Python抓取电影天堂电影信息的代码

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 ('
.*?>
'+
 '/Uploads/(.*?) ',re.S)
 items = re.findall(pattern,conent) 
 
 str = ''.join(items)
 pattern = re.compile ('/Uploads/(.*?).*?/Uploads/(.*?)',re.S)
 news = re.findall(pattern, str)

 for j in news:
 
 	movieUrls.append('http://www.dytt8.net'+j[0])

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'
/Uploads/(.*?)
', conent, re.S)
 if (len(movieName) > 0):
 movieName = movieName[0] + ""
 # 截取名称
 movieName = movieName[movieName.find("《") + 3:movieName.find("》")]
 else:
 movieName = ""

 print("电影名称: " + movieName.strip())

 movieContent = re.findall(r'/Uploads/(.*?)',conent , re.S)


 pattern = re.compile('/Uploads/(.*?)', re.S)
 movieDate = re.findall(pattern,movieContent[0])

 if (len(movieDate) > 0):
 movieDate = movieDate[0].strip() + ''
 else:
 movieDate = ""

 print("电影发布时间: " + movieDate[-10:])

 pattern = re.compile('
/Uploads/(.*?)
 0):
 movieInfo = movieInfo[0]+''

 # 删除
标签
 movieInfo = movieInfo.replace("
","")

 # 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('', re.S)	
 movieImg = re.findall(pattern,movieContent[0])

 if (len(movieImg) > 0):
 movieImg = movieImg[0]
 else:
 movieImg = ""
 
 print("电影海报: " + movieImg)

 pattern = re.compile('.*?', re.S)
 movieDownUrl = re.findall(pattern,movieContent[0])

 if (len(movieDownUrl) > 0):
 movieDownUrl = movieDownUrl[0]
 else:
 movieDownUrl = ""

 print("电影下载地址：" + movieDownUrl + "")

 print("------------------------------------------------


")

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")