Web scrape specific data from imdb project - python-3.x

Question

So i want to extract the movie scores from imdb with the score of 8.7 above.
i have done it up to here like this but i dont know what to do next
import re
import requests
from bs4 import BeautifulSoup
l = list()
r = requests.get('https://www.imdb.com/chart/top?ref_=nv_mv_250')
soup = BeautifulSoup(r.text,'html.parser')
res = soup.find_all('strong')
for x in res:
q = re.sub(r'\s+',' ',x.text)
print(q)
it gives me all the scores. i just want 8.7 and above.
and thanks for answering!

Answer 1

Okay so first of all:
The data presented is not consistent, There are two values of 200 and 206 which are indeed above the 8.7 rating but I guess don't fit the whole model of rating from 0 to 10.
I have edited the code so it is currently printing out the rating values.
Please note the expression:
if my_float >= 8.7 and my_float <= 10:
This expression not only makes sure that You get the scores equal or higher than 8.7 but also they cannot be equal or higher than the maximum rating of 10.
import re
import requests
from bs4 import BeautifulSoup
r = requests.get('https://www.imdb.com/chart/top?ref_=nv_mv_250')
soup = BeautifulSoup(r.text,'html.parser')
res = soup.find_all('strong')
for x in res:
q = re.sub(r'\s+',' ',x.text)
try:
my_float = float(q)
if my_float >= 8.7 and my_float <= 10:
print(q)
except ValueError as error:
print(error)
Hope this helps. If You wish to do anything else with the data instead of printing it out. Be sure to check list comprehensions or use another code block provided below
(I have noticed that You created an empty list l = list())
import re
import requests
from bs4 import BeautifulSoup
l = list()
r = requests.get('https://www.imdb.com/chart/top?ref_=nv_mv_250')
soup = BeautifulSoup(r.text,'html.parser')
res = soup.find_all('strong')
for x in res:
q = re.sub(r'\s+',' ',x.text)
try:
my_float = float(q)
if my_float >= 8.7 and my_float <= 10:
l.append(my_float)
print(q)
except ValueError as error:
print(error)

Answer 2

Just extract the rating convert to float and do comparison
import requests
from bs4 import BeautifulSoup as bs
r = requests.get('https://www.imdb.com/chart/top?ref_=nv_mv_250')
soup = bs(r.content, 'lxml')
for tr in soup.select('.lister-list tr'):
rating = float(tr.select_one('.imdbRating').text)
if rating >= 8.7:
print(tr.select_one('.titleColumn a').text.strip(), rating )
Less readable list comprehension:
import requests
from bs4 import BeautifulSoup as bs
r = requests.get('https://www.imdb.com/chart/top?ref_=nv_mv_250')
soup = bs(r.content, 'lxml')
results = [(tr.select_one('.titleColumn a').text.strip(), float(tr.select_one('.imdbRating').text)) for tr in soup.select('.lister-list tr') if float(tr.select_one('.imdbRating').text) >= 8.7]
print(results)

Answer 3

Following code shows how you can create a list of movies whose rating is greater or equal to 8.7 .
import re
import requests
from bs4 import BeautifulSoup
l = list()
r = requests.get('https://www.imdb.com/chart/top?ref_=nv_mv_250')
soup = BeautifulSoup(r.text,'html.parser')
s = soup.find_all("tbody", class_="lister-list")
desired_list = []
for movie in s[0].findChildren("tr" , recursive=False):
title = movie.find_all("a")
rating = movie.find_all("strong")
q = re.sub(r'\s+',' ',rating[0].text)
try:
rating = float(q)
if rating >= 8.7:
desired_list.append((rating, title[1].contents[0]))
except Exception as e:
print e
print desired_list