python使用关键字爬取url

python网路爬虫 --------- 使用百度输入的关键字搜索内容然后爬取搜索内容的url

开发环境：windows7+python3.6.3

开发语言：Python

开发工具：pycharm

第三方软件包：需安装lxml4.0，如果只安装lxml会出错，要需要lxml中的etree

 

废话不多说，贴上代码：

爬取数据保存以TXT格式保存，等会尝试使用Excel表格跟数据库保存。

 1 import requests,time
 2 from lxml import etree
 3 
 4 
 5 def Redirect(url):
 6     try :
 7         res = requests.get(url,timeout=10)
 8         url = res.url
 9     except Exception as e:
10         print('4',e)
11         time.sleep(1)
12     return url
13 
14 def baidu_search(wd,pn_max,sav_file_name):
15     url = 'http://www.baidu.com/s'
16     return_set = set()
17 
18     for page in range(pn_max):
19         pn = page*10
20         querystring = {'wd':wd,'pn':pn}
21         headers = {
22             'pragma':'no-cache',
23             'accept-encoding': 'gzip,deflate,br',
24             'accept-language' : 'zh-CN,zh;q=0.8',
25             'upgrade-insecure-requests' : '1',
26             'user-agent': "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:62.0) Gecko/20100101 Firefox/62.0",
27             'accept': "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
28             'cache-control': "no-cache",
29             'connection': "keep-alive",
30         }
31 
32         try :
33             response = requests.request('GET',url,headers=headers,params=querystring)
34             print('!!!!!!!!!!!!!!',response.url)
35             selector = etree.HTML(response.text,parser = etree.HTMLParser(encoding='utf-8'))
36         except Exception as e:
37             print('页面加载失败',e)
38             continue
39         with open(sav_file_name,'a+') as f:
40             for i in range(1,10):
41                 try :
42                     context = selector.xpath('//*[@id="'+str(pn+i)+'"]/h3/a[1]/@href')
43                     print(len(context),context[0])
44                     i = Redirect(context[0])
45                     print('context='+context[0])
46                     print ('i='+i)
47                     f.write(i)
48                     f.write('\n')
49                     break
50                     return_set.add(i)
51                     f.write('\n')
52                 except Exception as e:
53                     print(i,return_set)
54                     print('3',e)
55 
56     return return_set
57 
58 if __name__ == '__main__':
59     wd = '网络贷款'
60     pn = 100
61     save_file_name = 'save_url_soup.txt'
62     return_set = baidu_search(wd,pn,save_file_name)
View Code

 

posted @ 2018-10-21 17:54  a_dong  阅读(4664)  评论(0)  编辑  收藏  举报