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
import pandas as pd | |
from bs4 import BeautifulSoup | |
import requests | |
from time import sleep | |
import datetime | |
def clean_string(column): | |
return column.apply(lambda x: x.replace("\n",'',2)).apply(lambda x: x.replace(' ','')) | |
def scrape_reviews(PATH, n_pages, sleep_time = 0.3): |
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
var BASE64_MARKER = ';base64,'; | |
function convertDataURIToBinary(dataURI) { | |
var base64Index = dataURI.indexOf(BASE64_MARKER) + BASE64_MARKER.length; | |
var base64 = dataURI.substring(base64Index); | |
var raw = window.atob(base64); | |
var rawLength = raw.length; | |
var array = new Uint8Array(new ArrayBuffer(rawLength)); | |
for(i = 0; i < rawLength; i++) { |