爬取某电影网站(未写完)

  1 import requests
  2 import bs4
  3 import lxml
  4 import re
  5 import time
  6 from bs4 import BeautifulSoup
  7 #网站
  8 url = 'https://www.88ys.cc'
  9 #电影或电视剧的名字
 10 film = '家有女友'
 11 #代理ip
 12 proxy='120.24.245.33:16818'#已过期，需续费
 13 proxies = {
 14     'http':'http://'+proxy,
 15     'https':'https://'+proxy
 16     }
 17 #gzip访问速度更快
 18 headers = {
 19     "Accept-Encoding": "gzip"
 20     }
 21 ####搜索结果####
 22 def search():
 23     ####搜索结果####
 24     #搜索链接
 25     url_search = url + '/index.php?m=vod-search'
 26     #post需要提交的参数
 27     data = {
 28         'wd':film ,
 29         'submit':''
 30     }
 31     #提交搜索内容的表单
 32     #①无代理
 33     r_s = requests.post(url_search, data=data)
 34     #②有代理
 35     # r_s = requests.post(url_search, data=data, proxies=proxies, headers=headers)
 36     #设置编码
 37     r_s.encoding = 'utf-8'
 38     #接收返回的网页
 39     text_s = r_s.text
 40     #
 41     pat = re.compile(r'<a class="link-hover" href="(.*?)"')
 42     pat_is = re.findall(pat, text_s)
 43     # print(pat_is)
 44     return pat_is
 45 ####获取集数####
 46 def List(pat_search):
 47     ####获取集数####
 48     #搜索结果链接
 49     url_list = url + pat_search
 50     #打开合并的链接
 51     # r_list = requests.get(url_list, proxies=proxies, headers=headers)
 52     r_list = requests.get(url_list)
 53     #设置字符编码
 54     r_list.encoding = 'utf-8'
 55     #接收链接网页
 56     text_list = r_list.text
 57     # print(text_list)
 58     #使用BeautifulSoup获取第一个片源的所有集数链接
 59     text_l_b = BeautifulSoup(text_list,'lxml')
 60     stab81 = text_l_b.find_all(name='div', attrs={'id':'stab81'})
 61     stab81_re = re.findall(re.compile(r'href="(.*?)"'), str(stab81[0]))
 62     # print(stab81_re)
 63     return stab81_re
 64 ####搜索结果文字信息####
 65 def search_news(pat_search):
 66     ####搜索结果文字信息####
 67     #存储获取的信息以集合形式返回
 68     #[0]电影名[1]影片类型[2]语言
 69     information = []
 70     #建立连接
 71     url_search = url + pat_search
 72     r = requests.get(url_search)
 73     #设置编码
 74     r.encoding = 'utf-8'
 75     #获取电影信息的div
 76     bs = str(BeautifulSoup(r.text, 'lxml').find_all('div', class_='ct-c'))
 77     #获取电影名称，并添加到集合
 78     h1_bs = BeautifulSoup(bs,'lxml')
 79     h1_re = re.findall(re.compile(r'>(.*?)<'), str(h1_bs.h1))
 80     information.append(h1_re[0])
 81     #类型
 82     type_re = re.findall(re.compile(r'类型：</span>(.*?)</dd>'), bs)
 83     information.append(type_re[0])
 84     #语言
 85     language_re = re.findall(re.compile(r'语言：</span>(.*?)</dd>'), bs)
 86     information.append(language_re[0])
 87     # print(information)
 88     return information
 89 ####Main函数(循环获取搜索结果和集数)####
 90 def _for_():
 91     ####循环获取搜索结果和集数####
 92     #调用搜索
 93     pat_search = search()
 94     #接收影片返回信息
 95     information = None
 96     #接收片源一返回的信息
 97     stab81 = None
 98     # 循环调用方法
 99     for i in pat_search:
100         #调用方法并接收
101         information = search_news(i)
102         #调用方法并接收
103         stab81 = List(i)
104         #打印
105         print(information)
106         #打印
107         print(stab81)
108         #使用延时防止运行太快被网站强制断开连接
109         time.sleep(3)
110 # 调用主(Main)函数
111 _for_()
112 ####未做完，查看器和爬取源码不一致####
113 def a():
114     _url_ = url + '/vod-play-id-56106-src-1-num-1.html'
115     r = requests.get(_url_)
116     r.encoding = 'utf-8'
117     bs = BeautifulSoup(r.text,'lxml')
118     print(bs.prettify())

(未解决问题)

1.查看器和爬取源码不一致

2.获取视频链接

3.电影下载操作

转载于:https://www.cnblogs.com/Ly-233/p/11205661.html