python爬取百度电影榜单

# -*- codeing = utf-8 -*-
from bs4 import BeautifulSoup  # 网页解析，获取数据
import re  # 正则表达式，进行文字匹配`
import urllib.request, urllib.error  # 制定URL，获取网页数据
import xlwt  # 进行excel操作
import numpy as np
import matplotlib.pyplot as plt
import pymysql;
#import sqlite3  # 进行SQLite数据库操作




#
# host="47.108.13.197"
# user="root"
# password="@Qq12345678"
# port=3306
# db="python"
# charset="utf8"
# connect = pymysql.connect(host="47.108.13.197", user="root", password="@Qq12345678", port=3306, db="python", charset="utf8")
# cursor=connect.cursor()
#
# result=cursor.fetchone()

# cursor.close()
# connect.close()





findLink = re.compile(r'<a href="(.*?)">')  # 创建正则表达式对象，标售规则   影片详情链接的规则
findImgSrc = re.compile(r'<img.*src="(.*?)"', re.S)
findTitle = re.compile(r'<span class="title">(.*)</span>')
findRating = re.compile(r'<span class="rating_num" property="v:average">(.*)</span>')
findJudge = re.compile(r'<span>(\d*)人评价</span>')
findInq = re.compile(r'<span class="inq">(.*)</span>')
findBd = re.compile(r'<p class="">(.*?)</p>', re.S)
def main():
    baseurl = "https://movie.douban.com/top250?start="  #要爬取的网页链接
    # 1.爬取网页
    datalist = getData(baseurl)
    savepath = "豆瓣电影Top250.xls"    #当前目录新建XLS，存储进去]

    movname=[]
    pingjia=[]

    for i in range(250):

        movname.append(datalist[i][2])
        pingjia.append(datalist[i][5])
        # data.append([datalist[i][2],datalist[i][5]])
        # sql = "INSERT INTO move values(%s,%s)"
        # try:
        #     if cursor.execute(sql%str(datalist[i][2]),str(datalist[i][5])):
        #         connect.commit()
        #     print("********已入库**********")
        # except:
        #     print("#########入库失败#########")
        #     connect.rollback()
    print(datalist)
    # connect.close()
    saveData(datalist,savepath)
    matlab(movname,pingjia)
   



# 爬取网页
def getData(baseurl):
    datalist = []  #用来存储爬取的网页信息
    for i in range(0, 10):  # 调用获取页面信息的函数，10次
        url = baseurl + str(i * 25)
        html = askURL(url)  # 保存获取到的网页源码
        # 2.逐一解析数据
        soup = BeautifulSoup(html, "html.parser")
        for item in soup.find_all('div', class_="item"):  # 查找符合要求的字符串
            data = []  # 保存一部电影所有信息
            item = str(item)  #转换为字符串
            link = re.findall(findLink, item)[0]  # 通过正则表达式查找
            data.append(link)
            imgSrc = re.findall(findImgSrc, item)[0]
            data.append(imgSrc)
            titles = re.findall(findTitle, item)
            if (len(titles) == 2):
                ctitle = titles[0]
                data.append(ctitle)
                otitle = titles[1].replace("/", "")  #消除转义字符
                data.append(otitle)
            else:
                data.append(titles[0])
                data.append(' ')
            rating = re.findall(findRating, item)[0]
            data.append(rating)
            judgeNum = re.findall(findJudge, item)[0]
            data.append(judgeNum)
            inq = re.findall(findInq, item)
            if len(inq) != 0:
                inq = inq[0].replace("。", "") #将逗号替换成空格存储
                data.append(inq)
            else:
                data.append(" ")
            bd = re.findall(findBd, item)[0]  #查找
            bd = re.sub('<br(\s+)?/>(\s+)?', "", bd) #通过正则表达式查找
            bd = re.sub('/', "", bd)
            data.append(bd.strip())    #将所有信息都放入
            datalist.append(data)

    return datalist


# 得到指定一个URL的网页内容
def askURL(url):
    head = {  # 模拟浏览器头部信息，向豆瓣服务器发送消息
        "User-Agent": "Mozilla / 5.0(Windows NT 10.0; Win64; x64) AppleWebKit / 537.36(KHTML, like Gecko) Chrome / 80.0.3987.122  Safari / 537.36"

    }
    request = urllib.request.Request(url, headers=head)
    html = ""
    try:
        response = urllib.request.urlopen(request)
        html = response.read().decode("utf-8")
    except urllib.error.URLError as e:
        if hasattr(e, "code"):   #判断是否包含对应属性
            print(e.code)
        if hasattr(e, "reason"):
            print(e.reason)
    return html


# 保存数据到表格
def saveData(datalist,savepath):
    print("save.......")
    book = xlwt.Workbook(encoding="utf-8",style_compression=0) #创建workbook对象
    sheet = book.add_sheet('豆瓣电影Top250', cell_overwrite_ok=True) #创建工作表
    col = ("电影详情链接","图片链接","影片中文名","影片外国名","评分","评价数","概况","相关信息")
    for i in range(0,8):
        sheet.write(0,i,col[i])  #列名
    for i in range(0,250):
        # print("第%d条" %(i+1))       #输出语句，用来测试
        data = datalist[i]
        for j in range(0,8):
            sheet.write(i+1,j,data[j])  #数据
    book.save(savepath) #保存




def matlab(movname,pinglun): #视图
    cishu=0
    print(len(movname))



    for i in range(50):
        label_list = []
        cnt_list = []
        for j in range(5):
            if cishu<len(movname):
                label_list.append(movname[cishu])
                print(label_list)
                cnt_list.append(pinglun[cishu])
                print(cnt_list)
            # for i in range(10,250,10):
            cishu=cishu+1
            if j==4:
                plt.rcParams['font.sans-serif'] = ['Microsoft YaHei']
                plt.rcParams['axes.unicode_minus'] = False
                plt.bar(range(len(cnt_list)), cnt_list, label='TOP5', color='steelblue', alpha=1.0, width=0.8)
                plt.xticks(np.arange(len(label_list)), labels=label_list)
                plt.legend()
                plt.show()





if __name__ == "__main__":  # 当程序执行时
    # 调用函数
    main()
    #  matlab()
    # init_db("movietest.db")
    print("爬取完毕！")