xpath爬取新浪天气

 1 # -*- coding:utf-8 -*-
 2 import urllib2
 3 from lxml import etree
 4 user_agent = "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0"
 5 headers = {‘User-Agent‘:user_agent}
 6 url = ‘http://weather.sina.com.cn/‘
 7 user_input = raw_input("请输入你想查询天气的城市的拼音，如beijing\n")
 8 # print user_input
 9 url = url+user_input
10 # print url
11 req = urllib2.Request(url,headers=headers)
12 reponse = urllib2.urlopen(req)
13 text = reponse.read()
14 # print html
15 # print type(text)
16 html = etree.HTML(text)
17 # print html
18 # result = etree.tostring(html)
19 # print result
20 # 有时候当天天气信息的icons和times数据只有19条，分开处理
21 def change_list(lis):
22     new_lis = []
23     if len(lis) == 19:
24         if lis == icons:
25             new_lis.append(lis[0])
26             for i in range(1,19,2):
27                 new_lis.append(lis[i]+u‘转‘+lis[i+1])
28         elif lis == times:
29             new_lis.append(lis[0].text)
30             for i in range(1, 19, 2):
31                 new_lis.append(lis[i].text + u‘到‘ + lis[i + 1].text)
32     elif len(lis) == 20:
33         if lis == icons:
34             for i in range(20,2):
35                 new_lis.append(lis[i]+u‘转‘+lis[i+1])
36         elif lis == times:
37             for i in range(20,2):
38                 new_lis.append(lis[i].text + u‘到‘ + lis[i + 1].text)
39     return new_lis
40 note1 = html.xpath(‘//*[@class="wt_tt0_note"]‘)
41 note2 = html.xpath(‘//*[@class="wt_tt0_note"]/..‘)
42 # print note[0].text
43 dates = html.xpath(‘//*[@class="wt_fc_c0_i_date"]‘)
44 days = html.xpath(‘//*[@class="wt_fc_c0_i_date"]/following-sibling::*[1]‘)
45 icons = html.xpath(‘//*[@class="wt_fc_c0_i_icons clearfix"]/img/@alt‘)
46 # print len(icons)
47 icons = change_list(icons)
48 times = html.xpath(‘//*[@class="wt_fc_c0_i_times"]/span‘)
49 times = change_list(times)
50 temps = html.xpath(‘//*[@class="wt_fc_c0_i_temp"]‘)
51 tips = html.xpath(‘//*[@class="wt_fc_c0_i_tip"]‘)
52 ls = html.xpath(‘//*[@class="l"]‘)
53 rs = html.xpath(‘//*[@class="r"]‘)
54 print note1[0].text,note2[0].text
55 # print len(ls),len(rs)
56 # PM2.5和空气质量只有7条数据
57 for i in range(7):
58     print dates[i].text, days[i].text, times[i], icons[i], temps[i].text, tips[i].text, u‘PM2.5:‘+ls[i].text, u‘空气质量:‘+rs[i].text
59 for i in range(7,10):
60     print dates[i].text, days[i].text, times[i], icons[i], temps[i].text, tips[i].text