├── output
    └── .gitignore
├── requirements.txt
├── README.md
└── apkpure_get.py


/output/.gitignore:
--------------------------------------------------------------------------------
1 | *.apk
2 | 


--------------------------------------------------------------------------------
/requirements.txt:
--------------------------------------------------------------------------------
1 | progressbar2
2 | requests
3 | bs4
4 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # apkpure_get
 2 | 
 3 | This is a super simple tool for yanking APK's to reverse engineer from the APKPure service.  
 4 | It is not well written and has a zillion bugs but it works.
 5 | It is designed to be ran from other scripts. For example... If you have a list of the top 100 apps on the app store like "com.whatever.blah", do this...
 6 | 
 7 | ```
 8 | cat top_apps.txt | parallel -j 20 python apkpure_get.py
 9 | ```
10 | 
11 | I am hoping to pipeline this with automatic decompilation and analysis sometime, probably by feeding the apps downloaded to MobiSF or Jeb2 or something? idk.
12 | 


--------------------------------------------------------------------------------
/apkpure_get.py:
--------------------------------------------------------------------------------
 1 | #!/usr/bin/env python
 2 | # coding: utf-8
 3 | from __future__ import print_function
 4 | from bs4 import BeautifulSoup
 5 | import progressbar
 6 | import requests
 7 | import sys
 8 | ### XXX: hack to skip some stupid beautifulsoup warnings that I'll fix when refactoring
 9 | import warnings
10 | warnings.filterwarnings("ignore", category=UserWarning, module='bs4')
11 | 
12 | def get_apk(app_name): # XXX: this function needs refactoring/cleaning.
13 |     print("{+} getting download link for %s" %(app_name))
14 |     site = "https://apkpure.com"
15 |     url = "https://apkpure.com/search?q=%s" %(app_name)
16 |     html = requests.get(url)
17 |     parse = BeautifulSoup(html.text)
18 |     for i in parse.find("p"):
19 |         a_url = i["href"]
20 |         app_url = site + a_url + "/download?from=details"
21 |         html2 = requests.get(app_url)
22 |         parse2 = BeautifulSoup(html2.text)
23 |         for link in parse2.find_all("a",id="download_link"):
24 |             download_link = link["href"]
25 |         download_apk(app_name, download_link)
26 | 
27 | def make_progress_bar():
28 |     return progressbar.ProgressBar(
29 |         redirect_stdout=True,
30 |         redirect_stderr=True,
31 |         widgets=[
32 |             progressbar.Percentage(),
33 |             progressbar.Bar(),
34 |             ' (',
35 |             progressbar.AdaptiveTransferSpeed(),
36 |             ' ',
37 |             progressbar.ETA(),
38 |             ') ',
39 |         ])
40 | 
41 | def download_apk(app_name, download_link):
42 |     print("{+} downloading %s" %(app_name))
43 |     output_file = "output/" + app_name + ".apk"
44 |     r = requests.get(url=download_link, stream=True)
45 |     with open(output_file, 'wb') as f:
46 |         total_length = int(r.headers.get('content-length'))
47 |         bar = make_progress_bar()
48 |         bar.start(total_length)
49 |         readsofar = 0
50 |         for chunk in r.iter_content(chunk_size=1024):
51 |             if chunk:
52 |                 readsofar += len(chunk)
53 |                 bar.update(readsofar)
54 |                 f.write(chunk)
55 |                 f.flush()
56 |         bar.finish()
57 |     print("{+} done. file saved to %s" %(output_file))
58 | 
59 | def main(args):
60 |     if len(args) != 2:
61 |         sys.exit("use: %s com.blah.blah" %(args[0]))
62 |     get_apk(args[1])
63 | 
64 | if __name__ == "__main__":
65 |     main(args=sys.argv)
66 | 


--------------------------------------------------------------------------------