之前有个需求就是获取豆瓣电影上正在热映和即将热映的电影信息,开始求希望于豆瓣电影的api,发现豆瓣电影的这两个接口的权限是需要商业合作的,最后索性自己爬下来!
爬的是豆瓣电影的ID,通过这个ID可以通过豆瓣电影的开放API获取对应ID电影的详细信息,豆瓣总算没有把事情做绝了!
需要用的python模块有BeautifulSoup,请自行下载之!
#coding:utf-8
import urllib2from BeautifulSoup
import BeautifulStoneSoup
import cookielibHOST_URL = '
class DoubanMovies:
def __init__(self):
self.url = ''
def openUrl(self):
cj = cookielib.CookieJar()
openUrl = urllib2.urlopen(self.url)
cjHander = urllib2.HTTPCookieProcessor(cj)
opener = urllib2.build_opener(cjHander)
urllib2.install_opener(opener)
return openUrl.readlines()
#tag=p是正在热映的影片id
#tag=h3是即将上映影片的id
def getMovieId(self,tag):
movieStr = ''
movieId =[]
for html in self.openUrl():
movieStr += str(html).strip()
soup = BeautifulStoneSoup(movieStr.strip(''))
for con in soup.findAll(tag):
res = BeautifulStoneSoup(str(con))
movieId.append(str(res.a["href"]).split("/")[-2])
return movieId
#正在热映影片ID
def nowPlaying(self):
movie_id = []
for i in range(1,3,1):
url = HOST_URL + '/movie/recent/now?page=' + str(i)+'&session=833b8d4c'
self.url = url
for id in self.getMovieId('p'):
movie_id.append(id)
return movie_id
#即将上映影片ID
def soonPlaying(self):
url = r'http://movie.douban.com/later/shanghai/'
self.url = url
self.openUrl()
return self.getMovieId('h3')
#http://api.douban.com/v2/movie/subject/movieId(豆瓣接口)
if __name__ == "__main__":
print DoubanMovies().nowPlaying()