Skip to content

Instantly share code, notes, and snippets.

@binyuj
binyuj / main.py
Created March 29, 2013 12:04 — forked from zjjott/main.py
#coding=utf-8
import os
os.system("wget -r --spider http://diameizi.diandian.com 2>|log.txt")#非常简单的抓取整个网页树结构的语句————实质上是一种偷懒
filein=open('log.txt','r')
fileout=open('dst','w+')#一个装最后的结果的没用的文件
filelist=list(filein)
import urllib2,time
from bs4 import BeautifulSoup
header={
'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.7; rv:8.0.1) Gecko/20100101 Firefox/8.0.1'}
#!/bin/sh
curl -L -O https://github.com/python-greenlet/greenlet/archive/0.4.0.tar.gz && tar xvzpf 0.4.0.tar.gz && cd greenlet-0.4.0 && sudo python setup.py install
#!/bin/sh
curl -L -O https://github.com/gevent/gevent/releases/download/v1.0.2/gevent-1.0.2.tar.gz && tar xvzpf gevent-1.0.2.tar.gz && cd gevent-1.0.2 && sudo python setup.py install