1 """
 2 Version: Python3.5
 3 Author: OniOn
 4 Site: http://www.cnblogs.com/TM0831/
 5 Time: 2019/3/11 10:46
 6 """
 7 import re
 8 import queue
 9 import requests
10 from lxml import etree
11
12
13 class CrawlQueue:
14     def __init__(self):
15         """
16         初始化
17         """
18         self.q = queue.Queue()  # 爬取队列
19         self.username = input("请输入您的博客名称：")
20         self.q.put("http://www.cnblogs.com/" + self.username)
21         self.urls = ["http://www.cnblogs.com/" + self.username]  # 记录爬取过的url
22         self.result = []  # 储存阅读量数据
23
24     def request(self, url):
25         """
26         发送请求和解析网页
27         :param url: 链接
28         :return:
29         """
30         res = requests.get(url)
31         et = etree.HTML(res.text)
32         lst = et.xpath('//*[@class="postDesc"]/text()')
33         for i in lst:
34             num = i.split(" ")[5].lstrip("阅读(").rstrip(")")
35             self.result.append(int(num))
36
37         # 下一页
38         next_page = re.search('<a href="(.*?)">下一页</a>', res.text)
39         if next_page:
40             href = next_page.group().split('&nbsp;')[-1].replace('<a href="', '').replace('">下一页</a>', '')
41             if href not in self.urls:  # 确保之前没有爬过
42                 self.q.put(href)
43                 self.urls.append(href)
44
45     def get_url(self):
46         """
47         从爬取队列中取出url
48         :return:
49         """
50         if not self.q.empty():
51             url = self.q.get()
52             self.request(url)
53
54     def main(self):
55         """
56         主函数
57         :return:
58         """
59         while not self.q.empty():
60             self.get_url()
61
62
63 if __name__ == '__main__':
64     crawl = CrawlQueue()
65     crawl.main()
66     print("您的博客总阅读量为：{}".format(sum(crawl.result)))