大数据项目实践 数据采集清洗存储——b站编程课程采集与分析_大数据数据清洗界面(1)

img
img

网上学习资料一大堆,但如果学到的知识不成体系,遇到问题时只是浅尝辄止,不再深入研究,那么很难做到真正的技术提升。

需要这份系统化资料的朋友,可以戳这里获取

一个人可以走的很快,但一群人才能走的更远!不论你是正从事IT行业的老鸟或是对IT行业感兴趣的新人,都欢迎加入我们的的圈子(技术交流、学习资源、职场吐槽、大厂内推、面试辅导),让我们一起学习成长!

                    if link not in unique_links:
                        if self.state:
                            self.signal.emit(VideoID, VideoName, VideoAuther, Category, VideoView, Comment, Duration)
                            self.data += 1
                            time.sleep(0.1)
                        unique_links.add(link)
                        break
        self.page_number += 1
        self.o_number += 24

def Stop(self):
    self.state = 0

**在这个代码中,爬虫代码不断爬取数据,通过 self.signal.emit(VideoID, VideoName, VideoAuther, Category, VideoView, Comment, Duration) 这行代码将数据传递到界面上。**



#### 7、通过UI界面实时显示数据


**到最为关键的一步了,我们需要对设计好的UI界面进行初始化,并利用爬取好传递过来的数据来生成可视化图表,并实现实时自动刷新图表以及手动刷新图表。**


**还是和DataThread派生类一样,我们可以创建一个自己的窗口类MyWindow,继承于我们通过QtDesigner设计好的界面生成的类Ui\_MainWindow,同时还要继承于PyQt5中的QMainWindow类。**



class MyWindow(Ui_MainWindow,QMainWindow):
signal = pyqtSignal(str, str, str, str, int, int, str)
def init(self):
QMainWindow.init(self)
self.setupUi(self)
self.Operate()
self.dt = {‘C语言’: 0, ‘C++’: 0, ‘Python’: 0, ‘PHP’: 0, ‘算法’: 0, ‘Java’: 0, ‘go语言’: 0, ‘Mysql’: 0, ‘C#’: 0, ‘Scratch’: 0, ‘web’: 0, ‘计算机’: 0}
self.showflag = 0

# 初始化并指明各个函数
def Operate(self):
    self.InitTable()
    self.ConnectDB()
    self.CreateThread()
    

# 初始化各个图表
def InitTable(self):
# 设置列个数
    self.tableWidget_show_all_datas.setColumnCount(7)
    # 标题
    self.tableWidget_show_all_datas.setHorizontalHeaderLabels(
        ['视频ID号', '视频名称', '视频作者', '相关分类', '视频观看量', '评论数', '视频时长'])
    # 设置整行选中模式
    self.tableWidget_show_all_datas.setSelectionBehavior(True)
    # 设置列宽度
    self.tableWidget_show_all_datas.setColumnWidth(0, 147)
    self.tableWidget_show_all_datas.setColumnWidth(1, 630)
    self.tableWidget_show_all_datas.setColumnWidth(2, 247)
    self.tableWidget_show_all_datas.setColumnWidth(3, 147)
    self.tableWidget_show_all_datas.setColumnWidth(4, 120)
    self.tableWidget_show_all_datas.setColumnWidth(5, 120)
    self.tableWidget_show_all_datas.setColumnWidth(6, 147)
    # 最后一列自动填充剩余宽度
    # self.tableWidget_show_all_datas.horizontalHeader().setStretchLastSection(True)
    # 设置标题带排序
    self.tableWidget_show_all_datas.setSortingEnabled(True)
    # 隐藏默认行号
    self.tableWidget_show_all_datas.verticalHeader().setHidden(True)

def ConnectDB(self):
    self.con = GetConn()
    self.cur = self.con.cursor()
    sql = "delete from videos"
    try:
        self.cur.execute(sql)
        self.con.commit()
        print('清空数据成功')
    except Exception as e:
        print('清空数据失败', e)


def ShowSelWindow(self):
    selindex = self.tabWidget.currentIndex()
    self.tabWidget.setCurrentIndex(selindex)

# 创建多线程
def CreateThread(self):
    self.datathread = DataThread()
    self.datathread.data = 1
    self.datathread.signal.connect(self.DoWork)
    self.signal.connect(self.datathread.Stop)

# 启动多线程
def StartThread(self):  # 启动多线程
    text = self.pButton_data_collection.text()
    if text == '开始采集':
        self.pButton_data_collection.setText('停止采集')
        self.datathread.state = 1
        self.datathread.start()
    else:
        self.pButton_data_collection.setText('开始采集')
        self.datathread.Stop()

def DoWork(self, VideoID, VideoName, VideoAuther, Category, VideoView, Comment, Duration):
    pass

**我的MyWindow类大体架构就是这样,在这个类中,最最关键的成员函数是DoWork函数。第5步多线程中通过爬虫代码爬取的每一条数据都会依次传递到DoWork函数中。多线程在进行中状态下会不断调用DoWork函数,当多线程停止后才停止对DoWork函数的调用。**



#### 8、效果展示


**b站编程课程爬虫多线程客户端示例展示视频**







#### 9.完整代码


**bilibili\_UI.py**



-- coding: utf-8 --

Form implementation generated from reading ui file ‘bilibili_UI.ui’

Created by: PyQt5 UI code generator 5.15.9

WARNING: Any manual changes made to this file will be lost when pyuic5 is

run again. Do not edit this file unless you know what you are doing.

from PyQt5 import QtCore, QtGui, QtWidgets

class Ui_MainWindow(object):
def setupUi(self, MainWindow):
MainWindow.setObjectName(“MainWindow”)
MainWindow.resize(1450, 853)
self.centralwidget = QtWidgets.QWidget(MainWindow)
self.centralwidget.setObjectName(“centralwidget”)
self.layoutWidget = QtWidgets.QWidget(self.centralwidget)
self.layoutWidget.setGeometry(QtCore.QRect(0, 0, 1451, 29))
self.layoutWidget.setObjectName(“layoutWidget”)
self.horizontalLayout = QtWidgets.QHBoxLayout(self.layoutWidget)
self.horizontalLayout.setContentsMargins(0, 0, 0, 0)
self.horizontalLayout.setObjectName(“horizontalLayout”)
spacerItem = QtWidgets.QSpacerItem(40, 20, QtWidgets.QSizePolicy.Expanding, QtWidgets.QSizePolicy.Minimum)
self.horizontalLayout.addItem(spacerItem)
self.label = QtWidgets.QLabel(self.layoutWidget)
font = QtGui.QFont()
font.setFamily(“华文楷体”)
font.setPointSize(15)
font.setBold(True)
font.setWeight(75)
self.label.setFont(font)
self.label.setObjectName(“label”)
self.horizontalLayout.addWidget(self.label)
spacerItem1 = QtWidgets.QSpacerItem(40, 20, QtWidgets.QSizePolicy.Expanding, QtWidgets.QSizePolicy.Minimum)
self.horizontalLayout.addItem(spacerItem1)
self.tabWidget = QtWidgets.QTabWidget(self.centralwidget)
self.tabWidget.setGeometry(QtCore.QRect(0, 30, 1451, 791))
font = QtGui.QFont()
font.setBold(True)
font.setWeight(75)
self.tabWidget.setFont(font)
self.tabWidget.setObjectName(“tabWidget”)
self.tab = QtWidgets.QWidget()
self.tab.setObjectName(“tab”)
self.pButton_data_collection = QtWidgets.QPushButton(self.tab)
self.pButton_data_collection.setGeometry(QtCore.QRect(0, 10, 121, 41))
font = QtGui.QFont()
font.setFamily(“华文仿宋”)
font.setPointSize(9)
font.setBold(True)
font.setItalic(False)
font.setUnderline(False)
font.setWeight(75)
font.setStrikeOut(False)
font.setKerning(False)
self.pButton_data_collection.setFont(font)
self.pButton_data_collection.setObjectName(“pButton_data_collection”)
self.tableWidget_show_all_datas = QtWidgets.QTableWidget(self.tab)
self.tableWidget_show_all_datas.setGeometry(QtCore.QRect(0, 50, 1451, 331))
self.tableWidget_show_all_datas.setObjectName(“tableWidget_show_all_datas”)
self.tableWidget_show_all_datas.setColumnCount(0)
self.tableWidget_show_all_datas.setRowCount(0)
self.Label_current_collection_data = QtWidgets.QLabel(self.tab)
self.Label_current_collection_data.setGeometry(QtCore.QRect(0, 380, 1441, 31))
self.Label_current_collection_data.setText(“”)
self.Label_current_collection_data.setObjectName(“Label_current_collection_data”)
self.WebEngineView_show_data_pie = QtWebEngineWidgets.QWebEngineView(self.tab)
self.WebEngineView_show_data_pie.setGeometry(QtCore.QRect(0, 420, 811, 351))
self.WebEngineView_show_data_pie.setStyleSheet(“border: 1px solid black;”)
self.WebEngineView_show_data_pie.setObjectName(“WebEngineView_show_data_pie”)
self.label_pie = QtWidgets.QLabel(self.tab)
self.label_pie.setGeometry(QtCore.QRect(820, 420, 621, 341))
font = QtGui.QFont()
font.setFamily(“华文仿宋”)
font.setPointSize(17)
font.setBold(True)
font.setWeight(75)
self.label_pie.setFont(font)
self.label_pie.setText(“”)
self.label_pie.setObjectName(“label_pie”)
self.tabWidget.addTab(self.tab, “”)
self.tab_2 = QtWidgets.QWidget()
self.tab_2.setObjectName(“tab_2”)
self.WebEngineView_show_vv_Bar = QtWebEngineWidgets.QWebEngineView(self.tab_2)
self.WebEngineView_show_vv_Bar.setGeometry(QtCore.QRect(0, 50, 701, 361))
self.WebEngineView_show_vv_Bar.setStyleSheet(“border: 1px solid black;”)
self.WebEngineView_show_vv_Bar.setObjectName(“WebEngineView_show_vv_Bar”)
self.WebEngineView_show_cm_Bar = QtWebEngineWidgets.QWebEngineView(self.tab_2)
self.WebEngineView_show_cm_Bar.setGeometry(QtCore.QRect(0, 410, 701, 341))
self.WebEngineView_show_cm_Bar.setStyleSheet(“border: 1px solid black;”)
self.WebEngineView_show_cm_Bar.setObjectName(“WebEngineView_show_cm_Bar”)
self.pButton_show_four_picture = QtWidgets.QPushButton(self.tab_2)
self.pButton_show_four_picture.setGeometry(QtCore.QRect(10, 0, 121, 41))
self.pButton_show_four_picture.setObjectName(“pButton_show_four_picture”)
self.WebEngineView_show_ca_Tunnel = QtWebEngineWidgets.QWebEngineView(self.tab_2)
self.WebEngineView_show_ca_Tunnel.setGeometry(QtCore.QRect(700, 50, 751, 361))
self.WebEngineView_show_ca_Tunnel.setStyleSheet(“border: 1px solid black;”)
self.WebEngineView_show_ca_Tunnel.setObjectName(“WebEngineView_show_ca_Tunnel”)
self.WebEngineView_show_ca_Cloud = QtWebEngineWidgets.QWebEngineView(self.tab_2)
self.WebEngineView_show_ca_Cloud.setGeometry(QtCore.QRect(700, 410, 751, 341))
self.WebEngineView_show_ca_Cloud.setStyleSheet(“border: 1px solid black;”)
self.WebEngineView_show_ca_Cloud.setObjectName(“WebEngineView_show_ca_Cloud”)
self.tabWidget.addTab(self.tab_2, “”)
self.tab_3 = QtWidgets.QWidget()
self.tab_3.setObjectName(“tab_3”)
self.tabWidget1 = QtWidgets.QTabWidget(self.tab_3)
self.tabWidget1.setGeometry(QtCore.QRect(0, 0, 1441, 761))
font = QtGui.QFont()
font.setBold(True)
font.setWeight(75)
self.tabWidget1.setFont(font)
self.tabWidget1.setObjectName(“tabWidget1”)
self.tab_4 = QtWidgets.QWidget()
self.tab_4.setObjectName(“tab_4”)
self.WebEngineView_show_vv_Bar2 = QtWebEngineWidgets.QWebEngineView(self.tab_4)
self.WebEngineView_show_vv_Bar2.setGeometry(QtCore.QRect(0, 60, 921, 661))
self.WebEngineView_show_vv_Bar2.setStyleSheet(“border: 1px solid black;”)
self.WebEngineView_show_vv_Bar2.setObjectName(“WebEngineView_show_vv_Bar2”)
self.pButton_show1 = QtWidgets.QPushButton(self.tab_4)
self.pButton_show1.setGeometry(QtCore.QRect(20, 10, 111, 41))
self.pButton_show1.setObjectName(“pButton_show1”)
self.label_vv = QtWidgets.QLabel(self.tab_4)
self.label_vv.setGeometry(QtCore.QRect(920, 60, 511, 661))
font = QtGui.QFont()
font.setFamily(“华文仿宋”)
font.setPointSize(15)
font.setBold(True)
font.setWeight(75)
self.label_vv.setFont(font)
self.label_vv.setText(“”)
self.label_vv.setObjectName(“label_vv”)
self.tabWidget1.addTab(self.tab_4, “”)
self.tab_5 = QtWidgets.QWidget()
self.tab_5.setObjectName(“tab_5”)
self.pButton_show2 = QtWidgets.QPushButton(self.tab_5)
self.pButton_show2.setGeometry(QtCore.QRect(30, 10, 111, 41))
self.pButton_show2.setObjectName(“pButton_show2”)
self.WebEngineView_show_cm_Bar2 = QtWebEngineWidgets.QWebEngineView(self.tab_5)
self.WebEngineView_show_cm_Bar2.setGeometry(QtCore.QRect(0, 60, 981, 661))
self.WebEngineView_show_cm_Bar2.setStyleSheet(“border: 1px solid black;”)
self.WebEngineView_show_cm_Bar2.setObjectName(“WebEngineView_show_cm_Bar2”)
self.label_cm = QtWidgets.QLabel(self.tab_5)
self.label_cm.setGeometry(QtCore.QRect(990, 60, 441, 661))
font = QtGui.QFont()
font.setFamily(“华文仿宋”)
font.setPointSize(15)
font.setBold(True)
font.setWeight(75)
self.label_cm.setFont(font)
self.label_cm.setText(“”)
self.label_cm.setObjectName(“label_cm”)
self.tabWidget1.addTab(self.tab_5, “”)
self.tab_6 = QtWidgets.QWidget()
self.tab_6.setObjectName(“tab_6”)
self.pButton_show3 = QtWidgets.QPushButton(self.tab_6)
self.pButton_show3.setGeometry(QtCore.QRect(20, 10, 111, 41))
self.pButton_show3.setObjectName(“pButton_show3”)
self.WebEngineView_show_ca_Tunnel2 = QtWebEngineWidgets.QWebEngineView(self.tab_6)
self.WebEngineView_show_ca_Tunnel2.setGeometry(QtCore.QRect(0, 60, 961, 341))
self.WebEngineView_show_ca_Tunnel2.setStyleSheet(“border: 1px solid black;”)
self.WebEngineView_show_ca_Tunnel2.setObjectName(“WebEngineView_show_ca_Tunnel2”)
self.WebEngineView_show_ca_Cloud2 = QtWebEngineWidgets.QWebEngineView(self.tab_6)
self.WebEngineView_show_ca_Cloud2.setGeometry(QtCore.QRect(0, 400, 961, 321))
self.WebEngineView_show_ca_Cloud2.setStyleSheet(“border: 1px solid black;”)
self.WebEngineView_show_ca_Cloud2.setObjectName(“WebEngineView_show_ca_Cloud2”)
self.label_ca = QtWidgets.QLabel(self.tab_6)
self.label_ca.setGeometry(QtCore.QRect(970, 60, 451, 661))
font = QtGui.QFont()
font.setFamily(“华文仿宋”)
font.setPointSize(15)
font.setBold(True)
font.setWeight(75)
self.label_ca.setFont(font)
self.label_ca.setText(“”)
self.label_ca.setObjectName(“label_ca”)
self.tabWidget1.addTab(self.tab_6, “”)
self.tabWidget.addTab(self.tab_3, “”)
MainWindow.setCentralWidget(self.centralwidget)
self.menubar = QtWidgets.QMenuBar(MainWindow)
self.menubar.setGeometry(QtCore.QRect(0, 0, 1450, 26))
self.menubar.setObjectName(“menubar”)
MainWindow.setMenuBar(self.menubar)
self.statusbar = QtWidgets.QStatusBar(MainWindow)
self.statusbar.setObjectName(“statusbar”)
MainWindow.setStatusBar(self.statusbar)

    self.retranslateUi(MainWindow)
    self.tabWidget.setCurrentIndex(2)
    self.tabWidget1.setCurrentIndex(2)
    QtCore.QMetaObject.connectSlotsByName(MainWindow)

def retranslateUi(self, MainWindow):
    _translate = QtCore.QCoreApplication.translate
    MainWindow.setWindowTitle(_translate("MainWindow", "MainWindow"))
    self.label.setText(_translate("MainWindow", "B站编程课程采集与分析"))
    self.pButton_data_collection.setText(_translate("MainWindow", "开始采集"))
    self.tabWidget.setTabText(self.tabWidget.indexOf(self.tab), _translate("MainWindow", "采集课程数据"))
    self.pButton_show_four_picture.setText(_translate("MainWindow", "数据可视化"))
    self.tabWidget.setTabText(self.tabWidget.indexOf(self.tab_2), _translate("MainWindow", "数据可视化"))
    self.pButton_show1.setText(_translate("MainWindow", "显示分析"))
    self.tabWidget1.setTabText(self.tabWidget1.indexOf(self.tab_4), _translate("MainWindow", "分析点1"))
    self.pButton_show2.setText(_translate("MainWindow", "显示分析"))
    self.tabWidget1.setTabText(self.tabWidget1.indexOf(self.tab_5), _translate("MainWindow", "分析点2"))
    self.pButton_show3.setText(_translate("MainWindow", "显示分析"))
    self.tabWidget1.setTabText(self.tabWidget1.indexOf(self.tab_6), _translate("MainWindow", "分析点3"))
    self.tabWidget.setTabText(self.tabWidget.indexOf(self.tab_3), _translate("MainWindow", "数据分析"))

from PyQt5 import QtWebEngineWidgets



**main.py**



import sys
from PyQt5.QtWidgets import *
from Function import *

if name == ‘main’:
app = QApplication([])
mywin = MyWindow()
mywin.show()
sys.exit(app.exec_())



**DB.py**



import pymysql

def GetConn():
try:
conn = pymysql.connect(host=‘localhost’,user=‘root’,password=‘123456’,database=‘bilibili’)
except Exception as e:
print(“连接失败!\n”,e)
print()
else:
print(“连接成功!\n”)
return conn

def CloseConn(cur,conn):
try:
if cur:
cur.close()
if conn:
conn.close()
except Exception as e:
print(“操作异常!!!\n”)



**Function.py**



from PyQt5.QtWidgets import *
from PyQt5.QtCore import *
from PyQt5.QtGui import *
from PyQt5.QtWebEngineWidgets import *
import datetime
import time
from bilibili_UI import *
from DB import *
import pymysql
import requests
from lxml import etree
from pyecharts import options as opts
from pyecharts.charts import Funnel
from pyecharts.render import make_snapshot
from pyecharts.globals import ThemeType
from pyecharts import options as opts
from pyecharts.charts import Pie
from pyecharts.charts import Bar
from pyecharts.charts import WordCloud

class DataThread(QThread):
signal = pyqtSignal(str, str, str, str, int, int, str)
def init(self):
QThread.init(self)
self.state = 1
self.page_number = 1
self.o_number = 0
self.key = []
self.value = []
def run(self):
# while(self.state):
# 爬虫准备工作
base_url = ‘https://search.bilibili.com/all?vt=77434542&keyword=%E7%BC%96%E7%A8%8B%E8%AF%BE%E7%A8%8B&from_source=webtop_search&spm_id_from=333.1007&search_source=5’
params = {}

    headers = {
        "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36 Edg/120.0.0.0"
    }
        # page_number = 1
        # o_number = 0
    unique_links = set()
    video_data_by_keyword = ['C语言', 'C++', 'Python', 'PHP', '算法', 'Java', 'go语言','Mysql','C#','Scratch','web','计算机']
    while self.page_number <= 34:
        params['page'] = str(self.page_number)
        params['o'] = str(self.o_number)
        response = requests.get(base_url, params=params, headers=headers)
        html = response.text
        html = response.content.decode('utf-8')
        parse = etree.HTMLParser(encoding='utf-8')
        contentPath = []
        contentname = []
        contentauthor = []
        contentVV = []
        contentCM = []
        contentDR = []
        doc = etree.HTML(html)
        doc.xpath('//div[@class="bili-video-card__info--right"]//a/@href')
        contentPath = doc.xpath('//div[@class="bili-video-card__info--right"]/a/@href')
        contentname = doc.xpath('//div[@class="bili-video-card__info--right"]//h3[@class="bili-video-card__info--tit"]/@title')
        contentauthor = doc.xpath('//div[@class="bili-video-card__info--right"]//span[@class="bili-video-card__info--author"]/text()')
        contentVV = doc.xpath('//div[@class="bili-video-card__stats--left"]/span[@class="bili-video-card__stats--item"][1]/span/text()')
        contentCM = doc.xpath('//div[@class="bili-video-card__stats--left"]/span[@class="bili-video-card__stats--item"][2]/span/text()')
        contentDR = doc.xpath('//div[@class="bili-video-card__stats"]/span[@class="bili-video-card__stats__duration"]/text()')
        # print(contentVV)
        # print(contentCM)
        for link, name,auther,vv,cm,dr in zip(contentPath,contentname,contentauthor,contentVV,contentCM,contentDR):
            category_found = False
            VideoID = str(self.data)
            VideoName = name
            VideoAuther = auther
            if vv[-1] == '万':
                num = float(vv[0:-1])
                num *= 10000
                VideoView = int(num)
            else:
                VideoView = int(vv)
            if cm[-1] == '万':
                num = float(cm[0:-1])
                num *= 10000
                Comment = int(num)
            else:
                Comment = int(cm)
            Duration = dr
            Category = None
            for keyword in video_data_by_keyword:
                lower_keyword = keyword.lower()  # 将关键词转换为小写
                if lower_keyword in name.lower():
                    Category = keyword
                    if link not in unique_links:
                        if self.state:
                            self.signal.emit(VideoID, VideoName, VideoAuther, Category, VideoView, Comment, Duration)
                            self.data += 1
                            time.sleep(0.1)
                        unique_links.add(link)
                        break

            # for keyword in video_data_by_keyword:
            #     if keyword.lower() in name.lower():
            #         Category = keyword
            #         if self.state:
            #             self.signal.emit(VideoID, VideoName, VideoAuther, Category, VideoView, Comment, Duration)
            #             self.data += 1
            #             time.sleep(0.2)
            #         break
        self.page_number += 1
        self.o_number += 24

def Stop(self):
    self.state = 0

class MyWindow(Ui_MainWindow,QMainWindow):
signal = pyqtSignal(str, str, str, str, int, int, str)
def init(self):
QMainWindow.init(self)
self.setupUi(self)
self.Operate()
self.dt = {‘C语言’: 0, ‘C++’: 0, ‘Python’: 0, ‘PHP’: 0, ‘算法’: 0, ‘Java’: 0, ‘go语言’: 0, ‘Mysql’: 0, ‘C#’: 0, ‘Scratch’: 0, ‘web’: 0, ‘计算机’: 0}
self.showflag = 0

# 初始化并指明各个函数
def Operate(self):
    self.tabWidget.currentChanged.connect(self.ShowSelWindow)
    self.tabWidget.setCurrentIndex(0)
    self.tabWidget1.currentChanged.connect(self.ShowSelWindow)
    self.tabWidget1.setCurrentIndex(0)
    self.InitTable()
    self.ConnectDB()
    self.CreateThread()
    self.pButton_data_collection.clicked.connect(self.StartThread)
    self.pButton_show_four_picture.clicked.connect(self.show_four_htmls)
    self.pButton_show1.clicked.connect(self.show1)
    self.pButton_show2.clicked.connect(self.show2)
    self.pButton_show3.clicked.connect(self.show3)

# 初始化各个图表
def InitTable(self):
# 设置列个数
    self.tableWidget_show_all_datas.setColumnCount(7)
    # 标题
    self.tableWidget_show_all_datas.setHorizontalHeaderLabels(
        ['视频ID号', '视频名称', '视频作者', '相关分类', '视频观看量', '评论数', '视频时长'])
    # 设置整行选中模式
    self.tableWidget_show_all_datas.setSelectionBehavior(True)
    # 设置列宽度
    self.tableWidget_show_all_datas.setColumnWidth(0, 147)
    self.tableWidget_show_all_datas.setColumnWidth(1, 630)
    self.tableWidget_show_all_datas.setColumnWidth(2, 247)
    self.tableWidget_show_all_datas.setColumnWidth(3, 147)
    self.tableWidget_show_all_datas.setColumnWidth(4, 120)
    self.tableWidget_show_all_datas.setColumnWidth(5, 120)
    self.tableWidget_show_all_datas.setColumnWidth(6, 147)
    # 最后一列自动填充剩余宽度
    # self.tableWidget_show_all_datas.horizontalHeader().setStretchLastSection(True)
    # 设置标题带排序
    self.tableWidget_show_all_datas.setSortingEnabled(True)
    # 隐藏默认行号
    self.tableWidget_show_all_datas.verticalHeader().setHidden(True)

def ConnectDB(self):
    self.con = GetConn()
    self.cur = self.con.cursor()
    sql = "delete from videos"
    try:
        self.cur.execute(sql)
        self.con.commit()
        print('清空数据成功')
    except Exception as e:
        print('清空数据失败', e)


def ShowSelWindow(self):
    selindex = self.tabWidget.currentIndex()
    self.tabWidget.setCurrentIndex(selindex)

# 创建多线程
def CreateThread(self):
    self.datathread = DataThread()
    self.datathread.data = 1
    self.datathread.signal.connect(self.DoWork)
    self.signal.connect(self.datathread.Stop)

# 启动多线程
def StartThread(self):  # 启动多线程
    text = self.pButton_data_collection.text()
    if text == '开始采集':
        self.pButton_data_collection.setText('停止采集')
        self.datathread.state = 1
        self.datathread.start()
    else:
        self.pButton_data_collection.setText('开始采集')
        self.datathread.Stop()


def DoWork(self, VideoID, VideoName, VideoAuther, Category, VideoView, Comment, Duration):
    self.curind = self.datathread.data
    self.tableWidget_show_all_datas.insertRow(0)
    lst = [VideoID, VideoName, VideoAuther, Category, VideoView, Comment, Duration]
    if self.cur:
        sql = "insert into videos values ('{}','{}','{}','{}','{}','{}','{}')".format(VideoID, VideoName, VideoAuther, Category, VideoView, Comment, Duration)
        try:
            self.cur.execute(sql)
            self.con.commit()
        except Exception as e:
            print("插入失败!", e)

    for i in range(7):
        self.tableWidget_show_all_datas.setItem(0, i, QTableWidgetItem(str(lst[i])))
        self.tableWidget_show_all_datas.item(0, i).setTextAlignment(QtCore.Qt.AlignCenter | QtCore.Qt.AlignVCenter)

    self.dt[Category] = self.dt.get(Category, 0) + 1
    self.dt = dict(sorted(self.dt.items(), key=lambda x: x[0]))
    self.all_datas = list(self.dt.items())

    if self.showflag == 0:
        self.DrawPie()
        self.showflag = 1
    else:
        self.DrawFunnel()
        self.Draw_vv_Bar()
        self.Draw_cm_Bar()
        self.Draw_ca_Cloud()
        datas = list(self.dt.values())
        self.datathread.key = self.dt.keys()
        self.datathread.value = self.dt.values()
        js = "setValue({})".format(datas)
        self.WebEngineView_show_data_pie.page().runJavaScript(js)
        self.Label_current_collection_data.setText(
            '已采集:' + str(self.curind - 1) + '条    C#: ' + str(datas[0]) + '  C++: ' + str(
                datas[1]) + '  C语言: ' + str(datas[2])
            + '  Java: ' + str(datas[3]) + '  Mysql: ' + str(datas[4]) + '  PHP: ' + str(
                datas[5]) + '  Python: ' + str(datas[6])
            + '  Scratch: ' + str(datas[7]) + '  go语言: ' + str(datas[8])
            + '  web: ' + str(datas[9]) + '  算法: ' + str(datas[10]) + '  计算机: ' + str(datas[11])
        )
        self.label_pie.setText(self.get_fl_answer())



def DrawFunnel(self):
    data = []
    for key,value in zip(self.datathread.key,self.datathread.value):
        data.append((key,value))
    # print(data)
    sort_data = sorted(data,key=lambda x:x[1],reverse=True)
    # print(sort_data)
    funnel = Funnel(init_opts=opts.InitOpts(theme=ThemeType.VINTAGE))
    funnel.add("",sort_data,
               gap=0.9,
               label_opts=opts.LabelOpts(formatter="{b} : {d}"),
               )
    funnel.set_global_opts(
        title_opts=opts.TitleOpts(title="各编程课程分类统计漏斗图",pos_left="center"),
        legend_opts=opts.LegendOpts(pos_left='70%',pos_bottom='40%'),
    )
    funnel.render('各编程课程分类统计漏斗图.html')

def Draw_vv_Bar(self):
    self.cur = self.con.cursor()
    sql_query = "SELECT Category, VideoView FROM videos ORDER BY VideoView DESC LIMIT 20"
    self.cur.execute(sql_query)
    result = self.cur.fetchall()
    # 提取结果中的数据
    video_category = [row[0] for row in result]
    vv_values = [row[1] for row in result]
    # 使用 Pyecharts 生成横向柱状图
    bar = (
        Bar()
        .add_xaxis(video_category)
        .add_yaxis("Views", vv_values)
        .set_global_opts(
            title_opts=opts.TitleOpts(title="播放量最高的前20条视频的类型"),
            xaxis_opts=opts.AxisOpts(
                axislabel_opts=opts.LabelOpts(
                    rotate=-45,
                    font_size=11,
                    interval=0,
                )
            ),
        )
    )
    bar.render("videoview.html")

def Draw_cm_Bar(self):
    self.cur = self.con.cursor()
    sql_query1 = "SELECT Category, Comment FROM videos ORDER BY Comment DESC LIMIT 20"
    self.cur.execute(sql_query1)
    result = self.cur.fetchall()
    # 提取结果中的数据
    video_category = [row[0] for row in result]
    vv_comment = [row[1] for row in result]
    # 使用 Pyecharts 生成横向柱状图
    bar = (
        Bar()
        .add_xaxis(video_category)  # 将视频名称作为 x 轴数据
        .add_yaxis("Comments", vv_comment)  # 将视频数据作为 y 轴数据
        .reversal_axis()  # 将 x 轴和 y 轴交换
        .set_global_opts(
            title_opts=opts.TitleOpts(title="评论量最高的前20条视频"),
            xaxis_opts=opts.AxisOpts(
                axislabel_opts=opts.LabelOpts(
                    font_size=11,  # 调整字体大小
                    interval=0,  # 设置标签显示的间隔
                )
            ),
        )
    )
    bar.render("comment.html")

def Draw_ca_Cloud(self):
    data = []
    for key, value in zip(self.datathread.key, self.datathread.value):
        data.append((key, value))
    # print(data)
    sort_data = sorted(data, key=lambda x: x[1], reverse=True)
    print(sort_data)
    cloud = WordCloud(init_opts=opts.InitOpts(theme=ThemeType.VINTAGE))
    cloud.add('',data,shape='circle')
    cloud.set_global_opts(
        title_opts=opts.TitleOpts(title="课程分类云图",pos_left="37%",pos_top="3%")
    )
    cloud.render("课程分类云图.html")



def show_ca_Funnel(self):
    with open('各编程课程分类统计漏斗图.html', 'r') as file:
        html_content = file.read()
    self.WebEngineView_show_ca_Tunnel.setHtml(html_content)

def show_vv_Bar(self):
    with open('videoview.html', 'r') as file:
        html_content = file.read()
    self.WebEngineView_show_vv_Bar.setHtml(html_content)

def show_cm_Bar(self):
    with open('comment.html', 'r') as file:
        html_content = file.read()
    self.WebEngineView_show_cm_Bar.setHtml(html_content)

def show_ca_Cloud(self):
    with open('课程分类云图.html', 'r') as file:
        html_content = file.read()
    self.WebEngineView_show_ca_Cloud.setHtml(html_content)

def show_four_htmls(self):
    self.show_ca_Funnel()
    self.show_vv_Bar()
    self.show_cm_Bar()
    self.show_ca_Cloud()

def show1(self):
    with open('videoview.html', 'r') as file:
        html_content = file.read()
    self.WebEngineView_show_vv_Bar2.setHtml(html_content)
    self.label_vv.setText(self.get_vv_answer())

def show2(self):
    with open('comment.html', 'r') as file:
        html_content = file.read()
    self.WebEngineView_show_cm_Bar2.setHtml(html_content)
    self.label_cm.setText(self.get_cm_answer())

def show3(self):
    with open('各编程课程分类统计漏斗图.html', 'r') as file:
        html_content1 = file.read()
    with open('课程分类云图.html', 'r') as file:
        html_content2 = file.read()
    self.WebEngineView_show_ca_Tunnel2.setHtml(html_content1)
    self.WebEngineView_show_ca_Cloud2.setHtml(html_content2)
    self.label_ca.setText(self.get_fl_answer())


def get_fl_answer(self):
    data = []
    for key, value in zip(self.datathread.key, self.datathread.value):
        data.append((key, value))
    sort_data = sorted(data, key=lambda x: x[1])
    # print(sort_data)
    str = '从统计的结果来看,\n学习'+sort_data[0][0]+'、'+sort_data[1][0]+'、'+sort_data[2][0]+'的人相对较少,\n该些语言相对冷门\n'+'学习'+sort_data[-1][0]+'、'+sort_data[-2][0]+'、'+sort_data[-3][0]+'的人相对\n较多,\n该些语言相对热门\n'
    return str
    # self.label_pie.setText('从统计的结果来看,学习'+sort_data[0][0]+'的人最少,该语言相对冷门\n'+'学习'+sort_data[-1][0]+'的人最多,该语言相对热门\n')

def get_vv_answer(self):
    data = []
    for key, value in zip(self.datathread.key, self.datathread.value):
        data.append((key, value))
    sort_data = sorted(data, key=lambda x: x[1])
    # print(sort_data)
    str = 'B站编程社区对'+sort_data[0][0]+'、'+sort_data[1][0]+'、'+sort_data[2][0]+'等内容表\n现出浓厚的兴趣,而每个主题的播放量和视\n频数量提供了关于观众偏好和学习方向的\n有益见解。'
    # print(str)
    return str

def get_cm_answer(self):
    data = []
    for key, value in zip(self.datathread.key, self.datathread.value):
        data.append((key, value))
    sort_data = sorted(data, key=lambda x: x[1])
    # print(sort_data)
    str = sort_data[-1][0]+'是B站上最受欢迎的编程主题,\n其次是'+sort_data[-2][0]+'和'+sort_data[-3][0]+'科学基础知识。\n这些数据反映了不同编程主题在B站\n观众中的受欢迎程度和市场需求。\n高评论量表明了这些主题\n在编程学习社区中的重要性和吸引力。'
    # print(str)
    return str

def DrawPie(self):
    self.creat_echarts_byhtml(self.WebEngineView_show_data_pie, 'pie', self.all_datas)


def creat_echarts_byhtml(self, curwidget, drawtype, all_datas):
    # print(all_datas)
    the_html_content = '''
       <!DOCTYPE html>
       <html >
       <head>
           <meta charset="utf-8">
       </head>
       <body style="width:800px; height:300px;margin:auto;top:30px">
       <div id="container" style="width:800px; height:300px;margin:auto;top:30px"></div>
       <script type="text/javascript" src="https://cdn.jsdelivr.net/npm/echarts@5/dist/echarts.min.js"></script>
       <script type="text/javascript"> 

img
img

网上学习资料一大堆,但如果学到的知识不成体系,遇到问题时只是浅尝辄止,不再深入研究,那么很难做到真正的技术提升。

需要这份系统化资料的朋友,可以戳这里获取

一个人可以走的很快,但一群人才能走的更远!不论你是正从事IT行业的老鸟或是对IT行业感兴趣的新人,都欢迎加入我们的的圈子(技术交流、学习资源、职场吐槽、大厂内推、面试辅导),让我们一起学习成长!

print(all_datas)

    the_html_content = '''
       <!DOCTYPE html>
       <html >
       <head>
           <meta charset="utf-8">
       </head>
       <body style="width:800px; height:300px;margin:auto;top:30px">
       <div id="container" style="width:800px; height:300px;margin:auto;top:30px"></div>
       <script type="text/javascript" src="https://cdn.jsdelivr.net/npm/echarts@5/dist/echarts.min.js"></script>
       <script type="text/javascript"> 

[外链图片转存中…(img-ReB7zfRj-1715781943553)]
[外链图片转存中…(img-n4wzwBOt-1715781943554)]

网上学习资料一大堆,但如果学到的知识不成体系,遇到问题时只是浅尝辄止,不再深入研究,那么很难做到真正的技术提升。

需要这份系统化资料的朋友,可以戳这里获取

一个人可以走的很快,但一群人才能走的更远!不论你是正从事IT行业的老鸟或是对IT行业感兴趣的新人,都欢迎加入我们的的圈子(技术交流、学习资源、职场吐槽、大厂内推、面试辅导),让我们一起学习成长!

  • 7
    点赞
  • 13
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值