1 import requests
 2 from fake_useragent import UserAgent
 3 from pyquery import PyQuery
 4 from urllib.parse import urlencode
 5 from requests.packages import urllib3
 6 from pymongo import MongoClient
 7
 8 # 关闭警告
 9 urllib3.disable_warnings()
10
11 base_url = 'https://m.weibo.cn/api/container/getIndex?'
12
13 # 激活本地MongoDB客户端
14 client = MongoClient('localhost',27001)
15 # 创建数据库
16 pages = client['pages']
17 # 创建集合
18 ma_yun = pages['ma_yun']
19
20 # 保存到mongoDB中
21 def save_to_mongo(result):
22     if ma_yun.insert_one(result):
23         print('saved to Mongo','已获取{number}条数据'.format(number=ma_yun.count()))
24
25 # 生成UA
26 def create_user_agent():
27     ua = UserAgent(use_cache_server=False)
28     # print(ua.chrome)
29     return ua.chrome
30
31 # 生成headers
32 def create_headers():
33     headers = {
34         'User-Agent': create_user_agent()
35     }
36     return headers
37
38 # 获取页面
39 def get_page(page):
40     # 设置参数
41     params = {
42         'sudaref':'germey.gitbooks.io',
43         'display':'0',
44         'retcode':'6102',
45         'type':'uid',
46         'value':'2145291155',
47         'containerid':'1076032145291155',
48         'page':page
49     }
50     url = base_url + urlencode(params)
51     try:
52         response = requests.get(url,create_headers(),verify=False)
53         if response.status_code == 200:
54             return response.json()
55     except requests.ConnectionError as e:
56         print('Error',e.args)
57
58 # 解析页面
59 def parse_page(json):
60     if json:
61         items = json.get('data').get('cards')
62         if items != None:
63             for item in items:
64                 item = item.get('mblog')
65                 weibo = {}
66                 weibo['id'] = item.get('id')
67                 # 将正文中的 HTML 标签去除掉
68                 weibo['text'] = PyQuery(item.get('text')).text()
69                 # 点赞数
70                 weibo['attitudes_count'] = item.get('attitudes_count')
71                 # 评论数
72                 weibo['comments_count'] = item.get('comments_count')
73                 # 发布时间
74                 weibo['datetime'] = item.get('created_at')
75                 # 转发数
76                 weibo['reposts_count'] = item.get('reposts_count')
77
78                 yield weibo
79
80 # 设置主方法进行调用其他方法
81 def main():
82     for page in range(1,30):
83         json = get_page(page)
84         results = parse_page(json)
85         for result in results:
86             save_to_mongo(result)
87
88 if __name__ == '__main__':
89     main()