Google Play Store Scraper

from distutils . filelist import findall

from unicodedata import name

from xml . be . ElementPath import findtext

from bs4 import BeautifulSoup

import pandas as pd

import requests

import os

url =( ' https://play.google.com/store/search?q=vibrator%20apps&c=apps ' )

source = requests . get ( url )

soup = BeautifulSoup ( source.text , ' html.parser ' )

single = soup . find ( 'div' , class_ = " fUEl2e " )

data = {

'Question' : [ "" ],

'A' : [ "" ],

}

df = pd . DataFrame ( data )

df . to_csv ( '/Users/jitendersingh/Documents/test.csv' , mode = 'a' , index = False , header = True )

print ( "sheet created successfully." )

sheet = pd . read_csv ( '/Users/jitendersingh/Documents/test.csv' , squeeze = True , usecols =[ "Question" , "A" ])

delete = sheet . drop ( sheet.index [ [ 0 ]], axis = 0 , inplace = True ) #delete first row

save = sheet . to_csv ( '/Users/jitendersingh/Documents/test2.csv' ) #save file but index also deletes

bones . remove ( '/Users/jitendersingh/Documents/test.csv' )

link2 = pd . read_csv ( '/Users/jitendersingh/Documents/test2.csv' , squeeze = True , usecols =[ "Question" , "A" ]) #again open file for correct index

save = link2 . to_csv ( '/Users/jitendersingh/Documents/test.csv' ) #save file with correct index

bones . remove ( '/Users/jitendersingh/Documents/test2.csv' )

print ( sheet )

for singles in single :

mylist = singles . find ( 'a' , class_ = "Si6A0c Gy4nib" )[ 'href' ]

myappname = singles . find ( 'div' , class_ = "ubGTjb" ) . text

data = {

'Question' : [ myappname + ":- " ],

'To' : [ "https://play.google.com" + mylist + "" ],

}

df = pd . DataFrame ( data )

df . to_csv ( '/Users/jitendersingh/Documents/test.csv' , mode = 'a' , index = True , header = False )

print ( "Data appended successfully." )

link = pd . read_csv ( '/Users/jitendersingh/Documents/test.csv' , nrows = 10 , squeeze = True , usecols =[ "Question" , "A" ])

# new = link.reset_index() # add index in new file / try to run this code when upload new file

save = link . to_csv ( '/Users/jitendersingh/Documents/test.csv' ) #save file with correct index

appurl = link . loc [ 0 , 'Question' ]

tabname = link . loc [ 0 , 'A' ]

appsource = requests . get ( appurl )

finder = BeautifulSoup ( appsource.text , ' html.parser ' )

myname = finder . find ( 'h1' , class_ = "Fd93Bb F5UCq p5VxAd" ).span. text

myrating = finder . find ( 'div' , class_ = " TT9eCd " ). text

mydown = finder . find_all ( 'div' , class_ = "ClM7O" )[ 1 ].text

mylogo = finder . find_all ( 'div' , class_ = "Mqg6jb Mhrnjf" )

for logo in mylogo :

finallogo = logo.find ( 'img' , class_ = 'T75of nm4vBd arM4bb' )[ "src" ] #Picture

myss = finder . find_all ( 'div' , class_ = "ULeU3b Utde2e" )

for ss in myss :

newss = ss.find ( 'img' , class_ = 'T75of B5GQxf' )[ "src" ] #Picture

newss2 = newss.replace ( "=w526-h296" , "" )

ssdata = {

'Link' : [ newss2 ],

'Status' : [ "hello" ],

}

df = pd . DataFrame ( ssdata )

df . to_csv ( '/Users/jitendersingh/Documents/ss.csv' , mode = 'a' , index = False , header = False )

print ( "ss file created successfully." )