还是老生常谈的操作

import requests

import os

from bs4 import BeautifulSoup

from urllib.parse import urljoin

html = requests.get('http://www.332dy.com/pu/37192-0-0.html')

soup = BeautifulSoup(html.text,'lxml')

lists = soup.select('.stui-content__playlist.sort-list.column8.clearfix li a')

for list in lists:

print(list['href'])

返回

/pu/37192-0-0.html

/pu/37192-0-1.html

/pu/37192-0-2.html

/pu/37192-0-3.html

/pu/37192-0-4.html

/pu/37192-0-5.html

/pu/37192-1-0.html

/pu/37192-1-1.html

/pu/37192-1-2.html

/pu/37192-1-3.html

/pu/37192-1-4.html

/pu/37192-1-5.html

拼接一下

import requests

import os

from bs4 import BeautifulSoup

from urllib.parse import urljoin

base_url = 'http://www.332dy.com/'

html = requests.get('http://www.332dy.com/pu/37192-0-0.html')

soup = BeautifulSoup(html.text,'lxml')

lists = soup.select('.stui-content__playlist.sort-list.column8.clearfix li a')

for list in lists:

innerurl = urljoin(base_url,list['href'])

print(innerurl)

然后我们就要下载这个视频，来抓下包

可以看到是个ts流，这个就是分段下载，一般ts流都有个m3u8

可以看到这个sign是从一个script脚本里面取的，把鼠标移到上面可以看到share我们去源代码全局搜索下share

访问https://shuixian.nihaozuida.com/share/7f53f8c6c730af6aeb52e66eb74d8507可以看到是视频这个应该是

3u8文件，我们就取出var now=使用正则表达式因为script一般不在我们语法里面

re_m3u8 = re.compile('now="(.*?)"',re.I|re.S)

html2 = requests.get(innerurl)

m3u8Result = re_m3u8.findall(html2.text)[0]

print(m3u8Result)

成功获取到了，但是返回的为列表是4集我们获取第一个,所以加上[0]

我们访问一下抓包，可以看到访问了这个文件然后main里面我们访问就是下载的m3u8文件

同样正则获取一下里面的值

re_main = re.compile('main = "(.*?)"',re.I|re.S)

html3 = requests.get(m3u8Result)

mainResult = re_main.findall(html3.text)[0]

print(mainResult)

同样取出要拼接

baseurl = 'https://shuixian.nihaozuida.com/'

resultUrl = urljoin(baseurl,mainResult)

print(resultUrl)

然后我们把这个m3u8文件保存一下

if not os.path.exists('影视'):

os.mkdir('影视')

with open('影视/m3u81.txt','w',encoding='utf-8')as f:

f.write(requests.get(resultUrl).text)

print('m3u8存储完毕')

然后再读取出来

with open('影视/m3u81.txt', 'r', encoding='utf-8')as f:

lines = f.readlines()

for line in lines:

if line.startswith('#'):

continue

print(line)

输出

1024k/hls/index.m3u8

再拼接起来

现在获取到的就是里面很多ts流，同样保存起来

with open('影视/m3u82.txt', 'w', encoding='utf-8')as f:

f.write(requests.get(url).text)

print('m3u8存储完毕')

with open('影视/m3u82.txt', 'r', encoding='utf-8')as f:

lines = f.readlines()

for line in lines:

if line.startswith('#'):

continue

print(line)

输出

base = 'https://shuixian.nihaozuida.com/20200313/1391_06cf517b/1024k/hls/'

url = urljoin(base,line.strip().replace('\n',''))

print(url)

然后就是下载这些ts流，最终代码为

import requests

import os

import re

from bs4 import BeautifulSoup

from urllib.parse import urljoin

re_m3u8 = re.compile('now="(.*?)"',re.I|re.S)

re_main = re.compile('main = "(.*?)"',re.I|re.S)

html = requests.get('http://www.332dy.com/dili/37192.html')

soup = BeautifulSoup(html.text,'lxml')

lis = soup.select('ul.stui-content__playlist.sort-list.column8.clearfix li a')

base = 'http://www.332dy.com/'

for li in lis:

innerUrl = urljoin(base,li['href'])

# print(innerUrl)

html2 = requests.get(innerUrl)

m3u8Result = re_m3u8.findall(html2.text)

# print(m3u8Result)

if m3u8Result==[]:

base = 'http://www.332dy.com'

innerUrl = urljoin(base, li['href'])

html2 = requests.get(innerUrl)

m3u8Result = re_m3u8.findall(html2.text)

html3 = requests.get(m3u8Result[0])

mainResult = re_main.findall(html3.text)[0]

baseurl = 'https://shuixian.nihaozuida.com/'

resultUrl = urljoin(baseurl,mainResult)

if not os.path.exists('影视'):

os.mkdir('影视')

with open('影视/m3u81.txt','w',encoding='utf-8')as f:

f.write(requests.get(resultUrl).text)

print('m3u8存储完毕')

with open('影视/m3u81.txt', 'r', encoding='utf-8')as f:

lines = f.readlines()

for line in lines:

if line.startswith('#'):

continue

# print(line)

#https://shuixian.nihaozuida.com/20200313/1391_06cf517b/1024k/hls/index.m3u8

#1024k/hls/index.m3u8

basem3u8 = 'https://shuixian.nihaozuida.com/20200313/1391_06cf517b/'

url = urljoin(basem3u8,line)

break

with open('影视/m3u82.txt', 'w', encoding='utf-8')as f:

f.write(requests.get(url).text)

print('m3u8存储完毕')

with open('影视/m3u82.txt', 'r', encoding='utf-8')as f:

lines = f.readlines()

for line in lines:

if line.startswith('#'):

continue

# print(line)

base = 'https://shuixian.nihaozuida.com/20200313/1391_06cf517b/1024k/hls/'

ts_url = urljoin(base,line.strip().replace('\n',''))

# print(url)

with open('影视/1.mp4','ab')as f:

f.write(requests.get(ts_url).content)

效果