import urllib2
import os
import re
import string


# 电影URL集合
movieUrls = []


# 获取电影列表
def queryMovieList():

 url = 'http://www.dytt8.net/html/gndy/dyzz/index.html' 
 conent = urllib2.urlopen(url)
 conent = conent.read()
 conent = conent.decode('gb2312','ignore').encode('utf-8','ignore') 
 pattern = re.compile ('<div class="title_all"><h1><font color=#008800>.*"25" align="center" bgcolor="#F4FAE2"> ',re.S)
 items = re.findall(pattern,conent) 
 
 str = ''.join(items)
 pattern = re.compile ('<a href="(.*" class="ulink">(.*"htmlcode">

def queryMovieInfo(movieUrls):

 for index, item in enumerate(movieUrls):

 print('电影URL: ' + item)

 conent = urllib2.urlopen(item)
 conent = conent.read()
 conent = conent.decode('gb2312','ignore').encode('utf-8','ignore') 


 movieName = re.findall(r'<div class="title_all"><h1><font color=#07519a>(.*""
  # 截取名称
  movieName = movieName[movieName.find("《") + 3:movieName.find("》")]
 else:
  movieName = ""

 print("电影名称: " + movieName.strip())

 movieContent = re.findall(r'<div class="co_content8">(.*""

 print("电影发布时间: " + movieDate[-10:])

 pattern = re.compile('<br /><br />(.*"<br />","")

  # 根据 ◎ 符号拆分

  movieInfo = movieInfo.split('◎')

 else:
  movieInfo = ""

 print("电影基础信息: ")

 for item in movieInfo:
  print(item)


 # 电影海报
 pattern = re.compile('<img.*"(.*".*""
 
 print("电影海报: " + movieImg)

 pattern = re.compile('<td style="WORD-WRAP: break-word" bgcolor="#fdfddf"><a href="(.*">.*""

 print("电影下载地址：" + movieDownUrl + "")

 print("------------------------------------------------\n\n\n")


执行抓取


if __name__=='__main__':

  print("开始抓取电影数据");
 
  queryMovieList()
  print(len(movieUrls))

  queryMovieInfo(movieUrls)
  print("结束抓取电影数据")


总结
学好正则表达式很重要,很重要,很重要!!!! Python的语法好有感觉, 对比Java …