本文實(shí)例講述了Python3.6實(shí)現(xiàn)根據(jù)電影名稱(支持電視劇名稱),獲取下載鏈接的方法。分享給大家供大家參考,具體如下:
做個(gè)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','重復(fù)訂單','沒(méi)有騎手接單','聯(lián)系不上顧客','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(wèn)url,返回html頁(yè)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(jù)電影名稱,生成搜索結(jié)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 #從搜索結(jié)果頁(yè)面,提取電影的詳情頁(yè)面鏈接,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(yè)面中獲取電影標(biāo)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(yè)面中獲取此頁(yè)面所有的的下載鏈接 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 #傳入電影列表,獲取每個(gè)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(cuò)誤 m_title = get_movie_title(html) if u'游戲' not in m_title: #過(guò)濾游戲 if u'動(dòng)畫(huà)' not in m_title: #過(guò)濾動(dòng)畫(huà)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(xiàn)在頁(yè)面效果如下:
另一個(gè)網(wǎng)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(guān)閉https協(xié)議驗(yàn)證證書(shū) def get_html(url): #訪問(wèn)url,返回html頁(yè)面,如果url錯(cuò)誤,則返回狀態(tài)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(jù)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,默認(rèn)是- movie_type = { "Sciencefiction":"科幻片", "Horror" :"恐怖片", "Drama" :"劇情片", "Action" :"動(dòng)作片", "Comedy" :"喜劇片", "Love" :"愛(ài)情片", "War" :"戰(zhàn)爭(zhēng)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(yè)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鏈接的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
更多關(guān)于Python相關(guān)內(nèi)容可查看本站專題:《Python Socket編程技巧總結(jié)》、《Python數(shù)據(jù)結(jié)構(gòu)與算法教程》、《Python函數(shù)使用技巧總結(jié)》、《Python字符串操作技巧匯總》、《Python入門與進(jìn)階經(jīng)典教程》及《Python文件與目錄操作技巧匯總》
希望本文所述對(duì)大家Python程序設(shè)計(jì)有所幫助。
更多文章、技術(shù)交流、商務(wù)合作、聯(lián)系博主
微信掃碼或搜索:z360901061

微信掃一掃加我為好友
QQ號(hào)聯(lián)系: 360901061
您的支持是博主寫作最大的動(dòng)力,如果您喜歡我的文章,感覺(jué)我的文章對(duì)您有幫助,請(qǐng)用微信掃描下面二維碼支持博主2元、5元、10元、20元等您想捐的金額吧,狠狠點(diǎn)擊下面給點(diǎn)支持吧,站長(zhǎng)非常感激您!手機(jī)微信長(zhǎng)按不能支付解決辦法:請(qǐng)將微信支付二維碼保存到相冊(cè),切換到微信,然后點(diǎn)擊微信右上角掃一掃功能,選擇支付二維碼完成支付。
【本文對(duì)您有幫助就好】元
