from bs4 import BeautifulSoup           # 网页解析
import re               # 正则表达式，进行文字匹配
import urllib.request,urllib.error      # 指定URL，获取网页数据
import sqlite3          # 进行sqlite数据库操作

def main():baseurl = "https://movie.douban.com/top250?start="#1.爬取网页，用getDate()函数datalist = getDate(baseurl)#2.逐一解析数据（可与1同步进行）#3.保存数据，用saveData2DB()函数dbpath = "movie.bd"             #数据库保存路径saveData2DB(datalist,dbpath)    #存储到database中的方法
if __name__ == "__main__":          #当程序执行时#调用函数main()print("爬取完毕！")

# 得到指定一个url网页内容
def askURL(url):head = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.135 Safari/537.36"}           # 模拟浏览器头部信息，向豆瓣服务器发送消息（发送请求时对浏览器做的伪装）# 用户代理：表示告诉豆瓣浏览器，我们是什么类型的机器，实质上是告诉浏览器，我们可以接收什么水平的文件内容requst = urllib.request.Request(url,headers=head)       # 用封装的信息访问html = ""try:response = urllib.request.urlopen(requst)html = response.read().decode("utf-8")except urllib.error.URLError as e:if hasattr(e,"code"):print(e.code)if hasattr(e,"reason"):print(e.reason)return html

# 爬取网页
def getDate(baseurl):datalist = []for i in range(0,10):           # 调用获取页面信息的函数10次，一页25条url = baseurl + str(i*25)html = askURL(url)          # 保存获取到的网页源码

# 影片详情链接的规则
findLink = re.compile(r'<a href="(.*?)">')         #创建正则表达式对象，表示规则（字符串的模式）
# 影片图片
findImgSrc = re.compile(r'<img.*src="(.*?)"',re.S)      #re.S表示忽略换行的情况，让换行符包含在字符中
# 影片的片名
findTitle = re.compile(r'<span class="title">(.*)</span>')
# 影片的评分
findRating = re.compile(r'<span class="rating_num" property="v:average">(.*)</span>')
# 找到评价人数
findJudge = re.compile(r'<span>(d*)人评价</span>')
# 找到概况
findInq = re.compile(r'<span class="inq">(.*)</span>')
# 找到影片的相关内容
findBd = re.compile(r'<p class="">(.*?)</p>',re.S)

# 爬取网页
def getDate(baseurl):datalist = []for i in range(0,10):           # 调用获取页面信息的函数10次，一页25条url = baseurl + str(i*25)html = askURL(url)          # 保存获取到的网页源码# 逐一进行解析soup = BeautifulSoup(html,"html.parser")for item in soup.find_all('div',class_="item"):     #查找符合要求的字符串，形成列表# print(item)   #测试查看电影item全部信息data = []           #保存一部电影的所有信息item = str(item)# 获取影片详情的链接link = re.findall(findLink,item)[0]     #re库用来通过正则表达式查找指定的字符串(0表示只要一个）data.append(link)                       #添加链接imgSrc = re.findall(findImgSrc,item)[0]data.append((imgSrc))                   #添加图片title = re.findall(findTitle,item)      #片名可能只有一个中文名，没有外文名if(len(title) == 2):ctitiles = title[0]                 #添加中文名data.append(ctitiles)otitles = title[1].replace("/","")      #去掉无关的符号    #添加外国名data.append(otitles)else:data.append(title[0])data.append(' ')                    #外国片留空rating = re.findall(findRating,item)[0]data.append(rating)                         #添加评分judgeNum = re.findall(findJudge,item)[0]data.append(judgeNum)                       #添加评价人数inq = re.findall(findInq,item)if len(inq) != 0:inq = inq[0].replace("。","")            #去掉句号data.append(inq)                        #添加概述else:data.append(" ")                        # 留空bd = re.findall(findBd,item)[0]bd = re.sub('<br(s+)?/>(s+)?'," ",str(bd))        #去掉<br/>bd = re.sub('/'," ",str(bd))                        #替换/data.append(bd.strip())                             #去掉前后的空格datalist.append(data)                   #把处理好的一部电影信息放入datalistreturn datalist

def init_db(dbpath):sql = '''create table movie250 (id integer primary key autoincrement,info_link text,pic_link text,cname varchar,ename varchar,score numeric,rated numeric,introduction text,info text)'''conn = sqlite3.connect(dbpath)cursor = conn.cursor()cursor.execute(sql)conn.commit()conn.close()

def saveData2DB(datalist,dbpath):#init_db(dbpath)conn = sqlite3.connect(dbpath)cur = conn.cursor()for data in datalist:for index in range(len(data)):if index == 4 or index == 5:continuedata[index] = '"'+data[index]+'"'sql = '''insert into movie250(info_link,pic_link,cname,ename,score,rated,introduction,info)values(%s)'''%",".join(data)print(sql)cur.execute(sql)conn.commit()cur.close()conn.close()

import jieba                                #分词
from matplotlib import pyplot as plt        #绘图，数据可视化
from wordcloud import WordCloud, STOPWORDS  # 词云
from PIL import Image                       #图片处理
import numpy as np                          #矩阵运算
import _sqlite3                             #数据库#准备词云所需的文字（词）
con = _sqlite3.connect("D:/dai ma/pycharm/douban_flask/movie.bd")
cur = con.cursor()
sql = 'select introduction from movie250'
data = cur.execute(sql)
text = ""
for item in data:text = text + item[0]
print(text)
cur.close()
con.close()#分词
cut = jieba.cut(text)
string = ' '.join(cut)
print(len(string))#绘图
img = Image.open(r'D:dai mapycharmdouban_flaskstaticassetsimgtree.jpg')       #打开遮罩图片
img_array = np.array(img)       #将图片转化为数组
#设置屏蔽词
exclude={'我们','你们','我','你','是','的','了','和','都',}
wc = WordCloud(background_color='white',mask=img_array,stopwords=exclude,font_path="Deng.ttf"        #字体在C盘windows下的fonts文件夹下——属性复制名字.ttf文件
)
wc.generate_from_text(string)#绘制图片
fig = plt.figure(1)
plt.imshow(wc)
plt.axis('off')     #是否显示坐标轴#plt.show()          #显示生成的词云图片#输出词云图片到文件
plt.savefig(r'D:dai mapycharmdouban_flaskstaticassetsimgwordclud.jpg',dpi=500)

from flask import Flask,render_template
import sqlite3app = Flask(__name__)@app.route('/')
def index():return render_template("index.html")@app.route('/index')
def home():return render_template("index.html")# return index()@app.route('/movie')
def movie():datalist = []con = sqlite3.connect("D:/dai ma/pycharm/douban_flask/movie.bd")cur = con.cursor()sql = "select * from movie250"data = cur.execute(sql)for item in data:datalist.append(item)cur.close()con.close()return render_template("movie.html",movies = datalist)@app.route('/score')
def score():score = []      #评分num = []        #计数con = sqlite3.connect("D:/dai ma/pycharm/douban_flask/movie.bd")cur = con.cursor()sql = "select score,count(score) from movie250 group by score"data = cur.execute(sql)for item in data:score.append(item[0])num.append(item[1])cur.close()con.close()return render_template("score.html",score = score,num = num)@app.route('/word')
def word():return render_template("word.html")@app.route('/team')
def team():return render_template("team.html")if __name__ == '__main__':app.run(debug=True)