Last active
September 1, 2020 12:22
-
-
Save cstayyab/b99db5c8a5c1f492f85dc708d81a4882 to your computer and use it in GitHub Desktop.
Fetch App Information from APKPure using BeautifulSoup in Python
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Tested for APKPure Version 1.3.7 (this is website version that prints in Web Browser Console everytime a page from APK Pure Loads) | |
# Working as of September 1, 2020 | |
import requests | |
import cssutils | |
from bs4 import BeautifulSoup | |
def getAppDataFromAPKPure(apkpure_url): # Example: https://apkpure.com/subway-surfers-1/com.kiloo.subwaysurf | |
headers = { | |
'Access-Control-Allow-Origin': '*', | |
'Access-Control-Allow-Methods': 'GET', | |
'Access-Control-Allow-Headers': 'Content-Type', | |
'Access-Control-Max-Age': '3600', | |
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:79.0) Gecko/20100101 Firefox/79.0' | |
} | |
req = requests.get(apkpure_url, headers) | |
soup = BeautifulSoup(req.content, 'html.parser') | |
desc_element = soup.select("div.description > div.content") | |
description = desc_element[0].decode_contents() if desc_element is not None and len(desc_element) > 0 else "" | |
whatsnew_element = soup.select("div#whatsnew > div:nth-child(3)") | |
whatsnew = whatsnew_element[0].decode_contents() if whatsnew_element is not None and len(whatsnew_element) > 0 else "" | |
videoThumbTag_element = soup.select("a.details-tube") | |
videoThumbURL = "" | |
videoURL = "" | |
screenshots = [] | |
if videoThumbTag_element is not None and len(videoThumbTag_element) > 0: | |
style = videoThumbTag_element[0]['style'] | |
sheet = cssutils.css.CSSStyleSheet() | |
sheet.add("dummy_selector { %s }" % style) | |
videoThumbURL = list(cssutils.getUrls(sheet))[0] | |
videoURL = videoThumbTag_element[0]['data-src'] | |
screenshots_elements = soup.select("a.mpopup > img") | |
screenshots = [scrn["src"] for scrn in screenshots_elements] | |
return { | |
"description": description, | |
"whatsnew": whatsnew, | |
"videoThumbnail": videoThumbURL, | |
"videoURL": videoURL, | |
"screenshots": screenshots | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment