为什么选择python做爬虫

 1 import urllib
 2 import urllib.request
 3 
 4 def loadPage(url,filename):
 5 """
 6 作用：根据url发送请求，获取html数据;
 7 :param url:
 8 :return:
 9 """
10 request=urllib.request.Request(url)
11 html1= urllib.request.urlopen(request).read()
12 return html1.decode('utf-8')
13 
14 def writePage(html,filename):
15 """
16 作用将html写入本地
17 
18 :param html: 服务器相应的文件内容
19 :return:
20 """
21 with open(filename,'w') as f:
22 f.write(html)
23 print('-'*30)
24 def tiebaSpider(url,beginPage,endPage):
25 """
26 作用贴吧爬虫调度器，负责处理每一个页面url;
27 :param url:
28 :param beginPage:
29 :param endPage:
30 :return:
31 """
32 for page in range(beginPage,endPage+1):
33 pn=(page - 1)*50
34 fullurl=url+"&pn="+str(pn)
35 print(fullurl)
36 filename='第'+str(page)+'页.html'
37 html= loadPage(url,filename)
38 
39 writePage(html,filename)
40 
41 
42 
43 if __name__=="__main__":
44 kw=input('请输入你要需要爬取的贴吧名:')
45 beginPage=int(input('请输入起始页'))
46 endPage=int(input('请输入结束页'))
47 url='https://tieba.baidu.com/f?'
48 kw1={'kw':kw}
49 key = urllib.parse.urlencode(kw1)
50 fullurl=url+key
51 tiebaSpider(fullurl,beginPage,endPage)