Python自动化（二）使用Beautifu Soup爬取电影下载链接

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/gavinsun/article/details/77968973

#coding:utf-8
from bs4 import BeautifulSoup
import requests
import codecs
host = "http://www.poxiao.com"
url = "http://www.poxiao.com/mtype5.html"
html_doc = requests.get(url).content.decode("GBK")
with codecs.open("poxiao.html","w",encoding="GBK") as f:
    f.write(html_doc)
poxiao = BeautifulSoup(html_doc,"lxml")
div_content = poxiao.find(name="div",attrs={"class":"content"})
movies = div_content.find_all("h3")
for movie in movies:
    print movie.text
    movie_url = host+movie.a.get("href")
    movie_content = requests.get(movie_url).content
    movie_soup = BeautifulSoup(movie_content,"lxml")
    try:
        thunder_link = movie_soup.find("input",attrs={"name":"checkbox2"})
        print thunder_link.get("value")
    except:
        print "获取链接失败"