python实战爬取豆瓣电影信息

源代码：

import urllib.request
from  bs4 import BeautifulSoup
import re


def main():
    baseurl = "http://movie.douban.com/top250?start="
    datalist = getData(baseurl)
    savepath = ""
    saveData(savepath)

findLink = re.compile(r'<a href="(.*?)">') #创建正则表达式规则找到影片详情的链接

findImgSrc = re.compile(r'<img.*src="(.*?)"',re.S) #re.S让换行符包含在字符中，获取影片图片

findTitle = re.compile(r'<span class="title">(.*)</span>') #影片名

findRating = re.compile(r'<span class="rating_num" property="v:average">(.*)</span>')#评分

findJudge = re.compile(r'<span>(\d*)人评价</span>') #评价人数

findInq = re.compile(r'<span class="inq">(.*)</span>')#找到概况

findBd = re.compile(r'<p class="">(.*?)</p>',re.S)

#爬取网页
def getData(baseurl):
    datalist = []
    for i in range(0,1):
        url = baseurl + str(i*25) #获取多个不同页面
        html = askURL(url)  #保存获取的网页源码
        #逐一解析
        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,class加下划线来表示它的属性值
            #print(item)
            #找到影片详情的链接
            data = [] #保存一部电影的信息
            item = str(item) #转为字符串用来查找
            link = re.findall(findLink,item)[0] #用re库用正则表达式查找指定的字符串
            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)
            if len(title)==2:
                ctitle = title[0]
                data.append(ctitle)
                otitle = title[1].replace("/","")#将外国名的/去掉
                data.append(otitle)
            else:
                data.append(title[0])
                data.append(' ') #外国名字留空
            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("。","")
            else:
                inq = " "
            data.append(inq)
            bd = re.findall(findBd,item)[0]
            bd = re.sub('<br(\s+)?>(\s)?'," ",bd) #去掉<br/>
            bd.replace('/',"")
            data.append(bd.strip())  #去掉前后空格

            datalist.append(data)
            #print(html)
    for i in datalist:
         print(i)
    return datalist

#得到指定一个URL的网页内容
def askURL(url):
    head ={"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.92 Safari/537.36"} #用户代理表示告诉服务器，我们是什么类型的机器，伪装用
    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(savepath):
    print("save……")

if __name__ == "__main__":
    main()

执行截图：