Last active
August 29, 2015 14:26
-
-
Save dingyaguang117/088d07216ca52e13288a to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#coding=utf-8 | |
__author__ = 'ding' | |
from gevent import monkey | |
monkey.patch_all() | |
from gevent.pool import Pool | |
import requests | |
sites = [u'0i4t.com', u'0757dk.com', u'0007ka.com', u'003782.com', u'0735.com', u'04336789.com', u'078078.com', u'0851qy.com', u'008321.com', u'0427d7.se', u'010sf.com', u'0476com.com', u'0470a.com', u'0163.com', u'00992.com', u'0759job.com', u'0437t.com', u'057191.com', u'0932.info', u'0311xinhua.cn', u'041pao.com', u'009997.com', u'018tk.com', u'099cf.com', u'0576qq.com', u'0101010.info', u'001lv.org', u'0771pc.com', u'0734kj.com', u'076665.cn', u'001123.com', u'08kkkk.com', u'0416hlw.com', u'0452e.com', u'001ni.com', u'001dd.com', u'012666.com', u'010tk.com', u'0579h.com', u'0851yifu.com', u'06049.com', u'044944.com', u'0752oa.net', u'003003.net', u'050gg.com', u'02325.org', u'0744y.com', u'0523114.com', u'0449aa.com', u'0597house.com', u'0411house.com', u'099333.com', u'001lv.com', u'050q.com', u'067.cc', u'02kkk.com', u'050ww.com', u'0437.gov.cn', u'073311.com', u'024www.net', u'073img.com', u'0592rc.cn', u'09gao.com', u'008zyz.com', u'022car.com.cn', u'00087.com', u'050aa.com', u'001d88.com', u'02728.com', u'07073.cn', u'001jm.com', u'003zyz.com', u'0773f.com', u'0311dd.com', u'023001.com', u'040206.com', u'03088.com', u'099456.com', u'0907.org', u'0572home.com', u'0731tg.cc', u'007tk.net', u'030401.com', u'01116.com', u'035pao.com', u'0551night.com', u'0123456.co', u'009cnc.com', u'06379.com.cn', u'002cn.cn', u'08118.com', u'01666.com', u'021lvzhou.com', u'0519.com', u'07141.com.cn', u'028tsh.com', u'0768000.com', u'0510wxly.com', u'0370home.com', u'0755lswjs.com'] | |
def crawl_title(site): | |
try: | |
url = 'http://' + site | |
content = requests.get(url).content | |
except: | |
print site, 'get error' | |
return | |
print site, len(content) | |
def crawl(): | |
pool = Pool(10) | |
pool.map(crawl_title, sites) | |
if __name__ == '__main__': | |
crawl() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment