爬取猫眼电影

from itertools import chain
from urllib import request
from urllib.request import urlopen

def getPageHtml(url):
    #获取网页对应的源码
    user_agent = "Mozilla/5.0 (X11; Linux x86_64; rv:45.0) Gecko/20100101 Firefox/45.0"
    req = request.Request(url, headers={'User-Agent': user_agent})
    obj = urlopen(req)
    return obj.read()

def getfilename(text):
    #获取电影名称
    '''<p class="name"><a href="/films/1297" title="肖申克的救赎" data-act="boarditem-click" data-val="{movieId:1297}">肖申克的救赎</a></p>'''
    paattern = r'<p class="name"><.*?>(.*?)</a></p>'
    return re.findall(paattern,text)

def getfiletime(text):
    # 获取上映时间
    '''<p class="releasetime">上映时间：1994-10-14(美国)</p>'''
    pattern = r'<p class="releasetime">(.*?)</p>'
    return re.findall(pattern,text)

def getstar(text):
    #获取主演
    '''<p class="star">
                主演：宋在浩,李顺才,尹秀晶
        </p>
        <p class="releasetime">上映时间：1994-10-14(美国)</p>    </div>'''
    pattern = r'<p class="star">(.*?)</p>'
    s = re.findall(pattern,text)
    starname = []
    for i in s:
        starname.append(i.strip(' '))
    return starname

def get_imgurl(text):
    #获取图片的url
    '''<img data-src="http://p0.meituan.net/movie/[email protected]_220h_1e_1c" alt="辩护人" class="board-img" />'''
    pattern = r'<img data-src="(http://.*?)" .*? class="board-img" />'
    return re.findall(pattern,text)



def main():
    #建立四个列表把爬取的信息按类存放
    filename = []
    filetime = []
    filestar = []
    fileurl = []
    #爬取10页信息，并存入对应的列表中
    for i in range(10):
        url = 'http://maoyan.com/board/4?offset=%d0' %i
        text = getPageHtml(url).decode('utf-8').replace("\n", "")
        filestar.append(getstar(text))
        filename.append(getfilename(text))
        filetime.append(getfiletime(text))
        fileurl.append(get_imgurl(text))
        # http://maoyan.com/board/4?offset=20
    # print(filestar)
    # print(filename)
    # print(filetime)
    #把所有的电影名，主演，时间，图片网址一一对应
    for name,star,time,url in zip(filename,filestar,filetime,fileurl):
        for name1,star1,time1,url1 in zip(name,star,time,url):
            print(name1,star1,time1,url1)
    urlli = [j for i in fileurl for j in i]  #将所有页的图片保存到一个列表中
    # 将图片保存到指定的文件夹中
    for i,v in enumerate(urlli):
        with open("img1/img%d.jpg" %(i+1),'wb') as f:
            content = getPageHtml(v)
            f.write(content)

main()

图片：