python实现的爬取电影下载链接功能示例-创新互联

本文实例讲述了python实现的爬取电影下载链接功能。分享给大家供大家参考，具体如下：

#!/usr/bin/python
#coding=UTF-8
import sys
import urllib2
import os
import chardet
from bs4 import BeautifulSoup
reload(sys)
sys.setdefaultencoding("utf-8")
#从电影html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
#从电影html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('h2')
  title=title.string
  return title
#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 html
#从电影列表页，获取电影的url，拼接好，存到列表后返回
def 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',attrs={'class':'ulink'})
  host = "http://www.ygdy8.net"
  for a_url in a_urls:
    m_url=a_url.get('href')
    m_list.append(host+m_url)
  return m_list
#存入txt文件
def file_edit(wr_str):
  f1 = open(r'e:\down_load_url.txt','a')
  f1.write(wr_str)
  f1.close()
#传入电影url的列表集合，获取下载地址，并写入文件
def write_to_txt(a_urls):
  for a_url in a_urls:
    html=get_html(a_url)
    html=html.decode('GBK')
    write_title=get_movie_title(html)
    write_url=get_movie_download_url(html)
    file_edit(write_title+"\n")
    file_edit(write_url+"\n")
    file_edit("\n")
#传入页数，返回这几页的url列表
def get_pages_url(num):
  urls_list = []
  url="http://www.ygdy8.net/html/gndy/dyzz/list_23_"
  for n in range(1,num+1):
    new_url = url+str(n)+".html"
    urls_list.append(new_url)
  return urls_list
if __name__=='__main__':
  pages = 2 #打算爬取几页电影
  p_url = get_pages_url(pages)
  for i in p_url:
    write_to_txt(get_movie_list(i))#执行写入
  print "done"