python 简单爬虫

#coding=gbk
import urllib.request
url = "http://www.baidu.com"
res = urllib.request.urlopen(url)
print(type(res)) # http.client.HTTPResponse
print(res.geturl())
data = {}
data["word"] = "Jecccc world"
data["word2"] = "Jecccc world"
url = "http://www.baidu.com/s?"
url_values = urllib.parse.urlencode(data)
# urllib.parse.urlencode: data["word"] = "abc def" -> word = abc+def
# data["attr1"] = "val1",data["attr2"] = "val2" --> word=Jecccc+world&word2=Jecccc+world
full_url = url + url_values
print(full_url)
html = res.read()
print(html)

http://www.linuxeden.com/html/news/20141001/155957.html

import urllib2
url = "http://docs.30c.org/djangobook2/chapter"
for pageIndex in range(0,21):
	pre = str(pageIndex)
	if pageIndex < 10:
		pre = "0" + pre
	newurl = url + pre
	try:
		response = urllib2.urlopen(newurl)
	except :
		print "url not exist: " + newurl
		continue
	html = response.read()
	htmlfile = open(pre + ".html","w")
	htmlfile.write(html)
	htmlfile.close()
print "end"