Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

style: format code with Autopep8, Black, isort, Ruff Formatter and Yapf #1

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

style: format code with Autopep8, Black, isort, Ruff Formatter and Yapf #1

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 9 additions & 8 deletions moviedata/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,20 +1,21 @@
import json
import os

import numpy as np
import json
from tqdm import tqdm
import pandas as pd
import os
from dotenv import load_dotenv
from tqdm import tqdm

from moviedata.analysis import *
from moviedata.helper_functions import *
from moviedata.scraping import *

try:
from urllib.request import urlretrieve
except ImportError:
from urllib import urlretrieve
from bs4 import *

import requests
from bs4 import *

load_dotenv()

from moviedata.helper_functions import *
from moviedata.analysis import *
from moviedata.scraping import *
6 changes: 3 additions & 3 deletions moviedata/helper_functions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
from moviedata import *
import base64

from moviedata import *


def encode(message: str) -> bytes:
"""
Expand All @@ -16,6 +17,5 @@ def get_page(url: str, cookies: dict) -> BeautifulSoup:
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
}
req = requests.get(
url, headers=headers, cookies=cookies)
req = requests.get(url, headers=headers, cookies=cookies)
return BeautifulSoup(req.content, "html.parser")
30 changes: 17 additions & 13 deletions moviedata/scraping.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,34 +3,38 @@

class MovieDataScraper:
def __init__(
self, base_url: str = "https://www.imdb.com", specific_url: str = "/chart/moviemeter/?ref_=nv_mv_mpm"
self,
base_url: str = "https://www.imdb.com",
specific_url: str = "/chart/moviemeter/?ref_=nv_mv_mpm",
) -> None:
self.cookies = {
"UID": os.getenv('Cookie_UID'),
"aws-ubid-main": os.getenv('Cookie_aws-ubid-main'),
"UID": os.getenv("Cookie_UID"),
"aws-ubid-main": os.getenv("Cookie_aws-ubid-main"),
}
self.BASE_URL = base_url
self.page = get_page(self.BASE_URL + specific_url, self.cookies)

def get_reviews_details(self, reviews: BeautifulSoup) -> [str, str, str]:
review_details = []
for review in reviews:
review_url = review.find('a').attrs['href']
review_three_elems = review.find(
'span', class_="three-Elements").find_all('span')
review_count, review_type = review_three_elems[0].text, review_three_elems[1].text
review_url = review.find("a").attrs["href"]
review_three_elems = review.find("span", class_="three-Elements").find_all(
"span"
)
review_count, review_type = (
review_three_elems[0].text,
review_three_elems[1].text,
)
review_details.append([review_url, review_count, review_type])
return review_details

def movie_further_details(self, movieID: str, movieUrl: str):
movie_page = get_page(self.BASE_URL + movieUrl, self.cookies)
movie_description = movie_page.find(
'span', class_="sc-a31b0662-2 geLkLc").text
movie_description = movie_page.find("span", class_="sc-a31b0662-2 geLkLc").text
movie_scores = movie_page.find(
'li', class_="ipc-inline-list__item sc-9e83797f-1 cxyOpW")
user_reviews, critic_reviews, metascore = self.get_reviews_details(
movie_scores)

"li", class_="ipc-inline-list__item sc-9e83797f-1 cxyOpW"
)
user_reviews, critic_reviews, metascore = self.get_reviews_details(movie_scores)

def movies_basic_details(self):
movies = self.page.find_all(
Expand Down