复制代码 代码如下:
import re,sys
import urllib
from bs4 import BeautifulSoup
global r_url
def hq_url():
so_url = "http://movie.douban.com/subject_search?search_text="
data = urllib.urlopen(so_url+gjz).read()
r = re.findall(r'<a class="nbg" href=(.?) onclick',data)
r_url = re.sub('"','',r[0])
ymdata = urllib.urlopen(r_url).read()
soup = BeautifulSoup(ymdata)
wz = soup('span',{'property':'v:summary'})
title = re.findall(r'name="title" value="(.?)"',ymdata)
zy = re.findall(r'name="desc" value="(.?)"',ymdata)
imdb = re.findall(r': <a href="(.?)" target=',ymdata)
shijian = re.findall(r'<span property="v:runtime" content="109">(.*?)</span>',ymdata)
print u"IMDB电影网链接"
print imdb
print u"豆瓣电影链接"
print r_url
print '*'*70
print title[0]
print zy[0]
print "电影简介"
print ''70
print wz
if name=='main':
gjz=raw_input("请输入电影名: ").strip()
hq_url()
Copyright© 2013-2020
All Rights Reserved 京ICP备2023019179号-8