psiupuxa.com

psiupuxa.com.py

# -*- coding: utf-8 -*-

'''
$ mkvirtualenv psiupuxa.com
$ workon psiupuxa.com
$ pip install grequests
$ pip install scrapy
$ python psiupuxa.com.py > psiupuxa.com.txt
$ xargs -P 64 wget < psiupuxa.com.txt
'''

from grequests import get, map
from scrapy.selector import Selector

for response in map(
    (get(url) for url in ['http://psiupuxa.com/pages/{page}'.format(page=page + 1) for page in range(1, 8)])
):
    for url in Selector(text=response.text).xpath('//a/@href').extract():
        if '_desktop.' in url:
            print url