Python问题总结
1.Python抓取网页内容显示中文乱码
解决:
1 #coding=utf-8 2 3 import urllib2 4 import sys 5 6 page = 1 7 url = 'http://www.qiushibaike.com/hot/page/' + str(page) 8 user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)' 9 headers = { 'User-Agent' : user_agent} 10 11 12 13 try: 14 request = urllib2.Request(url, headers = headers) 15 response = urllib2.urlopen(request) 16 type = sys.getfilesystemencoding() #关键 17 #print type 18 print response.read().decode("UTF-8").encode(type) #关键 19 #print response.read() 20 21 except urllib2.URLError, e: 22 if hasattr(e, "code"): 23 print e.code 24 if hasattr(e, "reason"): 25 print e.reason