跟我学Python，今天我们来爬取豆瓣的电影

#coding:utf-8
import urllib2
import re
root_url = "https://movie.douban.com/"
class Movie():
 def __init__(self): #初始化
 self.url_tmp=[]#未抓取
 self.urls=[] #已抓取
 #self.number=1000 #抓取的网页数
 def getpage(self,url):#获取网页原代码函数
 req=urllib2.Request(url)
 req.add_header("User-Agent","Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.110 Safari/537.36")
 # req.add_header("Host","erebor.douban.com")
 # req.add_header("Referer","https://movie.douban.com/")
 page=urllib2.urlopen(req).read()
 return page
 def getcontent(self,url):#获取电影信息
 page=self.getpage(url)
 name=re.findall(r'<h1>.*?<span property="v:itemreviewed">(.*?)</span>.*?<span class="year">(.*?)</span>.*?</h1>',page,re.S)#电影名称
 score=re.findall(r'<strong class="ll rating_num" property="v:average">(.*?)</strong>',page,re.S)#评分
 e = page.find('<div id="info">')
 page = page[e:-1]
 d = page.find('</div>')
 page = page[:d]
 reg= re.compile(r'<[^>]+>', re.S)
 content=reg.sub('',page).replace(' ', '').strip()
 print "电影名称："+name[0][0] + name[0][1]
 print "电影评分："+"".join(score)
 print content
 def url_add(self,page): #url获取
 reg=re.compile(r'https://movie.douban.com/subject/\d{8}/')
 urltmp=re.findall(reg,page)
 urltmps = list(set(urltmp))
 for tmp in urltmps:
 if (tmp not in self.urls) and (tmp not in self.url_tmp):#判断URL是否爬取
 self.url_tmp.append(tmp)
 # else:
 # print "%s页面已存在" %tmp
 def urls_add(self):#URL循环获取
 page=self.getpage(root_url)
 self.url_add(page)
 while len(self.url_tmp)!=0:
 url=self.url_tmp.pop()
 self.urls.append(url)
 if len(url)!=0:
 page=self.getpage(url)
 self.url_add(page)
 print url+" 正在爬取..."
 self.getcontent(url)
Movie().urls_add()