Skip to content

Instantly share code, notes, and snippets.

@coeric
Created August 4, 2018 23:51
Show Gist options
  • Star 14 You must be signed in to star a gist
  • Fork 1 You must be signed in to fork a gist
  • Save coeric/7b27c7e24afc9ebea847375e7db38b82 to your computer and use it in GitHub Desktop.
Save coeric/7b27c7e24afc9ebea847375e7db38b82 to your computer and use it in GitHub Desktop.
#-*- coding:utf-8 -*-
#!/usr/bin/env python
import requests
from bs4 import BeautifulSoup
import re
import shutil
import os
out='/home/coericnb'
def get_video(url):
res=requests.get(url)
soup=BeautifulSoup(res.content,'html.parser')
temp=soup.findAll('script')
for i in temp:
if re.search("html5player.setVideoUrlHigh",i.text):
m= re.search("html5player.setVideoUrlHigh\('(.*?)'\);",i.text)
n= re.search("html5player.setVideoTitle\('(.*?)'\);",i.text)
url_mov=m.group(1)
filename=n.group(1)+".mp4"
# print filename
res_mov=requests.get(url_mov,stream=True)
path=os.path.join(out,filename)
if os.path.exists(path) and os.path.getsize(path)>0:pass
else:
f=open(path,'wb')
shutil.copyfileobj(res_mov.raw,f)
f.close()
def get_list():
url="http://www.xvideos.com/"
res=requests.get(url)
soup=BeautifulSoup(res.content,'html.parser')
temp=soup.find('div',attrs={'class':'mozaique'}).findAll('div',attrs={'class':'thumb-block '})
for i in temp:
url_mov="https://www.xvideos.com"+i.findAll('a')[0]['href']
print url_mov
get_video(url_mov)
get_list()
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment