def get_url(outer_order_id):
  refundId = get_refundId(outer_order_id)
  host_url = 'http://test.shequ.com/order/agreeRefund"htmlcode">

# -*- coding: utf-8 -*-
import urllib
from bs4 import BeautifulSoup
import re
#访问url，返回html页面
def get_html(url):
  req = urllib.request.Request(url)
  req.add_header('User-Agent','Mozilla/5.0')
  response = urllib.request.urlopen(url)
  html = response.read()
  return html
def get_movie_url(movie_name):#根据电影名称，生成搜索结果的URL
  host_url = 'http://s.dydytt.net/plus/search.php"http://www.ygdy8.com"
  for a_url in a_urls:
    m_url = a_url.get('href')
    m_url = str(m_url)
    if re.search(r'\d{8}',m_url) and (host not in 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此页面所有的的下载链接
def get_movie_download_url(html):
  soup = BeautifulSoup(html,'html.parser')
  fixed_html = soup.prettify()
  td = soup.find_all('td',attrs={'style':'WORD-WRAP: break-word'})
  down_urls = []
  for t in td:
    down_urls.append(t.a.get('href'))
  return down_urls
#传入电影列表，获取每个电影的下载地址
def get_movie(movie_list):
  movie_dict = {}
  for i in range(0,len(movie_list)):
    html = get_html(movie_list[i])
    html = html.decode('GBK','ignore') #忽略编码错误
    m_title = get_movie_title(html)
    if u'游戏' not in m_title: #过滤游戏
      if u'动画' not in m_title: #过滤动画片
        m_url_list = get_movie_download_url(html)
        for m_url in m_url_list:
          movie_dict[m_url] = m_title
  return movie_dict




用django展现在页面效果如下：

另一个网站的


# -*- coding: utf-8 -*-
from xpinyin import Pinyin
from bs4 import BeautifulSoup
from urllib import request,error
import time,re
import ssl
ssl._create_default_https_context = ssl._create_unverified_context #关闭https协议验证证书
def get_html(url): #访问url，返回html页面,如果url错误，则返回状态码,一般是404
  req = request.Request(url)
  req.add_header('User-Agent','Mozilla/5.0')
  try:
    response = request.urlopen(url)
    html = response.read()
    return html
  except error.HTTPError as e:
    return e.code
def get_m_html(movie_name):#根据电影名称，返回正确的电影html
  pin = Pinyin()
  pinyin_movie_name = pin.get_pinyin(movie_name,"")#不使用分隔符，默认是-
  movie_type = {
    "Sciencefiction":"科幻片",
    "Horror"    :"恐怖片",
    "Drama"     :"剧情片",
    "Action"    :"动作片",
    "Comedy"    :"喜剧片",
    "Love"     :"爱情片",
    "War"      :"战争片"
  }
  host = "https://www.kankanwu.com"
  for k,v in movie_type.items():
    movie_url = host + "/" + k + "/" + pinyin_movie_name + "/"
    html = get_html(movie_url)
    if isinstance(html,int):
      time.sleep(10)
    else:
      return html
def get_dload_url(html): #从电影html页面中获取下载地址
  movie_dict = {}
  soup = BeautifulSoup(html,'lxml')
  fixed_html = soup.prettify()
  a_urls = soup.find_all(href=re.compile("thunder"))#找到含有thunder链接的href
  for url in a_urls:
    m_title = url.get('title')
    m_url = url.get('href')
    movie_dict[m_title] = m_url
  return movie_dict




更多关于Python相关内容可查看本站专题：《Python Socket编程技巧总结》、《Python数据结构与算法教程》、《Python函数使用技巧总结》、《Python字符串操作技巧汇总》、《Python入门与进阶经典教程》及《Python文件与目录操作技巧汇总》
希望本文所述对大家Python程序设计有所帮助。