from bs4 import BeautifulSoup
import requests
import re
from Crypto.Cipher import AES
import os
def tsList(Index):
with open(os.getcwd()+ '/m3u8.txt','r') as f:
if '.ts' in f.read():
print('ts视频链接均已存储，无需重复请求')
else:
print('开始获取并存储ts链接')
with open(os.getcwd()+ '/m3u8.txt','r') as f:
m3u8Url = f.readlines()[0].strip()
content = requests.get(m3u8Url,headers=headers)
jiami=re.findall('#EXT-X-KEY:(.*)\n',content.text)
m3u8Url_before = ''
if len(jiami)>0:
key=str(re.findall('URI="(.*)"',jiami[0]))[2:-2]
if 'http' not in key:
m3u8Start = m3u8Url.find("\"url\":\"")+7
m3u8End = m3u8Url.find(".m3u8")+5
m3u8Url = m3u8Url[m3u8Start:m3u8End].replace('\\','')
m3u8Url_before="https://" + m3u8Url.split('/')[2]
else:
m3u8Url_before = ''
keycontent= requests.get(m3u8Url_before + key,headers).text
with open(os.getcwd()+ '/m3u8.txt','a') as f:
f.write(keycontent + '\n')
else:
with open(os.getcwd()+ '/m3u8.txt','a') as f:
f.write('000000000000')
if(content.status_code == 200):
pattern = re.compile(r'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+')
content = content.text.split(",")
index = 0
for item in content:
if 'http' not in item:
index += 1
temp = (m3u8Url_before+item).replace("\n", "")
url = str(pattern.findall(temp))[2:-2]
with open(os.getcwd()+ '/m3u8.txt','a') as f:
f.write(url + '\n')
else:
index += 1
url = str(pattern.findall(item))[2:-2]
with open(os.getcwd()+ '/m3u8.txt','a') as f:
f.write(url + '\n')
Download(Index)
def Download(Index):
now = videoName + "_第" + str(Index+1) + '集'
index = 0
try:
with open(os.getcwd()+ '/index.txt','r') as f3:
index = int(float(f3.read()))
except FileNotFoundError as e:
index = 4
index1 = index
with open(os.getcwd()+ '/m3u8.txt','r') as getKey:
keycontent = getKey.readlines()[1][0:-1]
print(keycontent)
if keycontent == '000000000000':
print("未加密")
else:
cryptor = AES.new(keycontent.encode('utf-8'), AES.MODE_CBC, keycontent.encode('utf-8'))
with open(os.getcwd()+ '/m3u8.txt','r') as getTsUrlList:
tsList = getTsUrlList.readlines()[index:]
tsListlen = len(tsList)
for i in tsList[1:]:
print("预估进度：" + str(index1-3) + '/' + str(tsListlen-1) + " 即将下载：" + i)
res = ''
for item in range(1,10):
try:
response = requests.get(i, headers=headers,timeout=3)
except Exception as e:
print(i[-12:-1] + '请求超时，重新请求第' + str(item) + '次')
continue
if(response.status_code == 200):
print(i[-12:-1] + '请求成功')
res = response
if keycontent == '000000000000':
print('未加密，直接追加')
cont=res.content
else:
try:
cont=cryptor.decrypt(res.content)
except:
pass
with open(os.getcwd() + '/' + now +'.mp4', 'ab+') as f:
f.write(cont)
f.close()
index1 += 1
print("追加完成，已标记")
with open(os.getcwd()+ '/index.txt','w') as f:
f.write(str(index1))
f.close()
break
else:
continue
with open(os.getcwd()+ '/jishu.txt','w') as indexFile:
indexFile.write(str(Index+1) + ' \n')
with open(os.getcwd()+ '/m3u8.txt','a') as indexFile:
indexFile.truncate(0)
with open(os.getcwd()+ '/index.txt','w') as f:
f.write('0')
f.close()
return True
def getM3u8(htmlUrl):
content = requests.get(htmlUrl,headers=headers).text
bsObj = BeautifulSoup(content,"html.parser")
index = 0
for scriptItem in bsObj.findAll("script"):
index += 1
if '.m3u8' in str(scriptItem):
pattern = re.compile(r'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+')
m3u8Url = pattern.search(str(scriptItem)).group()
global m3u8Url_before
m3u8Url_before=getDomain(m3u8Url)
if 'hls' not in m3u8Url:
content = requests.get(m3u8Url,headers=headers).text
count = 0
nList = []
for item in list(content):
count += 1
if item == '\n':
nList.append(count)
m3u8Url_hls = str(content)[nList[-2]:nList[-1]]
if 'http' not in m3u8Url_hls:
m3u8Url_hls = m3u8Url_before + m3u8Url_hls
else:
m3u8Url_hls = m3u8Url
if 'ENDLIST' not in m3u8Url_hls:
with open(os.getcwd()+ '/m3u8.txt','w') as f:
f.write(m3u8Url_hls)
return(1)
else:
content = requests.get(m3u8Url,headers=headers).text.split(",")
with open(os.getcwd()+ '/m3u8.txt','a+') as f:
f.write('hello~~' + '\n')
with open(os.getcwd()+ '/m3u8.txt','a+') as f:
f.write('000000000000\n')
for i in content:
if '/' in i:
breakpoint = i[1:].index('\n')+1
with open(os.getcwd()+ '/m3u8.txt','a+') as f:
f.write(i[1:breakpoint] + '\n')
return (2)
else:
if index == len(list(bsObj.findAll("script"))):
print("在页面Script中未找到相关m3u8链接。。。")
return (3)
def jiexiHtml(htmlUrl):
content = requests.get(htmlUrl,headers=headers).text
bsObj = BeautifulSoup(content,"html.parser")
global videoName
videoName = bsObj.find('h1',{'class','page-title'}).text
videoItemHtml = bsObj.find('div',{'class':'scroll-content'}).findAll('a',href=re.compile("^(/ShowInfo/)((?!:).)*$"))
with open(os.getcwd()+ '/' +videoName+'.txt','w') as indexFile:
indexFile.truncate(0)
for i in videoItemHtml:
item = str(i.attrs['href'])
if 'http' not in item:
Domain = getDomain(htmlUrl)
with open(os.getcwd()+ '/' +videoName+'.txt','a') as indexFile:
indexFile.write(Domain + item + '\n')
else:
with open(os.getcwd()+ '/' +videoName+'.txt','a') as indexFile:
indexFile.write(item + '\n')
print("indexFile已更新")
try:
with open(os.getcwd()+ '/jishu.txt','r') as indexFile:
pass
except FileNotFoundError as e:
print("jishu不存在，已创建并置零")
with open(os.getcwd()+ '/jishu.txt','a') as indexFile:
indexFile.write('0 \n')
with open(os.getcwd()+ '/' +videoName+'.txt','r') as indexFile:
HtmlArr = indexFile.readlines()
with open(os.getcwd()+ '/jishu.txt','r') as indexFile:
jishu = int(indexFile.read())
print("txt记录集数为：" + str(jishu))
for htmlItem in HtmlArr[jishu:]:
with open(os.getcwd()+ '/jishu.txt','r') as indexFile:
jishuRun = int(indexFile.read())
print("txt记录集数为：" + str(jishuRun))
openHtml(htmlItem,jishuRun)
def openHtml(htmlItem,jishu):
print("当前打开链接：" + htmlItem)
pd = getM3u8(htmlItem)
if(pd == 1):
tsList(jishu)
elif (pd == 2):
if Download(jishu):
return True
else:
pass
def getDomain(htmlUrl):
pattern = re.compile(r'http[s]?://[a-zA-Z\-.0-9]+(?=\/)')
return(str(pattern.search(htmlUrl).group()))
def searchVideo(searchName):
content = requests.get('你找的影院地址',headers=headers,params={'searchword': searchName})
bsObj = BeautifulSoup(content.text,"html.parser")
VideoList = bsObj.findAll("a",{"class":"module-item-pic"})
if VideoList:
htmlUrlList = VideoList
return htmlUrlList
else:
return False
if __name__ == '__main__':
searchName = input('输入想搜索的剧名：')
global headers
headers = {
}
htmlUrlList = searchVideo(searchName)
if htmlUrlList:
li = 0
for i in htmlUrlList:
li += 1
title = i.find('img',{"class":"lazyload"}).attrs['alt']
print(str(li) + '、' + title +'\n')
else:
print("未搜索到相关影片")
try:
raise RuntimeError('testError')
except RuntimeError as e:
print("程序即将中断")
os._exit(0)
liNo = input('选择需要尝试下载的影片的编号：')
if htmlUrlList[int(liNo)-1]:
htmlUrl = htmlUrlList[int(liNo)-1].attrs['href']
if os.path.exists(os.getcwd()+ '/' + searchName):
pass
else:
os.makedirs(os.getcwd()+ '/' + searchName)
os.chdir( os.getcwd()+ '/' + searchName )
jiexiHtml('你找的影院地址' + htmlUrl)
else:
print("数值超出范围")
