首页 > > 网络编程 > 其它 >

Python 爬虫 (四)

2018-08-17 09:47:17来源：博客园阅读 ()

requests: 练手雪qiu网

 1 import requests
 2 import json
 3 import re
 4 import pymysql
 5 url = 'https://xueqiu.com/v4/statuses/public_timeline_by_category.json?since_id=-1&max_id=-1&count=10&category=-1'
 6 headers = {
 7     'Cookie': 'aliyungf_tc=AQAAALoQF3p02gsAUhVFebQ3uBBNZn+H; xq_a_token=584d0cf8d5a5a9809761f2244d8d272bac729ed4; xq_a_token.sig=x0gT9jm6qnwd-ddLu66T3A8KiVA; xq_r_token=98f278457fc4e1e5eb0846e36a7296e642b8138a; xq_r_token.sig=2Uxv_DgYTcCjz7qx4j570JpNHIs; _ga=GA1.2.516718356.1534295265; _gid=GA1.2.1050085592.1534295265; u=301534295266356; device_id=f5c21e143ce8060c74a2de7cbcddf0b8; Hm_lvt_1db88642e346389874251b5a1eded6e3=1534295265,1534295722; Hm_lpvt_1db88642e346389874251b5a1eded6e3=1534295722',
 8     'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36',
 9 }
10 res = requests.get(url, headers=headers) #get请求,将url和头文件一并传入
11 response = res.content.decode('utf-8')  # content 和 request下的.read()作用是一样的
12 response = json.loads(response)#分析第一个页面 从第一个页面中提取下一个Ajax请求所需要的id
13 while True:
14     if response['next_id'] != None:
15         url = 'https://xueqiu.com/v4/statuses/public_timeline_by_category.json?since_id=-1&max_id={}&count=15&category=-1'
16         fullurl = url.format(response['next_id']) #通过上面获取的id将需要浏览的下一个网页的url进行补全
17         res = requests.get(fullurl, headers=headers)
18         response = res.content.decode('utf-8')
19         response = json.loads(response) #response是个字典
20         # print(response)
21         ans_text = response['list']
22         # print(type(ans_text)) #list
23         for i in ans_text:
24             #i是字典
25             rul  = re.compile(r'"topic_title":"(.*?)",') #通过正则将需要的数据提取出来
26             rul2 = re.compile(r'"description":"(.*?)",')
27             ans1 = rul.findall(i['data'])
28             ans2 = rul2.findall(i['data'])
29             print(ans1)  #type 为list
30             print(ans2)
31             print('-' * 50)
32             
33             #将数据存到数据库中
34             connection = pymysql.connect(host='localhost',user='root',password='1234',db='xq')
35         try:
36             with connection.cursor() as cursor:
37                 # Create a new record
38                 sql = "INSERT INTO `xq_info` (`title`, `info`) VALUES (%s, %s)"
39                 cursor.execute(sql, (ans1[0],ans2[0]))
40             connection.commit()
41         finally:
42             connection.close()
43         print('&'*50)
44     else:
45         break