Python抓取电影天堂电影信息的代码

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>(.*&#63;)</font></h1></div>', 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'<div class="co_content8">(.*&#63;)</tbody>',conent , re.S)


 pattern = re.compile('<ul>(.*&#63;)<tr>', 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('<br /><br />(.*&#63;)<br /><br />@@##@@ 0):
  movieInfo = movieInfo[0]+''

  # 删除<br />标签
  movieInfo = movieInfo.replace("<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('@@##@@', 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('<td style="WORD-WRAP: break-word" bgcolor="#fdfddf"><a href="(.*&#63;)">.*&#63;</a></td>', 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("------------------------------------------------\n\n\n")