Un fix pour la bbc, mon bbc33.py
j'utilise un autre site de proxys
/usr/bin/env python
# -*- coding:utf-8 -*-
# bbc_proxy version 0.3 par k3c, sortie quand deja telecharge
# passage de proxy en 2 ème parametre
import subprocess, sys, shlex
import random
import urllib2
import requests
import bs4 as BeautifulSoup
import socket
from threading import Thread
ON_POSIX = 'posix' in sys.builtin_module_names
Finished = False
listeUserAgents = [ 'Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_5; fr-fr) AppleWebKit/525.18 (KHTML, like Gecko) Version/3.1.2 Safari/525.20.1',
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.186 Safari/535.1',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/525.13 (KHTML, like Gecko) Chrome/0.2.149.27 Safari/525.13\
',
'Mozilla/5.0 (X11; U; Linux x86_64; en-us) AppleWebKit/528.5+ (KHTML, like Gecko, Safari/528.5+) midori',
'Mozilla/5.0 (Windows NT 6.0) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/13.0.782.107 Safari/535.1',
'Mozilla/5.0 (Macintosh; U; PPC Mac OS X; en-us) AppleWebKit/312.1 (KHTML, like Gecko) Safari/312',
'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.12 Safari/535.11',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.8 (KHTML, like Gecko) Chrome/17.0.940.0 Safari/535.8' ]
allTimeouts = (3, 10, 15, 20)
class FlushFile(object):
"""Write-only flushing wrapper for file-type objects."""
def __init__(self, f):
self.f = f
def write(self, x):
self.f.write(x)
self.f.flush()
def start_thread(func, *args):
t = Thread(target=func, args=args)
t.daemon = True
t.start()
return t
def consume(infile):
global Finished
for line in iter(infile.readline, ''):
if 'Finished writing to temp file.' in line:
Finished = True
if 'Already in history' in line:
Finished = True
print line,
infile.close()
def getProxy():
import re
import requests
import bs4 as BeautifulSoup
html = requests.get('http://www.gatherproxy.com/proxylist/country/?c=United%20Kingdom')
soup = BeautifulSoup.BeautifulSoup(html.text)
mastr = soup.find_all('script')
lst = []
for x in mastr:
slst = []
if "gp.insertPrx" in x.text:
m = re.search('"PROXY_IP":"(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})',x.text)
if m:
slst.append(m.group(1))
mport = re.search('"PROXY_PORT":"(\w*[0-9]*)',x.text)
if mport:
slst.append(int(mport.group(1),16))
mportype = re.search('"PROXY_TYPE":"(\w*)',x.text)
if mportype:
slst.append(mportype.group(1))
lst.append(slst)
for href in lst:
yield href
def getValidProxy():
for timeout in allTimeouts:
print 'Timeout =', timeout
socket.setdefaulttimeout(timeout)
for host, port, typeproxy in getProxy():
try:
print 'Trying %s:%s' % (host, port)
print host, type(host), port, type(port)
params = (host, port)
s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
s.connect(params)
s.close()
yield host, port, typeproxy
# except urllib2.URLError:
# pass
except socket.timeout:
pass
except socket.error:
pass
def main():
global Finished
# Replace stdout with an automatically flushing version
sys.stdout = FlushFile(sys.__stdout__)
sys.stderr = FlushFile(sys.__stderr__)
idvideo = sys.argv[1]
for host, port, typeproxy in getValidProxy():
print host, port, typeproxy
if len(sys.argv) > 1 and sys.argv[2] == '1':
cmds = "get_iplayer --get "+idvideo + " --nopurge --modes=best --subtitles --force -p 'http://"+host+":"+str(port)+"'"
else:
cmds = "get_iplayer --get "+idvideo + " --nopurge --modes=best --subtitles -p 'http://"+host+":"+str(port)+"'"
print cmds
arguments = shlex.split(cmds)
Finished = False
process = subprocess.Popen(arguments, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
pid = process.pid
thread1 = start_thread(consume, process.stdout)
thread2 = start_thread(consume, process.stderr)
thread1.join() # wait for IO completion
thread2.join() # wait for IO completion
retcode = process.wait()
print retcode
if Finished:
break
if __name__ == "__main__":
main()
