Last active
August 29, 2019 12:06
-
-
Save stefanpejcic/0bc219fc1853831bf428a8be5c951a16 to your computer and use it in GitHub Desktop.
IMDB rating for movies in cinema with python
This file contains 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
# -*- coding: UTF-8 -*- | |
from splinter import Browser | |
import sys | |
executable_path = {'executable_path':'C:\Program Files (x86)\Google\Chrome\Application\chrome.exe'} | |
#browser = Browser('chrome', **executable_path) | |
movie_titles = [] | |
movie_ratings = [] | |
with Browser('chrome', **executable_path) as cinema_browser: | |
url = "http://www.cinemaone.ro/movies/" | |
cinema_browser.visit(url) | |
div = cinema_browser.find_by_xpath('//div[@class="title"]') | |
prev_title = 'null' | |
for link in div: | |
links = link.find_by_tag('a') | |
if prev_title != links.first.value: | |
print (links.first.value) | |
movie_titles.append(links.first.value) | |
prev_title = links.first.value | |
with Browser('chrome', **executable_path) as imdb_browser: | |
url = "http://www.imdb.com/" | |
for title in movie_titles: | |
imdb_browser.visit(url) | |
imdb_browser.fill('q', title) | |
button = imdb_browser.find_by_id('navbar-submit-button') | |
button.click() | |
if imdb_browser.is_text_present('title'): | |
print("Yes, the official website was found for " + title) | |
h = imdb_browser.find_by_xpath('//td[@class="result_text"]') | |
link = h.find_by_tag('a') | |
link.first.click() | |
try: | |
rating = imdb_browser.find_by_xpath('//span[@itemprop="ratingValue"]').value | |
movie_ratings.append(rating) | |
except: | |
movie_ratings.append('N/A') | |
else: | |
print("No," + title + " wasn't found...") | |
count = 0 | |
current = 0 | |
def print_row(title, rating): | |
print(' %-45s %-15s ' % (title, rating)) | |
print('\n\n\n') | |
print_row ('TITLE', 'RATING') | |
print_row ('-----', '------') | |
for data in movie_titles: | |
print_row(movie_titles[count], movie_ratings[count]) | |
#print ((movie_titles[count] + ' \t\t\t ' + movie_ratings[count])) | |
count = count + 1 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment