绝地战绩数据抓取

andwp

初学python，拿绝地的战绩cha询练练手
通过对地址 https://pubgtracker.com/profile/pc/Xinyibaby-Aini?region=as
的抓包分析，逆向出数据的获取流程，最后用python模拟拿到数据。
代码写得烂，贴出来，欢迎找茬。

1. #!/usr/bin/env python
   
2. # -*- coding: utf-8 -*-
   
3. # 文件名：bgload.py
   
4. # 作者：andwp QQ：0x709933  
   
5. # 使用说明：python 2.7.10 绝地战绩数据抓取，仅解析部分数据
   
6. #   > python
   
7. #   >> import bgload
   
8. #   >> jsobj = bgload.seach('name', 'as')  
   
9. #
   
10. 
    
11. import requests
    
12. import re
    
13. import sys
    
14. import time
    
15. import urllib
    
16. import json
    
17. def runreq(url):
    
18.     user_agent = 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.20 Safari/537.36'
    
19.     payload = {'User-Agent':user_agent, 'Host':'pubgtracker.com','Accpet-Encoding':'gzip, deflate, br','Accpet-language':'zh-Hans-CN, zh-Hans; q=0.5','Upgrade-Insecure-Requests':'1', 'Referer': url}
    
20.     session = requests.Session()
    
21.     t = session.get(url, headers=payload)  
    
22.     cmpurl = urlextract(url, t.text)  
    
23.     payload = {'User-Agent':user_agent, 'Host':'pubgtracker.com','Referer':url, 'Accpet' :'text/html, application/xhtml+xml, image/jxr, */*','Accpet-Encoding':'gzip, deflate','Accpet-language':'zh-Hans-CN, zh-Hans; q=0.5', 'Upgrade-Insecure-Requests':'1'}
    
24.     print 'wait 4 load %s' % (cmpurl)
    
25.     time.sleep(3)
    
26.     t = session.get(cmpurl, headers=payload,allow_redirects=True)
    
27.     print t.status_code
    
28.     return jsonextract(t.text)
    
29. def urlextract(oriurl, context):
    
30.     tt1 = re.findall('[A-Za-z]+\=\{"[A-Za-z]+"\:\W+\}\;', context)
    
31.     tt2 = re.findall('[A-Za-z]+\.[A-Za-z]+[\+\-\*]\=\W+\;', context)
    
32.     fstr = re.sub('\=\{"', '.', tt1[0])
    
33.     fstr = re.sub('"\:', '=', fstr)
    
34.     fstr = re.sub('\}', '', fstr)
    
35. #print start
    
36.     a = []
    
37.     a.append(fstr)
    
38.     for item in tt2:
    
39.         a.append(item)
    
40.     bAry = []
    
41.     for item in a:
    
42.         temstr = re.sub('\!\+\[\]', '1', item)
    
43.         temstr = re.sub('\!\!\[\]', '1', temstr)
    
44.         temstr = re.sub('\[\]', '0', temstr)
    
45.         temstr = re.sub('\+\(\(', '(10*(', temstr)
    
46.         temstr = re.sub('\(\+', '(', temstr)
    
47.         temstr = re.sub('\.', 'tmp', temstr)
    
48.         bAry.append(temstr)
    
49.     sc = re.search('[A-Za-z]+',bAry[0]).group(0)
    
50.     tmpfeild = 'print '+ sc
    
51.     hosturl = re.match( 'https?\:\/\/\w+\.\w+', oriurl).group(0)
    
52.     urlLen = hosturl.__len__() - 8
    
53. #    bAry.append(tmpfeild)
    
54.     bAry.append('%s+=%d' % (sc, urlLen))
    
55. #    bAry.append(tmpfeild)
    
56.     for item in bAry:
    
57.         exec(item)
    
58. #        print item
    
59.     answer = locals()[sc]
    
60.     jschl_vc =  re.findall('jschl_vc"[^"]+"([^"]+)"', context)[0]
    
61.     passval = re.findall('pass"[^"]+"([^"]+)"', context)[0]
    
62.     action = re.findall('action\="([^"]+)"', context)[0]
    
63.     getargs = { 'pass': passval }
    
64.     encodeGet = urllib.urlencode(getargs)
    
65.     cmpurl = '%s%s?jschl_vc=%s&%s&jschl_answer=%s' % (hosturl, action, jschl_vc, encodeGet, answer)
    
66.     return cmpurl
    
67. def jsonextract(html):
    
68.     js = re.findall('var playerData[ |\=]+(\{"[\/|\.|\w|\d|\{|\}|\'|"|\[|\]|\;|\,|\:| |\-|\%]+\})', html)
    
69.     if js <> None and js.__len__() > 0:
    
70.         jsobject = json.loads(js[0])
    
71.         print 'Player name:%s; SteamID:%s' % (jsobject['PlayerName'], jsobject['SteamId'])
    
72.         stas = jsobject['Stats']
    
73.         i = -1
    
74.         if stas <> None:
    
75.             i = stas.__len__()
    
76.         while i > 0:
    
77.             i-=1
    
78.             print 'Region:%s ; Season:%s; Match:%s' % (stas[i]['Region'],stas[i]['Season'],stas[i]['Match'])
    
79.             stasInfo = stas[i]['Stats']
    
80.             if stasInfo <> None:
    
81.                 for info in stasInfo:
    
82.                     print '%s:%s\tcategory:%s' % (info['field'],info['displayValue'],info['category'])
    
83.         return js[0]
    
84.     else:
    
85.         return html
    
86. 
    
87. def seach(name, region):
    
88.     '''执行cha询方法
    
89.     [url=home.php?mod=space&uid=47252]@name[/url] 用户ID
    
90.     @region 区域 亚洲：AS 欧洲：EU 南美：NA 澳洲：OC 南韩/日本：JPKR 东南亚：SEA  所有区域统计：AGG
    
91.     '''
    
92.     urlstr = 'https://pubgtracker.com/profile/pc/%s?region=%s' % (name, region)
    
93.     return runreq(urlstr)
    
94. if __name__ == "__main__":
    
95.     '''    测试方法，测试执行的用户 '''
    
96.     seach(name = 'Xinyibaby-Aini', region = 'as')

复制代码

运行结果：

输出

1150129654

666666666666666666666

q374702102

感谢分享，支持楼主！

Awesome·LYG

这个网站应该不用抓包吧？别人有api说明呢