1. 程式人生 > 程式設計 >Python3.6實現根據電影名稱(支援電視劇名稱),獲取下載連結的方法

Python3.6實現根據電影名稱(支援電視劇名稱),獲取下載連結的方法

本文例項講述了Python3.6實現根據電影名稱(支援電視劇名稱),獲取下載連結的方法。分享給大家供大家參考,具體如下:

做個筆記
(python 3.6,django 2.0)

def get_url(outer_order_id):
  refundId = get_refundId(outer_order_id)
  host_url = 'http://test.shequ.com/order/agreeRefund?'
  reason_list = ['商品已售完','重複訂單','沒有騎手接單','聯絡不上顧客','顧客需要重新下單']
  reason = random.choice(reason_list)
  api_data = {
    'reason':reason,'refundId':refundId,'sendType':0
  }
  url = host_url + parse.urlencode(api_data)
  return url
print(get_url('3086123456'))
http://test.shequ.com/order/agreeRefund?reason=%E9%87%8D%E5%A4%8D%E8%AE%A2%E5%8D%95&refundId=1170611&sendType=0

# -*- coding: utf-8 -*-
import urllib
from bs4 import BeautifulSoup
import re
#訪問url,返回html頁面
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):#根據電影名稱,生成搜尋結果的URL
  host_url = 'http://s.dydytt.net/plus/search.php?kwtype=0&keyword='
  movie_sign = urllib.parse.quote(movie_name.encode('GBK'))
  search_url = host_url + movie_sign
  return search_url
#從搜尋結果頁面,提取電影的詳情頁面連結,存入列表返回
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')
  host = "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
#從電影詳情頁面中獲取電影標題
def get_movie_title(html):
  soup=BeautifulSoup(html,'html.parser')
  fixed_html=soup.prettify()
  title=soup.find('h1')
  title=title.string
  return title
#從電影詳情頁面中獲取此頁面所有的的下載連結
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
#傳入電影列表,獲取每個電影的下載地址
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') #忽略編碼錯誤
    m_title = get_movie_title(html)
    if u'遊戲' not in m_title: #過濾遊戲
      if u'動畫' not in m_title: #過濾動畫片
        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展現在頁面效果如下:

另一個網站的

# -*- 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 #關閉https協議驗證證書
def get_html(url): #訪問url,返回html頁面,如果url錯誤,則返回狀態碼,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):#根據電影名稱,返回正確的電影html
  pin = Pinyin()
  pinyin_movie_name = pin.get_pinyin(movie_name,"")#不使用分隔符,預設是-
  movie_type = {
    "Sciencefiction":"科幻片","Horror"    :"恐怖片","Drama"     :"劇情片","Action"    :"動作片","Comedy"    :"喜劇片","Love"     :"愛情片","War"      :"戰爭片"
  }
  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): #從電影html頁面中獲取下載地址
  movie_dict = {}
  soup = BeautifulSoup(html,'lxml')
  fixed_html = soup.prettify()
  a_urls = soup.find_all(href=re.compile("thunder"))#找到含有thunder連結的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

更多關於Python相關內容可檢視本站專題:《Python Socket程式設計技巧總結》、《Python資料結構與演算法教程》、《Python函式使用技巧總結》、《Python字串操作技巧彙總》、《Python入門與進階經典教程》及《Python檔案與目錄操作技巧彙總》

希望本文所述對大家Python程式設計有所幫助。