Applying some changes and modifications

README.md

@@ -1,9 +1,25 @@
 # movie-py-cli
-A simple script for fetching movie details right from the terminal
+
+A simple script for fetching movie details right from the terminal.
 
 # Requirements
+
  1. Requests
  2. BeautifulSoup4
- 3. Colorama
-# Usage
-![Screenshot](https://user-images.githubusercontent.com/29385192/36164961-073b7642-1114-11e8-93b3-6718b54bc00b.PNG)
+
+# Packages Installation
+
+Simply install the required packages with pip as below:
+
+    $ pip install -r requirements.txt
+
+# How to Use:
+
+For using it, simply change directory to the main folder (movie-py-cli), run the script as below by passing the title of your desired movie to retreive its information.
+(Note that this script is written with Python 3.~.)
+
+    $ python3 movie-py.py peaceful warrior
+
+# Screenshot
+
+![Screenshot from 2021-04-11 19-21-03](https://user-images.githubusercontent.com/16654946/114309842-e38cf000-9afd-11eb-9461-46f8ff1e40f3.png)

movie-py.py

@@ -1,71 +1,128 @@
+from utils import bcolors, Cleaner
 import sys
+import time
 import requests
 from bs4 import BeautifulSoup
-import time
-from colorama import init,Fore
-init(convert=True)
+from itertools import cycle
+import threading
+
+
+def animated_progress():
+    global stop
+    print()
+    steps = ["⢿", "⣻", "⣽", "⣾", "⣷", "⣯", "⣟", "⡿"]
+    for step in cycle(steps):
+        print(bcolors.BLUE + bcolors.ITALIC + f'\rScrapping... {step}' + bcolors.ENDC, end='', flush=True)
+        if stop:
+            print(bcolors.BLUE + bcolors.ITALIC + f"\rScrapping Done!" + bcolors.ENDC, flush=True)
+            print()
+            break
+
+def main():
+    # Call the `animated_progress` func in a different thread
+    global stop
+    stop = False
+    t = threading.Thread(target=animated_progress)
+    t.start()
+    # Variable definition for 'txt-block' to prevent NameError exception
+    movie_budget = 'N/A'
+    movie_opening = 'N/A'
+    movie_usa_gross = 'N/A'
+    movie_world_gross = 'N/A'
+    movie_ratio = 'N/A'
+    movie_tag_lines = 'N/A'
+    movie_also_known = 'N/A'
+    movie_country = 'N/A'
+    try:
+        # args = 'peaceful warrior'
+        # User's desired movie
+        args = sys.argv[1:]
+        if not args:
+            stop = True
+            time.sleep(1)
+            print(bcolors.WARNING + bcolors.BOLD + 'NO FILM TITLE IS PROVIDED!' + bcolors.ENDC)
+            sys.exit(1)
+        else:
+            movie = (' ').join(args)
+        # Scrape the page and do the assignments
+        page = requests.get('https://www.imdb.com/find?ref_=nv_sr_fn&q=' + movie + '&s=tt')
+        soup1 = BeautifulSoup(page.content, 'html.parser')
+        movie_id = soup1.select(".findList tr a")[0].get('href')
+        movie_link = "http://www.imdb.com" + movie_id
+        mlink_page = requests.get(movie_link)
+        soup2 = BeautifulSoup(mlink_page.content, 'html.parser')
+        title_nyear = soup2.select(".title_wrapper h1")[0].text
+        movie_title = title_nyear[0:len(title_nyear) - 8]
+        movie_year = title_nyear[len(title_nyear) - 6:len(title_nyear) - 2]
+        movie_rating = soup2.select(".ratingValue span")[0].text if soup2.select(".ratingValue span") else None
+        meta_score = soup2.select(".metacriticScore")
+        meta_score = meta_score[0].text.strip() if meta_score else None
+        content_rating = soup2.find('meta',{'itemprop':'contentRating'})
+        content_rating = content_rating['content'].strip() if content_rating else None
+        movie_length = soup2.select(".subtext time")[0].text.strip() if soup2.select(".subtext time") else 'N/A'
+        genres_ndate = [i.text for i in soup2.select(".subtext a")]
+        release_date = genres_ndate[-1].strip()
+        for i in soup2.find_all("div","txt-block"):
+            if i.h4:
+                if i.h4.text == "Budget:":movie_budget = i.h4.next_element.next_element.strip()
+                if i.h4.text == "Opening Weekend USA:":movie_opening = i.h4.next_element.next_element.strip()[:-1]
+                if i.h4.text == "Gross USA:":movie_usa_gross = i.h4.next_element.next_element.strip()[:-1]
+                if i.h4.text == "Cumulative Worldwide Gross:":movie_world_gross = i.h4.next_element.next_element.strip()[:-1]
+                if i.h4.text == "Aspect Ratio:":movie_ratio = i.h4.next_element.next_element.strip()
+                if i.h4.text == "Taglines:":movie_tag_lines = i.h4.next_element.next_element.strip()
+                if i.h4.text == "Also Known As:":movie_also_known = i.h4.next_element.next_element.strip()
+                if i.h4.text == "Country:":movie_country = i.h4.next_sibling.next_element.text.strip()
+        movie_genres = ""
+        for x in range(len(genres_ndate) - 1):
+            movie_genres = movie_genres + ',' + genres_ndate[x]
+        movie_genres = movie_genres[1:]
+        movie_desc = soup2.select(".summary_text")[0].text.strip()
+        # Movie cast extraction
+        movie_cast = [i.text.strip().replace('\n', ' ') for i in soup2.select(".credit_summary_item")]
+        # Make a dictionary of movie cast
+        dict_cast = {}
+        for item in movie_cast:
+            # Create a dictionary of the casts
+            dict_cast[item[:item.find(':')]] = item[item.find(':')+1:]
+        # Get rid of useless characters
+        cleaned_movie_cast = Cleaner()
+        movie_cast = cleaned_movie_cast.text_cleaner(dict_cast=dict_cast)
+        movie_director = movie_cast['Director'] if movie_cast.get('Director') else (movie_cast['Creator'] if movie_cast.get('Creator') else 'N/A')
+        movie_actors = movie_cast['Stars'] if movie_cast.get('Stars') else 'N/A'
 
-print(Fore.LIGHTBLACK_EX+"Loading...")
-time.sleep(0.5)
-print(Fore.LIGHTBLACK_EX+"Please wait...\n")
+        # After scraping, stop the `animated_progress` func and print the results
+        stop = True
+        time.sleep(1)
 
-try:
-    args = sys.argv[1:]
-    movie = (' ').join(args)
-    page = requests.get('http://www.imdb.com/find?ref_=nv_sr_fn&q=' + movie + '&s=tt');
-    soup1 = BeautifulSoup(page.content, 'html.parser')
-    movieid = soup1.select(".findList tr a")[0].get('href')
-    movielink = "http://www.imdb.com" + movieid
-    mlinkpage = requests.get(movielink)
-    soup2 = BeautifulSoup(mlinkpage.content, 'html.parser')
-    titlenyear = soup2.select(".title_wrapper h1")[0].text
-    movietitle = titlenyear[0:len(titlenyear) - 8]
-    movieyear = titlenyear[len(titlenyear) - 6:len(titlenyear) - 2]
-    movierating = soup2.select(".ratingValue span")[0].text
-    metascore = soup2.select(".metacriticScore")
-    metascore = metascore[0].text.strip() if metascore else None
-    contentrating = soup2.find('meta',{'itemprop':'contentRating'})
-    contentrating = contentrating['content'].strip() if contentrating else None
-    movielength = soup2.select(".subtext time")[0].text.strip()
-    genresndate = [i.text for i in soup2.select(".subtext a")]
-    releasedate = genresndate[-1].strip()
-    moviegenres = ""
-    for i in soup2.find_all("div","txt-block"):
-        if i.h4:
-            if i.h4.text=="Budget:":moviebudget = i.h4.next_element.next_element.strip()
-            if i.h4.text=="Opening Weekend USA:":movieopening = i.h4.next_element.next_element.strip()[:-1]
-            if i.h4.text=="Gross USA:":movieusagross = i.h4.next_element.next_element.strip()[:-1]
-            if i.h4.text=="Cumulative Worldwide Gross:":movieworldgross = i.h4.next_element.next_element.strip()[:-1]
-            if i.h4.text=="Aspect Ratio:":movieratio = i.h4.next_element.next_element.strip()
-            if i.h4.text=="Taglines:":movietaglines = i.h4.next_element.next_element.strip()
-            if i.h4.text=="Also Known As:":moviealsoknown = i.h4.next_element.next_element.strip()
-            if i.h4.text=="Country:":moviecountry = i.h4.next_sibling.next_element.text.strip()
-    for x in range(len(genresndate) - 1):
-        moviegenres = moviegenres + ',' + genresndate[x]
-    moviegenres = moviegenres[1:]
-    moviedesc = soup2.select(".summary_text")[0].text.strip()
-    moviecast = [i.text for i in soup2.select(".credit_summary_item span a span")]
-    moviedirector = moviecast[0]
-    movieactors = moviecast[3] + ',' + moviecast[4] + ',' + moviecast[5];
+        # Print the results
+        print(bcolors.RED + "Title: " + bcolors.BOLD + bcolors.GREEN + movie_title + bcolors.ENDC)
+        if movie_rating:
+            print(bcolors.RED + "IMDB Rating: " + bcolors.BOLD + bcolors.GREEN + movie_rating + "/10" + bcolors.ENDC)
+        if meta_score:
+            print(bcolors.RED + "Metascore: " + bcolors.BOLD + bcolors.GREEN + meta_score + "/100" + bcolors.ENDC)
+        print(bcolors.RED + "Length: " + bcolors.BOLD + bcolors.GREEN + movie_length + bcolors.ENDC)
+        print(bcolors.RED + "Year: " + bcolors.BOLD + bcolors.GREEN + movie_year + bcolors.ENDC)
+        print(bcolors.RED + "Genre: " + bcolors.BOLD + bcolors.GREEN + movie_genres + bcolors.ENDC)
+        print(bcolors.RED + "Description: " + bcolors.ENDC + movie_desc)
+        print(bcolors.RED + "Release date: " + bcolors.BOLD + bcolors.GREEN + release_date + bcolors.ENDC)
+        if content_rating:
+            print(bcolors.RED + "Rating: " + bcolors.BOLD + bcolors.GREEN + content_rating + bcolors.ENDC)
+        print(bcolors.RED + "Director: " + bcolors.BOLD + bcolors.GREEN + movie_director + bcolors.ENDC)
+        print(bcolors.RED + "Lead Cast: " + bcolors.BOLD + bcolors.GREEN + movie_actors + bcolors.ENDC)
+        print(bcolors.RED + "Country: " + bcolors.BOLD + bcolors.GREEN + movie_country + bcolors.ENDC)
+        print(bcolors.RED + "Also Known As: " + bcolors.BOLD + bcolors.GREEN + movie_also_known + bcolors.ENDC)
+        print(bcolors.RED + "Budget: " + bcolors.BOLD + bcolors.GREEN + movie_budget + bcolors.ENDC)
+        print(bcolors.RED + "Opening Weekend USA: " + bcolors.BOLD + bcolors.GREEN + movie_opening + bcolors.ENDC)
+        print(bcolors.RED + "Gross USA: " + bcolors.BOLD + bcolors.GREEN + movie_usa_gross + bcolors.ENDC)
+        print(bcolors.RED + "Cumulative Worldwide Gross: " + bcolors.BOLD + bcolors.GREEN + movie_world_gross + bcolors.ENDC)
+        print(bcolors.RED + "Ratio: " + bcolors.BOLD + bcolors.GREEN + movie_ratio + bcolors.ENDC)
+        print(bcolors.RED + "Taglines: " + bcolors.BOLD + bcolors.GREEN + movie_tag_lines + bcolors.ENDC)
+        print(bcolors.RED + "URL: " + bcolors.BOLD + bcolors.GREEN + movie_link + bcolors.ENDC)
+    except Exception as e:
+        stop = True
+        time.sleep(1)
+        print(bcolors.ITALIC + bcolors.WARNING + "Something goes wrong!\nError: {}".format(e), bcolors.ENDC)
+        sys.exit(1)
 
-    print(Fore.LIGHTRED_EX + "Title: " + Fore.LIGHTGREEN_EX + movietitle)
-    print(Fore.LIGHTRED_EX + "IMDB Rating: " + Fore.LIGHTYELLOW_EX + movierating + "/10")
-    if metascore: print(Fore.LIGHTRED_EX + "Metascore: " + Fore.LIGHTYELLOW_EX + metascore + "/100")
-    print(Fore.LIGHTRED_EX + "Length: " + Fore.LIGHTCYAN_EX + movielength)
-    print(Fore.LIGHTRED_EX + "Year: " + Fore.LIGHTMAGENTA_EX + movieyear)
-    print(Fore.LIGHTRED_EX + "Genre: " + Fore.LIGHTBLUE_EX + moviegenres)
-    print(Fore.LIGHTRED_EX + "Description: " + Fore.LIGHTWHITE_EX + moviedesc)
-    print(Fore.LIGHTRED_EX + "Release date: " + Fore.LIGHTCYAN_EX + releasedate)
-    if contentrating: print(Fore.LIGHTRED_EX + "Rating: " + Fore.LIGHTCYAN_EX + contentrating)
-    print(Fore.LIGHTRED_EX + "Director: " + Fore.LIGHTBLACK_EX + moviedirector)
-    print(Fore.LIGHTRED_EX + "Lead Cast: " + Fore.LIGHTBLACK_EX + movieactors)
-    print(Fore.LIGHTRED_EX + "Country: " + Fore.LIGHTBLUE_EX + moviecountry)
-    print(Fore.LIGHTRED_EX + "Also Known As: " + Fore.LIGHTBLUE_EX + moviealsoknown)
-    print(Fore.LIGHTRED_EX + "Budget: " + Fore.LIGHTBLUE_EX + moviebudget)
-    print(Fore.LIGHTRED_EX + "Opening Weekend USA: " + Fore.LIGHTBLUE_EX + movieopening)
-    print(Fore.LIGHTRED_EX + "Gross USA: " + Fore.LIGHTBLUE_EX + movieusagross)
-    print(Fore.LIGHTRED_EX + "Cumulative Worldwide Gross: " + Fore.LIGHTBLUE_EX + movieworldgross)
-    print(Fore.LIGHTRED_EX + "Ratio: " + Fore.LIGHTBLUE_EX + movieratio)
-    print(Fore.LIGHTRED_EX + "Taglines: " + Fore.LIGHTBLUE_EX + movietaglines)
-except:
-    print(Fore.LIGHTRED_EX+"Something's wrong,Try Again Later")
+if __name__ == '__main__':
+    main()

requirements.txt

@@ -1,9 +1,9 @@
-beautifulsoup4==4.6.0
+beautifulsoup4==4.9.3
 bs4==0.0.1
-certifi==2018.1.18
-chardet==3.0.4
-colorama==0.3.9
-idna==2.6
+certifi==2020.12.5
+chardet==4.0.0
+idna==2.10
 pkg-resources==0.0.0
-requests==2.18.4
-urllib3==1.22
+requests==2.25.1
+soupsieve==2.2.1
+urllib3==1.26.4

utils.py

@@ -0,0 +1,42 @@
+class bcolors:
+    '''
+    Bash script styling
+
+    Source: https://stackoverflow.com/a/42449998/12537848
+    '''
+    HEADER = '\033[95m'
+    RED = '\033[91m'
+    GREEN = '\033[92m'
+    BLUE = '\033[94m'
+    WARNING = '\033[93m'
+    BOLD = '\033[1m'
+    ITALIC = '\033[3m'
+    UNDERLINE = '\033[4m'
+    ENDC = '\033[0m'
+
+
+class Cleaner:
+    '''
+    Get rid of useless contents
+    '''
+
+    def __init__(self):
+        pass
+
+    def text_cleaner(self, dict_cast):
+        '''
+        Gets rid of useless characters
+
+        Input:
+            :param: text -> A dictionary of movie casts to be gotten rid of the useless characters.
+            :type: dict
+
+        Returns:
+            A cleaned string dictionary
+        '''
+        cleaned_text = {}
+        for item in dict_cast:
+            pos = dict_cast[item].find('|')
+            cleaned_text[item] = (dict_cast[item][:pos].strip())
+
+        return cleaned_text