python实现简单爬虫和数据可视化-爬取豆瓣top250电影信息

此内容全程跟着成都工业大学的李巍老师爬虫入门视频敲的代码，如有侵权删
观看的视频链接如下：李巍老师爬虫入门视频

整个爬虫可分为三个部分：

1. 爬取网页-“https://movie.douban.com/top250?start=0”

2.解析数据，打开自己要爬取的网站，进入开发者工具

3. 保存自己想要的数据到excel

4.具体代码如下，当出现403时，可以换一个"User-Agent"

#coding = utf-8
#version:python 3.6.0
#Tools:Pycharm 2018.11.27
_date_ = '2021/8/28 21:59'
_author_ = '小强'

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  sqlite3 #进行sqllite数据库操作

def main():
    baseurl = "https://movie.douban.com/top250?start=0"
    # #1.爬取数据
    datalist = getData(baseurl)
    savepath = ".//豆瓣电影Top250.xls"
    # print(datalist)

    #3.保存数据
    saveData(datalist,savepath)

    # askURL("https://movie.douban.com/top250")
findlink = re.compile(r'<a href="(.*?)">')#创建正则表达式对象，表示规则
#影片图片
findImgSrc = re.compile(r'<img.*src="(.*?)"',re.S) #re.S让换行符包含在字符中
#影片片名
findTitle = re.compile(r'span class="title">(.*?)</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)
findRating = re.compile(r'<span class="rating_num" property="v:average">.*</span>')

#爬取网页
def getData(baseurl):
    datalist = []
    for i in range(0,10):
        url = baseurl + str(i*25)
        html = askURL(url)

    #2.解析数据

        soup = BeautifulSoup(html,'html.parser')
        for item in soup.find_all('div',class_="item"):
            # print(item) #测试：
            data=[]
            item = str(item)

            link = re.findall(findlink,item)[0]
            data.append(link)
            imgSrc = re.findall(findImgSrc,item)[0]
            data.append(imgSrc)
            titles = re.findall(findTitle,item)  #片名可能只有一个中文名，没有外文名
            if(len(titles)==2):
                ctitle = titles[0]
                data.append(ctitle)
                otitle = titles[1].replace("/","")  #去掉无关的符号
                data.append(otitle)
            else:
                data.append(titles[0])
                data.append(' ')  #国外名字留空

            rating = re.findall(findRating,item)[0]#添加评分
            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("。","") #去掉句号
                data.append(inq)
            else:
                data.append(" ")   #留空

            bd = re.findall(findBd,item)[0]
            bd = re.sub('<br(/s+)?/>(/s+)?'," ",bd)  #去掉<br/>
            bd = re.sub('/'," ",bd)
            data.append(bd.strip())  #去掉前后的空格

            datalist.append(data)

    print(datalist)
    return datalist




#得到指定一个URL的网页内容
def askURL(url):
    head = {
        "User-Agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.153 Safari/537.36"
           # "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:30.0) Gecko/20100101 Firefox/30.0",
           # "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.75.14 (KHTML, like Gecko) Version/7.0.3 Safari/537.75.14",
           # "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; Win64; x64; Trident/6.0)",
           # 'Mozilla/5.0 (Windows; U; Windows NT 5.1; it; rv:1.8.1.11) Gecko/20071127 Firefox/2.0.0.11',
           # 'Opera/9.25 (Windows NT 5.1; U; en)',
           # 'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)',
           # 'Mozilla/5.0 (compatible; Konqueror/3.5; Linux) KHTML/3.5.5 (like Gecko) (Kubuntu)',
           # 'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8.0.12) Gecko/20070731 Ubuntu/dapper-security Firefox/1.5.0.12',
           # 'Lynx/2.8.5rel.1 libwww-FM/2.14 SSL-MM/1.4.1 GNUTLS/1.2.9',
           # "Mozilla/5.0 (X11; Linux i686) AppleWebKit/535.7 (KHTML, like Gecko) Ubuntu/11.04 Chromium/16.0.912.77 Chrome/16.0.912.77 Safari/535.7",
           # "Mozilla/5.0 (X11; Ubuntu; Linux i686; rv:10.0) Gecko/20100101 Firefox/10.0 "
           # "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36"
    }
    #用户代理，表示告诉豆瓣服务器，我们是什么类型的机器，浏览器（本质上是告诉浏览器，我们可以接收什么水平的文件）
    #当出现403时，可以换一个"User-Agent"
    request = urllib.request.Request(url, headers=head)
    html = ""
    try:
        response = urllib.request.urlopen(request)
        html = response.read().decode("utf-8")
        print(html)
    except urllib.error.URLError as e:
        if hasattr(e,"code"):
            print(e.code)
        if hasattr(e,"reason"):
            print(e.reason)

    return html




#保存数据
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)
        data = datalist[i]
        for j in range(0,8):
            sheet.write(i+1,j,data[j])

    book.save(savepath)


if __name__ == "__main__":
    main()

5.得到的结果如下

6…爬虫有风险，用时需谨慎，之后发现自己再进去豆瓣top250出现异常，要我登录才可以访问,不过问题不大，之后自己也会注意这方面