btn"]') \
.click() # 点击
def getGrade():
time.sleep(2)
grade=driver.find_element_by_xpath('//p[@class="img"]')
gradeNum=grade.text
des=driver.find_element_by_xpath('//p[@class="desc text"]')
desContent=des.text
print(gradeNum)
print(desContent)
time.sleep(1)
autoWriteUrl('https://yma16.blog.csdn.net/article/details/131407234')
运行结果：
批量读取：
from selenium import webdriver
import time,json
dir_path='C:\\Users\MY\PycharmProjects\Spider_python\study2021\day07\dirver\msedgedriver.exe'
driver=webdriver.Edge(executable_path=dir_path)
url='https://www.csdn.net/qc'
driver.get(url)
now_url=driver.current_url
def autoWriteUrl(url):
print(url)
driver.find_element_by_xpath('//input[@type="text" and @popperclass="csdn-input-autocomplete"]') \
.send_keys(url) # 输入内容
searchBtn()
return getGrade()
def searchBtn():
driver.find_element_by_xpath('//div[@class="trends-input-box-btn"]') \
.click() # 点击
def getGrade():
time.sleep(1)
grade=driver.find_element_by_xpath('//p[@class="img"]')
gradeNum=grade.text
des=driver.find_element_by_xpath('//p[@class="desc text"]')
desContent=des.text
print(gradeNum)
print(desContent)
return [gradeNum,desContent]
# autoWriteUrl('https://yma16.blog.csdn.net/article/details/131407234')
# 质量分数据
gradeJsonData={}
def mapJson(jsonVal):
for key in jsonVal.keys():
gradeJsonData[key]=[]
for childItem in jsonVal[key]:
print(childItem)
grade = 0
des = ''
temp={}
for childItemKey in childItem:
temp[childItemKey]=childItem[childItemKey]
if(childItemKey=='src'):
grade=autoWriteUrl(childItem[childItemKey])[0]
des=autoWriteUrl(childItem[childItemKey])[1]
temp['grade']=grade
temp['des']=des
gradeJsonData[key].append(temp)
if __name__=='__main__':
with open('articleContent.json', 'r') as f:
jsonData = json.load(f)
mapJson(jsonData)
with open("./articleGrade.json", 'w', encoding='utf-8') as write_f:
write_f.write(json.dumps(gradeJsonData, indent=4, ensure_ascii=False))
driver.close()
运行结果如下：
💖 inscode结合echarts展示
echarts读取json显示柱状图
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<title>echarts 滚动事件</title>
<!-- vue2 生产环境版本，优化了尺寸和速度 -->
<script src="https://cdn.jsdelivr.net/npm/vue@2"></script>
<script src="./echarts.js"></script>
<script type="text/javascript" src="./csdnGrade.js"></script>
</head>
<style>
#app {
position: absolute;
height: 100vh;
width: 100vw;
}
</style>
<body>
<div id="app">
<div>
csdn 质量分柱状图
<div id="first" style="width: 900px;height:1200px;"></div>
</div>
</div>
<script type="text/javascript">
csdnJson.articleInfo.sort((a,b)=> parseInt(a.grade)-parseInt(b.grade))
const instanceVue = {
el: '#app',
name: 'ecahrts',
data() {
return {
firstChart: null,
secondChart: null,
thirdChart: null,
maxNum: 1000,
};
},
mounted() {
this.initFirstData()
},
methods: {
initFirstData() {
// 基于准备好的dom，初始化echarts实例
var myChart = echarts.init(document.getElementById('first'));
// 指定图表的配置项和数据
let base = +new Date(1968, 9, 3);
let oneDay = 24 * 3600 * 500;
let date = [];
let data = [Math.random() * 300];
for (let i = 1; i < this.maxNum; i++) {
var now = new Date((base += oneDay));
date.push([now.getFullYear(), now.getMonth() + 1, now.getDate()].join('/'));
data.push(Math.round((Math.random() - 0.5) * 20 + data[i - 1]));
}
const option = {
tooltip: {
trigger: 'axis',
axisPointer: {
type: 'shadow'
}
},
legend: {},
xAxis: {
type: 'category',
data: csdnJson.articleInfo.map(item => item.username)
},
yAxis: {
type: 'value'
},
series: [
{
data: csdnJson.articleInfo.map(item => item.grade),
type: 'bar',
showBackground: true,
backgroundStyle: {
color: 'rgba(180, 180, 180, 0.2)'
}
}
]
};
// 使用刚指定的配置项和数据显示图表。
myChart.setOption(option);
// 监听
this.firstChart = myChart;
},
}
}
// 实例化
new Vue(instanceVue);
</script>
</body>
</html>
运行结果：
inscode:
结束
本文分享python的自动化获取质量分到此结束！
