I've been using this scraper to scrape critic reviews for this URL: https://www.rottentomatoes.com/m/avengers_endgame/reviews Although, I've been struggling with how to go through additional pages as this currently scrapes critic reviews of the first page. Does anyone know how I would go about this?
import selenium
from selenium import webdriver
import pandas as pd
driver = webdriver.Chrome()
driver.get("https://www.rottentomatoes.com/m/avengers_endgame/reviews")
review_1df = pd.DataFrame(columns=['Date', 'Reviewer', 'Website', 'Review', 'Score'])
dates = []
reviews = []
scores = []
newscores = []
names = []
sites = []
results = driver.find_elements_by_class_name("review_area")
reviewnum = 1
reviewers = driver.find_elements_by_class_name("col-xs-8")
for r in results:
dates.append(r.find_element_by_class_name('subtle').text)
reviews.append(r.find_element_by_class_name('the_review').text)
revs = r.find_element_by_class_name('review_desc')
scores.append(revs.find_element_by_class_name('subtle').text)
for r in reviewers:
names.append(r.find_element_by_xpath('//*[@id="reviews"]/div[2]/div[4]/div[' +str(reviewnum)+ ']/div[1]/div[3]/a[1]').text)
sites.append(r.find_element_by_xpath('//*[@id="reviews"]/div[2]/div[4]/div[' +str(reviewnum)+']/div[1]/div[3]/a[2]/em').text)
reviewnum+=1
for score in scores:
if score == ('Full Review'):
newscores.append('no score')
else:
score2 = score[14:]
newscores.append(score2)
review_1df['Date'] = dates
review_1df['Review'] = reviews
review_1df['Score'] = newscores
review_1df['Reviewer'] = names
review_1df['Website'] = sites