根据电影名称，获取下载链接

做个笔记

# -*- coding: utf-8 -*-import urllibimport sysimport urllib2from bs4 import BeautifulSoupimport rereload(sys)sys.setdefaultencoding("utf-8")#访问url，返回html页面def get_html(url):    req=urllib2.Request(url)    req.add_header('User-Agent','Mozilla/5.0')    response=urllib2.urlopen(url)    html=response.read()    return htmldef get_movie_url(movie_name):#根据名称，返回下载地址    host_url = 'http://s.dydytt.net/plus/search.php?kwtype=0&keyword='    movie_sign = urllib.quote(movie_name.decode('utf-8').encode('gbk'))    movie_url = host_url+movie_sign    search_result = get_movie_list(movie_url)    return movie_url#从搜索结果页面，获取电影的urldef get_movie_list(url):    m_list = []    html = get_html(url)    soup = BeautifulSoup(html,'html.parser')    fixed_html=soup.prettify()    a_urls = soup.find_all('a')    host = "http://www.ygdy8.com"    for a_url in a_urls:        m_url = a_url.get('href')        if re.search(r'\d{8}',m_url):            m_list.append(host+m_url)    return m_list#从电影详情页面中获取电影标题def get_movie_title(html):    soup=BeautifulSoup(html,'html.parser')    fixed_html=soup.prettify()    title=soup.find('h1')    title=title.string    return title#从电影详情页面中获取视频下载地址def get_movie_download_url(html):    soup=BeautifulSoup(html,'html.parser')    fixed_html=soup.prettify()    td=soup.find('td',attrs={'style':'WORD-WRAP: break-word'})    url_a=td.find('a')    url_a=url_a.string    return url_a#传入电影列表，获取每个电影的下载地址def get_movie(movie_list):    for i in range(0,len(movie_list)):    #for url in movie_list:        html = get_html(movie_list[i])        html = html.decode('GBK')        m_title = get_movie_title(html)        m_url = get_movie_download_url(html)        print i+1,"--",m_title        print m_url        print "--"*50if __name__ == "__main__":    movie_name = '悟空传'#搜索电影的名称    movie_list = get_movie_list(get_movie_url(movie_name))    get_movie(movie_list)