爬取某电影网站(未写完)(不会获取视频链接)

import requests

import bs4

import lxml

import re

import time

from bs4 import BeautifulSoup

#网站

url = 'https://www.88ys.cc'

#电影或电视剧的名字

film = '家有女友'

#代理ip

proxy='120.24.245.33:16818'#已过期，需续费

proxies = {

'http':'http://'+proxy,

'https':'https://'+proxy

}

#gzip访问速度更快

headers = {

"Accept-Encoding": "gzip"

}

####搜索结果####

def search():

####搜索结果####

#搜索链接

url_search = url + '/index.php?m=vod-search'

#post需要提交的参数

data = {

'wd':film ,

'submit':''

}

#提交搜索内容的表单

#①无代理

r_s = requests.post(url_search, data=data)

#②有代理

# r_s = requests.post(url_search, data=data, proxies=proxies, headers=headers)

#设置编码

r_s.encoding = 'utf-8'

#接收返回的网页

text_s = r_s.text

#

pat = re.compile(r'<a class="link-hover" href="(.*?)"')

pat_is = re.findall(pat, text_s)

# print(pat_is)

return pat_is

####获取集数####

def List(pat_search):

####获取集数####

#搜索结果链接

url_list = url + pat_search

#打开合并的链接

# r_list = requests.get(url_list, proxies=proxies, headers=headers)

r_list = requests.get(url_list)

#设置字符编码

r_list.encoding = 'utf-8'

#接收链接网页

text_list = r_list.text

# print(text_list)

#使用BeautifulSoup获取第一个片源的所有集数链接

text_l_b = BeautifulSoup(text_list,'lxml')

stab81 = text_l_b.find_all(name='div', attrs={'id':'stab81'})

stab81_re = re.findall(re.compile(r'href="(.*?)"'), str(stab81[0]))

# print(stab81_re)

return stab81_re

####搜索结果文字信息####

def search_news(pat_search):

####搜索结果文字信息####

#存储获取的信息以集合形式返回

#[0]电影名[1]影片类型[2]语言

information = []

#建立连接

url_search = url + pat_search

r = requests.get(url_search)

#设置编码

r.encoding = 'utf-8'

#获取电影信息的div

bs = str(BeautifulSoup(r.text, 'lxml').find_all('div', class_='ct-c'))

#获取电影名称，并添加到集合

h1_bs = BeautifulSoup(bs,'lxml')

h1_re = re.findall(re.compile(r'>(.*?)<'), str(h1_bs.h1))

information.append(h1_re[0])

#类型

type_re = re.findall(re.compile(r'类型：</span>(.*?)</dd>'), bs)

information.append(type_re[0])

#语言

language_re = re.findall(re.compile(r'语言：</span>(.*?)</dd>'), bs)

information.append(language_re[0])

# print(information)

return information

####Main函数(循环获取搜索结果和集数)####

def _for_():

####循环获取搜索结果和集数####

#调用搜索

pat_search = search()

#接收影片返回信息

information = None

#接收片源一返回的信息

stab81 = None

# 循环调用方法

for i in pat_search:

#调用方法并接收

information = search_news(i)

#调用方法并接收

stab81 = List(i)

#打印

print(information)

#打印

print(stab81)

#使用延时防止运行太快被网站强制断开连接

time.sleep(3)

# 调用主(Main)函数

_for_()

####未做完，查看器和爬取源码不一致####

def a():

_url_ = url + '/vod-play-id-56106-src-1-num-1.html'

r = requests.get(_url_)

r.encoding = 'utf-8'

bs = BeautifulSoup(r.text,'lxml')

print(bs.prettify())