[Python爬虫] Selenium获取百度百科旅游景点的InfoBox消息盒

 1 # coding=utf-8  
 2 """ 
 3 Created on 2015-09-04 @author: Eastmount  
 4 """  
 5   
 6 import time          
 7 import re          
 8 import os  
 9 import sys
10 import codecs
11 from selenium import webdriver      
12 from selenium.webdriver.common.keys import Keys      
13 import selenium.webdriver.support.ui as ui      
14 from selenium.webdriver.common.action_chains import ActionChains  
15   
16 #Open PhantomJS  
17 driver = webdriver.PhantomJS(executable_path="G:\phantomjs-1.9.1-windows\phantomjs.exe")  
18 #driver = webdriver.Firefox()  
19 wait = ui.WebDriverWait(driver,10)
20 global info #全局变量
21 
22 #Get the infobox of 5A tourist spots  
23 def getInfobox(name):  
24     try:  
25         #create paths and txt files
26         global info
27         basePathDirectory = "Tourist_spots_5A"  
28         if not os.path.exists(basePathDirectory):  
29             os.makedirs(basePathDirectory)  
30         baiduFile = os.path.join(basePathDirectory,"BaiduSpider.txt")  
31         if not os.path.exists(baiduFile):  
32             info = codecs.open(baiduFile,‘w‘,‘utf-8‘)  
33         else:  
34             info = codecs.open(baiduFile,‘a‘,‘utf-8‘)  
35       
36         #locate input  notice: 1.visit url by unicode 2.write files  
37         print name.rstrip(‘\n‘) #delete char ‘\n‘  
38         driver.get("http://baike.baidu.com/")  
39         elem_inp = driver.find_element_by_xpath("//form[@id=‘searchForm‘]/input")  
40         elem_inp.send_keys(name)  
41         elem_inp.send_keys(Keys.RETURN)  
42         info.write(name.rstrip(‘\n‘)+‘\r\n‘)  #codecs不支持‘\n‘换行
43         #print driver.current_url  
44         time.sleep(5)  
45   
46         #load infobox  
47         elem_name = driver.find_elements_by_xpath("//div[@class=‘basic-info‘]/dl/dt")  
48         elem_value = driver.find_elements_by_xpath("//div[@class=‘basic-info‘]/dl/dd")  
49   
50         #create dictionary key-value
51         #字典是一种散列表结构,数据输入后按特征被散列,不记录原来的数据,顺序建议元组
52         elem_dic = dict(zip(elem_name,elem_value)) 
53         for key in elem_dic:  
54             print key.text,elem_dic[key].text  
55             info.writelines(key.text+" "+elem_dic[key].text+‘\r\n‘)  
56         time.sleep(5)  
57           
58     except Exception,e: #‘utf8‘ codec can‘t decode byte  
59         print "Error: ",e  
60     finally:  
61         print ‘\n‘  
62         info.write(‘\r\n‘)  
63   
64 #Main function  
65 def main():
66     global info
67     #By function get information   
68     source = open("Tourist_spots_5A_BD.txt",‘r‘)  
69     for name in source:  
70         name = unicode(name,"utf-8")  
71         if u‘故宫‘ in name: #else add a ‘?‘  
72             name = u‘北京故宫‘  
73         getInfobox(name)  
74     print ‘End Read Files!‘  
75     source.close()  
76     info.close()  
77     driver.close()  
78   
79 main()  

#设置编码utf-8
import sys 
reload(sys)  
sys.setdefaultencoding(‘utf-8‘)
#显示当前默认编码方式
print sys.getdefaultencoding()

 1 import codecs
 2 
 3 #用codecs提供的open方法来指定打开的文件的语言编码,它会在读取的时候自动转换为内部unicode
 4 if not os.path.exists(baiduFile):  
 5     info = codecs.open(baiduFile,‘w‘,‘utf-8‘)  
 6 else:  
 7     info = codecs.open(baiduFile,‘a‘,‘utf-8‘)
 8     
 9 #该方法不是io故换行是‘\r\n‘
10 info.writelines(key.text+":"+elem_dic[key].text+‘\r\n‘)