京东秒杀爬取失败

Ygh6688

为什么爬取会报出这个错误,请大佬指出错误
raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)

1. # -*- coding:utf-8 -*-
   
2. import requests
   
3. from urllib.parse import urlencode
   
4. from pyquery import PyQuery as pq
   
5. 
   
6. headers = {
   
7. 'authority': 'api.m.jd.com',
   
8. 'method': 'GET',
   
9. 'path': '/api?appid=o2_channels&functionId=pcMiaoShaAreaList&client=pc&clientVersion=1.0.0&callback=pcMiaoShaAreaList&jsonp=pcMiaoShaAreaList&body=%7B%7D&_=1616493634850',
   
10. 'scheme': 'https',
    
11. 'accept': '*/*',
    
12. 'accept-encoding': 'gzip, deflate, br',
    
13. 'accept-language': 'zh-CN,zh;q=0.9',
    
14. 'cache-control': 'no-cache',
    
15. 'cookie': 'TrackID=1xqFc2zG8fzZ1DgwKjzbAIXwVgdxq8FbvVKVqpOKGunmnVJEYBI433iK3erNEOqqlcmLqavJbDvZr2JNhepHCNAGITbTvWpllfIw-nwF9K75IiMD_x_iqu26W6K8iLUQP; pinId=iJEuA68AAzuroBl9QC0OE7V9-x-f3wj7; unpl=V2_ZzNtbUFRSh1xD0YDLBFbDWJQR18SVBZHcgEUUCkaDFZhAREOclRCFnUUR1dnGlwUZAAZXEVcQhVFCEdkexhdBGYBEVhAVXMlRQtGZHopXAJnARpdRVVEFnAAQFR9HFoEZgMRXEVncxV9DHZUehhdBWEAFVpDVkIlPFQEDT9FDDViAxNeQlVDE3Y4R2R6KQprZwITXENWRhZxAAtUfBleDWcEEFpBUksTdQ5DUnoYXAZmBCJcclQ%3d; shshshfpb=iwzn640W8VGfTaBwT9diXwA%3D%3D; shshshfp=e61376a46a79972cf4294c5e3f30b834; shshshfpa=be283d73-f7de-8663-87fe-95e9027adae4-1609231016; __jdu=16139163624971747001206; __jda=122270672.16139163624971747001206.1613916362.1613916364.1616492719.2; __jdv=122270672|direct|-|none|-|1616492718785; __jdc=122270672; areaId=7; ipLoc-djd=7-412-46823-0; __jdb=122270672.4.16139163624971747001206|2.1616492719; 3AB9D23F7A4B3C9B=H4M7Z6JQXGHM7T6JJFVYTEZQOMQZPPJTAVQWEY7SLGMC3KRLRYSYY6WIMADV2ZHF63PG567ARBKBDFCG7QMLOLVU2I',
    
16. 'pragma': 'no-cache',
    
17. 'referer': 'https://miaosha.jd.com/',
    
18. 'sec-ch-ua': '"Google Chrome";v="89", "Chromium";v="89", ";Not A Brand";v="99"',
    
19. 'sec-ch-ua-mobile': '?0',
    
20. 'sec-fetch-dest': 'script',
    
21. 'sec-fetch-mode': 'no-cors',
    
22. 'sec-fetch-site': 'same-site',
    
23. 'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36'
    
24. }
    
25. base_url = 'https://api.m.jd.com/api?'
    
26. 
    
27. def get_page():
    
28.     parmes = {
    
29.         'appid': 'o2_channels',
    
30.         'functionId': 'pcMiaoShaAreaList',
    
31.         'client': 'pc',
    
32.         'clientVersion': '1.0.0',
    
33.         'callback': 'pcMiaoShaAreaList',
    
34.         'jsonp': 'pcMiaoShaAreaList',
    
35.         'body': '{}',
    
36.         '_': '1616493634850'
    
37.     }
    
38.     url = base_url + urlencode(parmes)
    
39.     try:
    
40.         response = requests.get(url=url,headers=headers)
    
41.         if response.status_code == 200:
    
42.             return response.json()
    
43.     except requests.ConnectionError as e:
    
44.         print('错误',e.args)
    
45. def parse_page(json):
    
46.     if json:
    
47.         items = json.get('pcMiaoShaAreaList')
    
48.         for item in items:
    
49.             item = item.get('miaoShaList')
    
50.             miaosha = {}
    
51.             miaosha['名字'] = pq(item.get('shortWname')).text()
    
52.             miaosha['秒杀时间'] = item.get('startTimeShow')
    
53.             miaosha['折扣'] = item.get('rate')
    
54.             miaosha['秒杀后价格'] = item.get('miaoShaPrice')
    
55.             miaosha['秒杀前价格'] = item.get('jdPrice')
    
56.             yield miaosha
    
57. if __name__ == '__main__':
    
58.     json = get_page()
    
59.     results = parse_page(json)
    
60.     for i in results:
    
61.         print(i)

复制代码

suchocolate

print(response.text)看一下就知道了，返回的不是直接的json数据。

Ygh6688

suchocolate 发表于 2021-3-27 17:28
print(response.text)看一下就知道了，返回的不是直接的json数据。

那这种怎么办呢？